SocratiCode

"There is only one good, knowledge, and one evil, ignorance." — Socrates

Your AI reads code. SocratiCode understands it.

The open-source codebase context engine: give any AI instant automated knowledge of your entire codebase (and infrastructure) — at scale, zero configuration, fully private, completely free.

Kindly sponsored by Altaire Limited

🛡️ Need MCP governance together with codebase context? See our sibling project JanuScope — the local-first MCP policy proxy: tool blocking, SQL-mutation gate, PII redaction, audit, rate-limit.

If SocratiCode has been useful to you, please ⭐ star this repo — it helps others discover it — and share it with your dev team and fellow developers!

💬 Questions or just want to chat? Join us on Discord.

☁️ SocratiCode Cloud (private beta) — Hosted, shared team index built on the same engine as the open-source version, plus SSO, audit logs, branch-aware indexing, and VPC / air-gapped deployment options. The open-source core remains free forever. Request early access →

One thing, done well: deep codebase intelligence — zero setup, no bloat, fully automatic. SocratiCode gives AI assistants deep semantic understanding of your codebase — hybrid search, cross-project search, polyglot code dependency graphs, symbol-level impact analysis and flow, interactive HTML graph explorer for visual navigation, and searchable context artifacts (database schemas, API specs, infra configs, architecture docs). Zero configuration — add it to any MCP host, or install the Native Plugin for Claude Code, Cursor, VS Code Copilot, Codex or Gemini CLI. It manages everything automatically.

Production-ready, battle-tested on enterprise-level large repositories (up to and over ~40 million lines of code). Batched, automatic resumable indexing checkpoints progress — pauses, crashes, restarts, and interruptions don't lose work. The file watcher keeps the index automatically updated at every file change and across sessions. Multi-branch, multi-repo and multi-agent ready — multiple AI agents can work on the same codebase simultaneously, sharing a single index with automatic coordination and zero configuration.

Private and local by default — Docker handles everything, no API keys required, no data leaves your machine. Cloud ready for embeddings (OpenAI, Google Gemini) and Qdrant, and a full suite of configuration options are all available when you need them.

Code intelligence that belongs to you, AI and host agnostic — your codebase's understanding lives with the code, not locked to any one assistant, IDE or model. And because SocratiCode pre-computes the hard parts (blast radius, call-flow, dependency traversal), smaller models can handle architectural complex tasks that would otherwise need top-tier reasoning, saving even more on token cost.

The first Qdrant‑based MCP/Claude Plugin/Skill that pairs auto‑managed, zero‑config local Docker deployment with AST‑aware code chunking, hybrid semantic + BM25 (RRF‑fused) code search, polyglot dependency graphs with circular‑dependency visualisation, symbol‑level Impact Analysis (blast‑radius & call‑flow tracing across 18 languages), and searchable infra/API/database artifacts in a single focused, zero-config and easy to use code intelligence engine.

Benchmarked on VS Code (2.45M lines): SocratiCode uses 61% less context, 84% fewer tool calls, and is 37x faster than grep‑based exploration — tested live with Claude Opus 4.6. See the full benchmark →

Contents

• Quick Start
• Plugins
• Why SocratiCode
• Features
• Prerequisites
• Example Workflow
• Agent Instructions
• Configuration
• Language Support
• Ignore Rules
• Context Artifacts
• Environment Variables
• Docker Resources
• Testing
• Why Not Just Grep?
• FAQ
• Community
• SocratiCode Cloud
• License

Quick Start

Only Docker (running) required.

One-click install — Claude Code, VS Code and Cursor:

All MCP hosts — add the following to your mcpServers (Claude Desktop, Windsurf, Cline, Roo Code) or servers (VS Code project-local .vscode/mcp.json) config:

"socraticode": {
  "command": "npx",
  "args": ["-y", "socraticode"]
}

Claude Code — install the plugin (recommended, includes workflow skills for best results):

From your shell:

claude plugin marketplace add giancarloerra/socraticode
claude plugin install socraticode@socraticode

Or from within Claude Code:

/plugin marketplace add giancarloerra/socraticode
/plugin install socraticode@socraticode

Auto-updates: After installing, enable automatic updates by opening /plugin → Marketplaces → select socraticode → Enable auto-update.

Or as MCP only (without skills):

claude mcp add socraticode -- npx -y socraticode

Updating: npx caches the package after the first run. To get the latest version, clear the cache and restart your MCP host: rm -rf ~/.npm/_npx && claude mcp restart socraticode. Alternatively, use npx -y socraticode@latest in your config to always check for updates on startup (slightly slower).

OpenCode — add to your opencode.json (or opencode.jsonc):

{
  "mcp": {
    "socraticode": {
      "type": "local",
      "command": ["npx", "-y", "socraticode"],
      "enabled": true
    }
  }
}

OpenAI Codex CLI — add to ~/.codex/config.toml:

[mcp_servers.socraticode]
command = "npx"
args = ["-y", "socraticode"]

Restart your host. On first use SocratiCode automatically pulls Docker images, starts its own Qdrant and Ollama containers, and downloads the embedding model — one-time setup, ~5 minutes depending on your connection. After that, it starts in seconds.

First time on a project — ask your AI: "Index this codebase". Indexing runs in the background; ask "What is the codebase index status?" to monitor progress. Depending on codebase size and whether you're using GPU-accelerated Ollama or cloud embeddings, first-time indexing can take anywhere from a few seconds to a few minutes (it takes under 10 minutes to first-index +3 million lines of code on a Macbook Pro M4). Once complete it doesn't need to be run again, you can search, explore the dependency graph, and query context artifacts.

Every time after that — just use the tools (search, graph, etc.). On server startup SocratiCode automatically detects previously indexed projects, restarts the file watcher, and runs an incremental update to catch any changes made while the server was down. If indexing was interrupted, it resumes automatically from the last checkpoint. You can also explicitly start or restart the watcher with codebase_watch { action: "start" }.

macOS / Windows on large codebases: Docker containers can't use the GPU. For medium-to-large repos, install native Ollama (auto-detected, no config change needed) for Metal/CUDA acceleration, or use OpenAI embeddings for speed without a local install. Full details.

Recommended: For best results, add the Agent Instructions to your AI assistant's system prompt or project instructions file (CLAUDE.md, AGENTS.md, etc.). The key principle — search before reading — helps your AI use SocratiCode's tools effectively and avoid unnecessary file reads.

Claude Code users: If you installed the SocratiCode plugin, the Agent Instructions are included automatically as skills — no need to add them to your CLAUDE.md. The plugin also bundles the MCP server, so you don't need a separate claude mcp add.

Advanced: cloud embeddings (OpenAI / Google), external Qdrant, remote Ollama, native Ollama, and dozens of tuning options are all available. See Configuration below.

Plugins

SocratiCode is available as a native plugin on multiple AI coding platforms. Plugins bundle the MCP server with workflow skills and agent instructions — one install gives you everything.

Extension vs plugin (what to install in VS Code / Cursor):

• The extension (Marketplace / Open VSX listing) is a regular VS Code-style extension. It auto-registers the MCP server in Copilot agent mode, Cline, Continue, Roo Code, plus adds a sidebar, status-bar item, interactive graph webview, walkthrough and palette commands. Best for most users.
• The plugins (/add-plugin for Cursor, Chat: Install Plugin From Source for VS Code Copilot) bundle the MCP server plus skills + agent instructions that teach the AI to use SocratiCode tools effectively. Best when you want the agent to be opinionated about using SocratiCode.
• You can install both. The extension only registers the MCP server once, so they don't conflict.
• VS Code Copilot note: the chat plugins feature is in preview. Enable it with chat.plugins.enabled: true in your VS Code settings.

Codex local plugin install: Clone the repo and register it in your personal plugin marketplace:

bash

git clone https://github.com/giancarloerra/socraticode.git ~/.agents/plugins/socraticode

Then add it to ~/.agents/plugins/marketplace.json:

json

{
  "plugins": [
    {
      "name": "socraticode",
      "path": "~/.agents/plugins/socraticode"
    }
  ]
}

Codex will discover the plugin from .codex-plugin/plugin.json on next launch.

All other MCP hosts (Claude Desktop, Windsurf, Cline, Roo Code, OpenCode): Use the MCP config — works with any host that supports the MCP protocol.

Why SocratiCode

I built SocratiCode because I regularly work on existing, large, and complex codebases across different languages and need to quickly understand them and act. Existing solutions were either too limited, insufficiently tested for production use, or bloated with unnecessary complexity. I wanted a single focused tool that does deep codebase intelligence well — zero setup, no bloat, fully automatic — and gets out of the way.

Built-in Code Search vs SocratiCode

_{¹ VS Code Copilot: remote index via GitHub / Azure DevOps; local "External Ingest" gradually rolling out. ² LSP-based Find References / Go to Definition (Usages tool), not a full dependency graph. ³ Cursor: embeddings processed on Cursor servers (encrypted in transit and at rest). ⁴ VS Code Copilot: remote index hosted on GitHub / Azure DevOps. Sources: Cursor docs, Claude Code docs, VS Code Copilot docs.}

🔌 The context lives with your codebase, not with the assistant. Built-in indexes (Cursor's, Copilot's) are tied to that one tool — switch assistants and you start from scratch. SocratiCode is independent: index once, then plug it into Claude Code, Cursor, Copilot, Windsurf, your own private model, or all of them at once. They share the same understanding of your code.

On VS Code's 2.45M‑line codebase, SocratiCode answers architectural questions with 61% less data, 84% fewer steps, and 37× faster response than a grep‑based AI agent. Full benchmark →

Features

• Hybrid code search — Built on Qdrant, a purpose-built vector database with HNSW indexing, concurrent read/write, and payload filtering. Each chunk stores both a dense vector and a BM25 sparse vector; the Query API runs both sub-queries in a single round-trip and fuses results with Reciprocal Rank Fusion (RRF). Semantic search handles conceptual queries like "authentication middleware" even when those exact words don't appear in the code. BM25 handles exact identifier and keyword lookups. You get the best of both in every query with no tuning required.
• Configurable Qdrant — Use the built-in Docker Qdrant (default, zero config) or connect to your own instance (self-hosted, remote server, or Qdrant Cloud). Configure via QDRANT_MODE, QDRANT_URL, and QDRANT_API_KEY environment variables.
• Configurable Ollama — Use the built-in Docker Ollama (default, zero config) or point to your own Ollama instance (native install -GPU access-, remote server, etc.). Configure via OLLAMA_MODE, OLLAMA_URL, EMBEDDING_MODEL and EMBEDDING_DIMENSIONS environment variables.
• Multi-provider embeddings — Switch between Local Ollama (private, GPU access), Docker Ollama (zero-config), OpenAI (text-embedding-3-small, fastest), Google Gemini (gemini-embedding-001, free tier), LM Studio (local OpenAI-compatible server), or LiteLLM (proxy gateway in front of 100+ providers) with a single environment variable. No provider-specific configuration files.
• Private & secure — Everything runs on your machine — your code never leaves your network. The default Docker setup includes Ollama (embeddings) and Qdrant (vector storage) with no external API calls. No API costs, no token limits. Suitable for air-gapped and on-premises environments. Optional cloud providers (OpenAI, Google Gemini, Qdrant Cloud) are available but never required.
• AST-aware chunking — Files are split at function/class boundaries using AST parsing (ast-grep), not arbitrary line counts. This produces higher-quality search results. Falls back to line-based chunking for unsupported languages.
• Polyglot code dependency graph — Static analysis of import/require/use/include statements using ast-grep for 18+ languages. No external tools like dependency-cruiser required. Detects circular dependencies and generates visual Mermaid diagrams.
• Language-agnostic — Works with every programming language, framework, and file type out of the box. No per-language parsers to install, no grammar files to maintain, no "unsupported language" limitations. If your AI can read it, SocratiCode can index it.
• Incremental indexing — After the first full index, only changed files are re-processed. Content hashes are persisted in Qdrant so state survives server restarts.
• Batched & resumable indexing — Files are processed in batches of 50, with progress checkpointed to Qdrant after each batch. If the process crashes or is interrupted, the next run automatically resumes from where it left off — already-indexed files are skipped via hash comparison. This keeps peak memory low and makes indexing reliable even for very large codebases.
• Live file watching — Optionally watch for file changes and keep the index updated in real time (debounced 2s). Watcher also invalidates the code graph cache.
• Parallel processing — Files are scanned and chunked in parallel batches (50 at a time) for fast I/O, while embedding generation and upserts are batched separately for optimal throughput.
• Multi-project — Index multiple projects simultaneously. Each gets its own isolated collection with full project path tracking.
• Cross-project search — Search across multiple related projects in a single query. Link projects via .socraticode.json or the SOCRATICODE_LINKED_PROJECTS env var, then set includeLinked: true on codebase_search. Results are tagged with project labels and ranked by cosine similarity, which is comparable across projects of very different sizes (falling back to rank fusion when a cosine is unavailable for any hit).
• Branch-aware indexing — Maintain separate indexes per git branch by setting SOCRATICODE_BRANCH_AWARE=true. Each branch gets its own Qdrant collections, so switching branches instantly switches to the correct index. Ideal for CI/CD pipelines and PR review workflows.
• Respects ignore rules — Honors all .gitignore files (root + nested), plus an optional .socraticodeignore for additional exclusions. Includes sensible built-in defaults. .gitignore processing can be disabled via RESPECT_GITIGNORE=false. Dot-directories (e.g. .agent) can be included via INCLUDE_DOT_FILES=true.
• Custom file extensions — Projects with non-standard extensions (e.g. .tpl, .blade) can be included via EXTRA_EXTENSIONS env var or extraExtensions tool parameter. Such files are indexed as plaintext and appear as leaf nodes in the code graph (no AST chunking or symbols). To instead treat a custom extension as a real language (full AST chunking, symbols, call graph), map it with EXTENSION_LANGUAGE_MAP (e.g. .inc:php).
• Configurable infrastructure — All ports, hosts, and API keys are configurable via environment variables. Qdrant API key support for enterprise deployments.
• Enterprise-ready simplicity — No agent coordination tuning, no memory limit environment variables, no coordinator/conductor capacity knobs, no backpressure configuration. SocratiCode scales by relying on production-grade infrastructure (Qdrant, proven embedding APIs) rather than complex in-process orchestration.
• Auto-setup & zero configuration — Just install the Claude Plugin/Skill or add the MCP server to your AI host config. On first use, the server automatically checks Docker, pulls images, starts Qdrant and Ollama containers, and downloads the embedding model. No config files, no YAML, no environment variables to tune, no native dependencies to compile. Works everywhere Docker runs.
• Session resume — When reopening a previously indexed project, the file watcher starts automatically on first tool use (search, status, update, or graph query). It catches any changes made since the last session and keeps the index live — no manual action needed.
• Auto-start watcher — The file watcher is automatically activated when you use any SocratiCode tool on an indexed project. It starts after codebase_index completes, after codebase_update, and on the first codebase_search, codebase_status, or graph query. You can also start it manually with codebase_watch { action: "start" } if needed.
• Auto-build code graph — The code dependency graph is automatically built after indexing and rebuilt when watched files change. No need to call codebase_graph_build manually unless you want to force a rebuild.
• Multi-agent collaboration — Multiple AI agents (each running their own MCP instance) can work on the same codebase simultaneously and share a single index. One agent triggers indexing, all agents search against the same data. Only one watcher runs per project — every agent benefits from real-time updates. Cross-process file locking coordinates indexing and watching automatically. Ideal for workflows like one agent writing tests while another fixes code, or a planning agent and an implementation agent working in parallel.
• Cross-process safety — File-based locking (proper-lockfile) prevents multiple MCP instances from simultaneously indexing or watching the same project. Stale locks from crashed processes are automatically reclaimed. When another MCP process is already watching a project, codebase_status reports "active (watched by another process)" instead of incorrectly showing "inactive."
• Concurrency guards — Duplicate indexing and graph-build operations are prevented. If you call codebase_index while indexing is already running, it returns the current progress instead of starting a second operation.
• Graceful stop — Long-running indexing operations can be stopped safely with codebase_stop. The current batch finishes and checkpoints, preserving all progress. Re-run codebase_index to resume from where it left off.
• Graceful shutdown — On server shutdown, active indexing operations are given up to 60 seconds to complete, all file watchers are stopped cleanly, and the everything closes gracefully.
• Structured logging — All operations are logged with structured context for observability. Log level configurable via SOCRATICODE_LOG_LEVEL.
• Graceful degradation — If infrastructure goes down during watch, the watcher backs off and retries instead of crashing.

Prerequisites

Docker must be running when you use the server in the default managed mode.

The Qdrant container is managed automatically. If you set QDRANT_MODE=external and point QDRANT_URL at a remote or cloud Qdrant instance, Docker is only needed for Ollama (embeddings) in that case.

The Ollama container (embeddings) is also managed automatically in the default auto mode. SocratiCode first checks if Ollama is already running natively — if so it uses it. Otherwise it manages a Docker container for you. First-time download of the docker images or embedding models may take a few minutes, depending on your internet speed, and is required only at first launch.

Embedding performance on macOS / Windows

Docker containers on macOS and Windows cannot access the GPU (no Metal or CUDA passthrough). For small projects this is fine, but for medium-to-large codebases the CPU-only container is noticeably slower.

For best performance, install native Ollama: download and run the installer from ollama.com/download. Once Ollama is running, SocratiCode will automatically detect and use it — no extra configuration needed (first-time download of the embedding model, if not present, might take a few minutes). This gives you Metal GPU acceleration on macOS and CUDA on Windows/Linux.

If you prefer speed without a local install, see OpenAI Embeddings and Google Generative AI Embeddings below for cloud-based options. OpenAI is very fast with no local setup required. Google’s free tier is functional but rate-limited. See Environment Variables for configuration details.

Example Workflow

All tools default projectPath to the current working directory, so you never need to specify a path for the active project.

User: "Index this project"
→ codebase_index {}
  ⚡ Indexing started in the background — call codebase_status to check progress
→ codebase_status {}
  ⚠ Full index in progress — Phase: generating embeddings (batch 1/1)
  Progress: 247/1847 chunks embedded (13%) — Elapsed: 12s
→ codebase_status {}
  ✓ Indexing complete: 342 files, 1,847 chunks (took 115.2s)
  File watcher: active (auto-updating on changes)

User: "Search for how authentication is handled"
→ codebase_search { query: "authentication handling" }
  Runs dense semantic search + BM25 keyword search in parallel, fuses results with RRF
  Returns top 10 results ranked by combined relevance

User: "What files depend on the auth middleware?"
→ codebase_graph_query { filePath: "src/middleware/auth.ts" }
  Returns imports and dependents
  (graph was auto-built after indexing — no manual build needed)

User: "Show me the dependency graph"
→ codebase_graph_visualize {}
  Returns a Mermaid diagram colour-coded by language

User: "Are there any circular dependencies?"
→ codebase_graph_circular {}
  Found 2 cycles: src/a.ts → src/b.ts → src/a.ts

User: "What breaks if I rename validateUser?"
→ codebase_impact { target: "validateUser" }
  Blast radius for symbol: validateUser
  Hop 1 (3 files): src/auth/login.ts, src/api/users.ts, tests/auth.test.ts
  Hop 2 (5 files): ...

User: "What does the server entry point actually do?"
→ codebase_flow {}
  Detected 4 entry point(s):
    main (cmd/server.go:10) — well-known-name:main
    healthz (src/api/routes.ts:42) — framework:get
    ...
→ codebase_flow { entrypoint: "main" }
  └── main (cmd/server.go:10)
      ├── loadConfig (cmd/server.go:15)
      └── startServer (src/server.ts:8)
          └── ...

User: "Who calls bcryptCompare and what does it call?"
→ codebase_symbol { name: "bcryptCompare" }
  Symbol: bcryptCompare (function)
  Defined: src/auth/hash.ts:42–58
  Callers (3): ← src/auth/login.ts:12, ← src/auth/reset.ts:30 ...
  Callees (1): → compare [unique, 1 candidate]

Agent Instructions

Claude Code plugin users: These instructions are included automatically as skills in the SocratiCode plugin. You don't need to copy them into CLAUDE.md. The section below is for non-Claude Code hosts (VS Code, Cursor, Claude Desktop, etc.).

For best results, add instructions like the following to your AI assistant's project-level instructions file. The core principle: search before reading. The index gives you a map of the codebase in milliseconds; raw file reading is expensive and context-consuming.

Where to place these instructions (per IDE):

Why this matters: Installing the MCP server alone gives your agent access to SocratiCode tools, but the agent still decides when to use them. Adding these instructions to your project ensures the agent consistently prefers SocratiCode search over raw file reads, uses the graph for dependency-aware tasks, and follows the search-before-reading workflow.

## Codebase Search (SocratiCode)

This project is indexed with SocratiCode. Always use its MCP tools to explore the codebase
before reading any files directly.

### Workflow

1. **Start most explorations with `codebase_search`.**
   Hybrid semantic + keyword search (vector + BM25, RRF-fused) runs in a single call.
   - Use broad, conceptual queries for orientation: "how is authentication handled",
     "database connection setup", "error handling patterns".
   - Use precise queries for symbol lookups: exact function names, constants, type names.
   - Prefer search results to infer which files to read — do not speculatively open files.
   - **When to use grep instead**: If you already know the exact identifier, error string,
     or regex pattern, grep/ripgrep is faster and more precise — no semantic gap to bridge.
     Use `codebase_search` when you're exploring, asking conceptual questions, or don't
     know which files to look in.

2. **Follow the graph before following imports.**
   Use `codebase_graph_query` to see what a file imports and what depends on it before
   diving into its contents. This prevents unnecessary reading of transitive dependencies.
   - **Before modifying or deleting a file**, check its dependents with `codebase_graph_query`
     to understand the blast radius.
   - **When planning a refactor**, use the graph to identify all affected files before
     making changes.

3. **Use Impact Analysis BEFORE refactoring, renaming, or deleting code.**
   The symbol-level call graph (`codebase_impact`, `codebase_flow`, `codebase_symbol`,
   `codebase_symbols`) goes one step deeper than the file graph: it knows which
   functions and methods call which.
   - `codebase_impact` answers "what breaks if I change X?" (blast radius — every file
     that transitively calls into the target).
   - `codebase_flow` answers "what does this code do?" by tracing forward from an entry
     point. Call with no `entrypoint` to discover candidate entry points (auto-detected
     via orphans, conventional names like `main()`, framework routes, tests).
   - `codebase_symbol` gives a 360° view of one function: definition, callers, callees.
   - `codebase_symbols` lists symbols in a file or searches by name.
   - Always prefer these over reading multiple files when the question is about
     dependencies between functions, not concepts.

4. **Read files only after narrowing down via search.**
   Once search results clearly point to 1–3 files, read only the relevant sections.
   Never read a file just to find out if it's relevant — search first.

5. **Use `codebase_graph_circular` when debugging unexpected behaviour.**
   Circular dependencies cause subtle runtime issues; check for them proactively.
   Also run `codebase_graph_circular` when you notice import-related errors or unexpected
   initialisation order.

6. **Check `codebase_status` if search returns no results.**
   The project may not be indexed yet. Run `codebase_index` if needed, then wait for
   `codebase_status` to confirm completion before searching.

7. **Leverage context artifacts for non-code knowledge.**
   Projects can define a `.socraticodecontextartifacts.json` config to expose database
   schemas, API specs, infrastructure configs, architecture docs, and other project
   knowledge that lives outside source code. These artifacts are auto-indexed alongside
   code during `codebase_index` and `codebase_update`.
   - Run `codebase_context` early to see what artifacts are available.
   - Use `codebase_context_search` to find specific schemas, endpoints, or configs
     before asking about database structure or API contracts.
   - If `codebase_status` shows artifacts are stale, run `codebase_context_index` to
     refresh them.

### When to use each tool

| Goal | Tool |
|------|------|
| Understand what a codebase does / where a feature lives | `codebase_search` (broad query) |
| Find a specific function, constant, or type | `codebase_search` (exact name) or grep if you know already the exact string |
| Find exact error messages, log strings, or regex patterns | grep / ripgrep |
| See what a file imports or what depends on it | `codebase_graph_query` |
| Check blast radius before modifying or deleting a file | `codebase_impact` (symbol-level) or `codebase_graph_query` (file-level) |
| **What breaks if I change function X?** | `codebase_impact target=X` |
| **What does this entry point actually do?** | `codebase_flow entrypoint=X` |
| **List entry points in this codebase** | `codebase_flow` (no args) |
| **Who calls this function and what does it call?** | `codebase_symbol name=X` |
| **What functions/classes exist in this file?** | `codebase_symbols file=path` |
| **Search for symbols by name across the project** | `codebase_symbols query=X` |
| Spot architectural problems | `codebase_graph_circular`, `codebase_graph_stats` |
| Visualise module structure | `codebase_graph_visualize` |
| Verify index is up to date | `codebase_status` |
| Discover what project knowledge (schemas, specs, configs) is available | `codebase_context` |
| Find database tables, API endpoints, infra configs | `codebase_context_search` |

Why semantic search first? A single codebase_search call returns ranked, deduplicated snippets from across the entire codebase in milliseconds. This gives you a broad map at negligible token cost — far cheaper than opening files speculatively. Once you know which files matter, targeted reading is both faster and more accurate. That said, grep remains the right tool when you have an exact string or pattern — use whichever fits the query.

Keep the connection alive during indexing. Indexing runs in the background — the MCP server continues working even when not actively responding to tool calls. However, some MCP hosts might disconnect an idle MCP connection after a period of inactivity, which might cut off the background process. Instruct your AI to call codebase_status roughly every 60 seconds after starting codebase_index until it completes. This keeps the host connection active and provides real-time progress.

Configuration

Install

Claude Code plugin (recommended for Claude Code users)

The SocratiCode plugin bundles both the MCP server and workflow skills that teach Claude how to use the tools effectively. One install gives you everything:

From your shell:

claude plugin marketplace add giancarloerra/socraticode
claude plugin install socraticode@socraticode

Or from within Claude Code:

/plugin marketplace add giancarloerra/socraticode
/plugin install socraticode@socraticode

The plugin includes:

• MCP server — all 21 SocratiCode tools (search, graph, context artifacts, etc.)
• Exploration skill — teaches Claude the search-before-reading workflow
• Management skill — guides setup, indexing, watching, and troubleshooting
• Explorer agent — delegatable subagent for deep codebase analysis

If you previously installed SocratiCode as a standalone MCP (claude mcp add socraticode), remove it after installing the plugin to avoid duplicates: claude mcp remove socraticode

Auto-updates: Third-party plugins don't auto-update by default. To enable automatic updates, open /plugin → Marketplaces → select socraticode → Enable auto-update. To update manually:

From your shell:

claude plugin marketplace update socraticode
claude plugin update socraticode@socraticode

Or from within Claude Code:

/plugin marketplace update socraticode
/plugin update socraticode@socraticode

Configuring environment variables: SocratiCode works with zero config for most users (local Ollama + managed Qdrant). If you need cloud embeddings, a remote Qdrant, or other customisation:

1. Claude Code settings (recommended) — add to ~/.claude/settings.json:

   json

   {
     "env": {
       "EMBEDDING_PROVIDER": "openai",
       "OPENAI_API_KEY": "sk-..."
     }
   }
   

   This works in all environments — CLI, VS Code, and JetBrains.

2. Shell profile — set vars in ~/.zshrc or ~/.bashrc:

   bash

   export EMBEDDING_PROVIDER=openai
   export OPENAI_API_KEY=sk-...
   

   Works when Claude Code is launched from a terminal. Note: IDE-launched sessions (e.g. VS Code opened from Finder/Dock) may not inherit shell profile variables — use option 1 instead.

Restart Claude Code after changing variables. See Environment Variables for all options.

npx (recommended for all other MCP hosts — no installation)

Requires Node.js 18+ and Docker (running). Already covered in Quick Start above, add the following to your mcpServers (Claude Desktop, Windsurf, Cline, Roo Code) or servers (VS Code project-local .vscode/mcp.json) config:

    "socraticode": {
      "command": "npx",
      "args": ["-y", "socraticode"]
    }

Zed

Add SocratiCode as a custom MCP server in Zed's settings (Zed > Settings > Settings or cmd+,). Under context_servers, add:

{
  "context_servers": {
    "socraticode": {
      "command": "npx",
      "args": ["-y", "socraticode"],
      "env": {}
    }
  }
}

To pass environment variables (e.g. for cloud embeddings or branch-aware indexing), add them to the env object:

{
  "context_servers": {
    "socraticode": {
      "command": "npx",
      "args": ["-y", "socraticode"],
      "env": {
        "EMBEDDING_PROVIDER": "openai",
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

Zed auto-reads AGENTS.md from the project root for agent instructions. Copy the Agent Instructions block into your project's AGENTS.md to ensure the agent uses SocratiCode tools effectively. You can also add them as a default rule in Zed's Rules Library (agent: open rules library).

From source (for contributors)

git clone https://github.com/giancarloerra/socraticode.git
cd socraticode
npm install
npm run build

Then use node /absolute/path/to/socraticode/dist/index.js in place of npx -y socraticode in the config examples below.

MCP host config variants

All env options below apply equally to the npx install. Just add the "env" block to the npx config shown above.

Add to your MCP settings - mcpServers (Claude Desktop, Windsurf, Cline, Roo Code) or servers (VS Code project-local .vscode/mcp.json):

Default (zero config, from source)

Using npx? Your config is already in Quick Start. Add any "env" block from the examples below as needed.

{
  "mcpServers": {
    "socraticode": {
      "command": "node",
      "args": ["/absolute/path/to/socraticode/dist/index.js"]
    }
  }
}

Tip: The default OLLAMA_MODE=auto detects native Ollama (port 11434) on startup and uses it if available, otherwise falls back to a managed Docker container. To make your config self-documenting, add an "env" block with explicit values. See Environment Variables for all options.

External Ollama (native install)

If you have Ollama installed natively, set OLLAMA_MODE=external and point to your instance:

{
  "mcpServers": {
    "socraticode": {
      "command": "node",
      "args": ["/absolute/path/to/socraticode/dist/index.js"],
      "env": {
        "OLLAMA_MODE": "external",
        "OLLAMA_URL": "http://localhost:11434"
      }
    }
  }
}

The embedding model is pulled automatically on first use. To pre-download: ollama pull nomic-embed-text

Remote Ollama server

{
  "mcpServers": {
    "socraticode": {
      "command": "node",
      "args": ["/absolute/path/to/socraticode/dist/index.js"],
      "env": {
        "OLLAMA_MODE": "external",
        "OLLAMA_URL": "http://gpu-server.local:11434"
      }
    }
  }
}

OpenAI Embeddings

Use OpenAI's cloud embedding API instead of local Ollama. Requires an API key.

{
  "mcpServers": {
    "socraticode": {
      "command": "node",
      "args": ["/absolute/path/to/socraticode/dist/index.js"],
      "env": {
        "EMBEDDING_PROVIDER": "openai",
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

Defaults: EMBEDDING_MODEL=text-embedding-3-small, EMBEDDING_DIMENSIONS=1536. For higher quality, use text-embedding-3-large with EMBEDDING_DIMENSIONS=3072.

Google Generative AI Embeddings

Use Google's Gemini embedding API. Requires an API key.

{
  "mcpServers": {
    "socraticode": {
      "command": "node",
      "args": ["/absolute/path/to/socraticode/dist/index.js"],
      "env": {
        "EMBEDDING_PROVIDER": "google",
        "GOOGLE_API_KEY": "AIza..."
      }
    }
  }
}

Defaults: EMBEDDING_MODEL=gemini-embedding-001, EMBEDDING_DIMENSIONS=3072.

LM Studio (local, OpenAI-compatible)

LM Studio ships with a Local Server that exposes an OpenAI-compatible API on http://localhost:1234/v1. Use this provider when you want to host embedding models in LM Studio (e.g. when LM Studio is your single source for both chat and embedding models, or when you want a Mac/Windows-friendly desktop UI for managing GGUF models).

{
  "mcpServers": {
    "socraticode": {
      "command": "node",
      "args": ["/absolute/path/to/socraticode/dist/index.js"],
      "env": {
        "EMBEDDING_PROVIDER": "lmstudio",
        "EMBEDDING_MODEL": "nomic-embed-text-v1.5",
        "EMBEDDING_DIMENSIONS": "768"
      }
    }
  }
}

No defaults — EMBEDDING_MODEL and EMBEDDING_DIMENSIONS are required. LM Studio has no out-of-the-box embedding model; you load one yourself in the Local Server tab. SocratiCode fails fast if either is missing.

Optional: LMSTUDIO_URL (default http://localhost:1234/v1) for non-default ports; LMSTUDIO_API_KEY if you've enabled API key auth in LM Studio; LMSTUDIO_ALLOW_MISSING_MODEL_LISTING=true for OpenAI-compatible servers that have no /v1/models endpoint (see below).

This provider also drives any other server that speaks the OpenAI embeddings API. Single-model servers such as HuggingFace Text Embeddings Inference (TEI) fix the model at startup and answer /v1/models with a 404, so readiness needs LMSTUDIO_ALLOW_MISSING_MODEL_LISTING=true to fall back to probing /v1/embeddings:

{
  "mcpServers": {
    "socraticode": {
      "command": "node",
      "args": ["/absolute/path/to/socraticode/dist/index.js"],
      "env": {
        "EMBEDDING_PROVIDER": "lmstudio",
        "LMSTUDIO_URL": "http://localhost:8080/v1",
        "EMBEDDING_MODEL": "BAAI/bge-m3",
        "EMBEDDING_DIMENSIONS": "1024",
        "LMSTUDIO_ALLOW_MISSING_MODEL_LISTING": "true"
      }
    }
  }
}

EMBEDDING_MODEL is whatever the server was started with (TEI's --model-id) and EMBEDDING_DIMENSIONS must match that model's output width — the probe checks it and fails fast on a mismatch, since without /v1/models there is nothing else to verify against.

LiteLLM (proxy gateway, 100+ providers)

LiteLLM Proxy Server exposes an OpenAI-compatible /v1/embeddings endpoint and fans out to any of 100+ underlying providers (OpenAI, Anthropic, Cohere, Voyage, HuggingFace, Bedrock, Vertex AI, Ollama, ...). Use this provider when you want centralised key management (one virtual key per developer instead of N provider keys spread across MCP configs), fallback / load balancing between embedding backends, or provider-agnostic indexes that survive a backend swap.

{
  "mcpServers": {
    "socraticode": {
      "command": "node",
      "args": ["/absolute/path/to/socraticode/dist/index.js"],
      "env": {
        "EMBEDDING_PROVIDER": "litellm",
        "LITELLM_API_KEY": "sk-...",
        "EMBEDDING_MODEL": "text-embedding-3-small",
        "EMBEDDING_DIMENSIONS": "1536"
      }
    }
  }
}

LITELLM_API_KEY, EMBEDDING_MODEL, and EMBEDDING_DIMENSIONS are all required. LiteLLM proxies always authenticate (master key or virtual key from /key/generate); the alias name and underlying dimension come from your config.yaml. SocratiCode fails fast on any missing piece.

Optional: LITELLM_URL (default http://localhost:4000/v1) — must include the /v1 suffix; LITELLM_SEND_DIMENSIONS=true to forward the OpenAI dimensions parameter through the proxy (only safe for Matryoshka-aware backends like text-embedding-3-* or voyage-3 — non-Matryoshka backends reject the request).

This is a client for the LiteLLM proxy server, not the LiteLLM Python library, and it does not route provider/model strings itself. It sends EMBEDDING_MODEL to LITELLM_URL verbatim and requires that name to appear in the proxy's /v1/models. To reach a backend such as OpenRouter, register it in the proxy's config.yaml model_list (set model_name to the value you put in EMBEDDING_MODEL, and litellm_params.model to e.g. openrouter/qwen/qwen3-embedding-8b); the proxy does the routing and SocratiCode just sends the alias. Pointing LITELLM_URL directly at a non-LiteLLM endpoint works only if that endpoint is OpenAI-compatible, lists your EMBEDDING_MODEL under /v1/models, and accepts it under its own native model id (no LiteLLM provider/ prefix).

Git Worktrees (shared index across directories)

If you use git worktrees — or any workflow where the same repository lives in multiple directories — each path would normally get its own Qdrant index. This means redundant embedding and storage for what is essentially the same codebase.

Set SOCRATICODE_PROJECT_ID to share a single index across all directories of the same project.

MCP hosts with git worktree detection (e.g. Claude Code)

Some MCP hosts (like Claude Code) resolve the project root by following git worktree links. Since worktrees point back to the main repository's .git directory, the host automatically maps all worktrees to the same project config. This means you only need to configure the MCP server once for the main checkout — all worktrees inherit it automatically.

For Claude Code, add the server with local scope from your main checkout:

cd /path/to/main-checkout
claude mcp add -e SOCRATICODE_PROJECT_ID=my-project --scope local socraticode -- npx -y socraticode

All worktrees created from this repo will automatically connect to socraticode with the shared project ID. No per-worktree setup needed.

Note: This only works for git worktrees. Separate git clones of the same repo have independent .git directories and won't share the config.

Other MCP hosts (per-project .mcp.json)

For MCP hosts that don't resolve git worktree paths, add a .mcp.json at the root of each worktree (and your main checkout):

{
  "mcpServers": {
    "socraticode": {
      "command": "npx",
      "args": ["-y", "socraticode"],
      "env": {
        "SOCRATICODE_PROJECT_ID": "my-project"
      }
    }
  }
}

Add .mcp.json to your .gitignore if you don't want it tracked.

How it works

With this config, agents running in /repo/main, /repo/worktree-feat-a, and /repo/worktree-fix-b all share the same codebase_my-project, codegraph_my-project, and context_my-project Qdrant collections.

How it works in practice:

• The semantic index reflects whichever worktree last triggered a file change — but since branches typically differ by only a handful of files, the index is 99%+ accurate for all worktrees
• Your AI agent reads actual file contents from its own worktree; the shared index is only used for discovery and navigation
• When changes merge back to main, the file watcher re-indexes the changed files and the index converges

Team-Shared Index (committed projectId)

The env-var approach above works per-machine. For a stable identifier that every teammate (and CI runner) picks up automatically, commit a projectId in .socraticode.json at the project root:

{
  "projectId": "my-project"
}

Now any checkout of the repo — regardless of where it lives on disk or which user account owns it — addresses the same codebase_my-project, codegraph_my-project, and context_my-project Qdrant collections. This is the recommended setup for teams sharing a Qdrant instance: the index is built once and benefits everyone, even across different OS users and laptops with completely different filesystem layouts.

The value must match [a-zA-Z0-9_-]+; whitespace is trimmed, and a missing or empty value falls back to the path-hash default. The SOCRATICODE_PROJECT_ID env var, when set, takes precedence over this file — handy for ad-hoc per-machine overrides without touching the repo.

Cross-Project Search (linked projects)

If you work across multiple related repositories or packages, you can search them all in a single query.

Configuration

Create a .socraticode.json file in your project root:

{
  "linkedProjects": [
    "../shared-lib",
    "/absolute/path/to/other-project"
  ]
}

Or set the SOCRATICODE_LINKED_PROJECTS environment variable (comma-separated paths):

SOCRATICODE_LINKED_PROJECTS="../shared-lib,/absolute/path/to/other-project"

Both sources are merged and deduplicated. Relative paths are resolved from the project root. Non-existent paths are silently skipped.

Usage

Pass includeLinked: true to codebase_search:

Search for "authentication middleware" with includeLinked: true

Results are ranked by cosine similarity against the query, not by each hit's position within its own project. A rank only means something inside the list it came from, so ranking on it let the top hit of a small project outrank a far stronger hit from a large one, and capped every cross-project score at 1/61 ≈ 0.016 — below the SEARCH_MIN_SCORE default of 0.10, which then discarded everything. Cosine is an absolute measure against the same query vector, so it is comparable across projects and lands on the same scale the threshold expects. Single-project search is unaffected and still uses Qdrant's server-side RRF.

If a cosine cannot be computed for every hit, ranking falls back to the previous rank fusion for that whole query rather than mixing two different measures. That is detected in three cases, each logged with the collection involved: a chunk returned without a usable dense vector, a vector of zero magnitude, and a vector whose dimensionality differs from the query's. Note the limit of that last one: it catches a collection embedded with a model of a different dimensionality, but a different model producing the same dimensionality is indistinguishable here and would still be scored, so keep linked projects on one embedding model.

In the fallback, a single hit contributes at most 1/(60+0+1) ≈ 0.0164, though a file matching as several chunks accumulates one contribution per chunk (1/61 + 1/62 ≈ 0.0325), so final scores can exceed that bound. Either way they sit far below the 0.10 default, so lower minScore for that query if you hit it.

Results are tagged with [project-name] labels showing which project each result came from. Deduplication is scoped to a single project: the same relative path in two different projects is kept as two separate results, because they are genuinely different files (your own src/util.ts and a linked project's are not interchangeable). Within one project, the higher-priority occurrence of a path wins.

Note: Each linked project must be independently indexed (codebase_index) before it can be searched.

Branch-Aware Indexing

By default, all branches of a project share the same index. When you switch branches, changed files are re-indexed by the watcher, and the index reflects the current branch state.

For workflows where you need separate, persistent indexes per branch — such as CI/CD pipelines or comparing code across branches — enable branch-aware mode:

SOCRATICODE_BRANCH_AWARE=true

With this enabled, collection names include the branch name (e.g. codebase_abc123__main, codebase_abc123__feat_my-feature). Each branch maintains its own independent index, code graph, and context artifacts.

When to use:

• CI/CD pipelines that index each branch/PR separately
• Comparing search results across branches
• Keeping a pristine main index unaffected by feature branch changes

When NOT to use:

• Local development with frequent branch switching (default shared index is more efficient)
• Projects tracked via SOCRATICODE_PROJECT_ID (explicit IDs bypass branch detection)

How it works: projectIdFromPath() detects the current git branch via git rev-parse --abbrev-ref HEAD and appends a sanitized branch suffix (e.g. feat/my-feature → feat_my-feature) to the hash-based project ID. Detached HEAD states fall back to the branchless ID.

Available tools

Once connected, 21 tools are available to your AI assistant:

Indexing

Search

Code Graph

Impact Analysis (symbol-level call graph)

A second graph layer goes one step deeper than file imports — it tracks which functions and methods call which. Use these tools BEFORE refactoring, renaming, or deleting code.

Accepted limits. The call graph is static-analysis-based — no type inference. Dynamic dispatch (getattr, obj[key](...), reflection, eval), unexpanded macros, and framework magic (Spring @Autowired, Angular DI, Rails has_many, decorator-driven routing) are invisible. Callers that reach a method only through these mechanisms will not appear in codebase_impact. Treat "zero callers" as a hint to double-check on DI-heavy codebases. codebase_graph_status reports unresolvedEdgePct as a quality signal. See DEVELOPER.md § Impact Analysis for the full list.

Interactive graph explorer

Ask your AI "show me an interactive graph of this project" (or invoke codebase_graph_visualize with mode: "interactive") and SocratiCode generates a self-contained HTML page and opens it in your default browser:

• File view — every source file as a node, imports as edges, language-coloured, circular deps in red.
• Symbol view — toggle to see functions/classes/methods as nodes with call edges (available when the symbol graph fits within the embed cap; above that threshold the file view remains and the banner points at codebase_impact for symbol-level queries).
• Sidebar — click a node to see imports / dependents / symbols-in-file / line numbers, with action buttons for blast radius and call flow.
• Right-click any node → highlights its reverse-transitive closure (who breaks if this changes).
• Live search filters and centres matching nodes. Layout switcher — Dagre / force-directed / concentric / breadth-first / grid / circle. Export PNG produces a shareable image.
• Offline-safe — Cytoscape.js + Dagre are vendored inside the SocratiCode package. No CDN, no network, works in air-gapped environments.

The output is a single HTML file (written to the OS temp dir, one per project) that you can also commit to a PR or share on Slack.

Management

Context Artifacts

Language Support

SocratiCode supports languages at three levels:

Full Support (indexing + code graph + AST chunking)

JavaScript, TypeScript, TSX, Python, Java, Kotlin, Scala, C, C++, C#, Go, Rust, Ruby, PHP, Swift, Dart, Elixir (including HEEx/EEx), Bash/Shell, HTML, CSS/SCSS, Svelte, Vue

Svelte and Vue: imports extracted from <script> blocks (re-parsed as TypeScript) and CSS @import/@require from <style> blocks (any combination of lang, scoped, module, global attributes). Path aliases from tsconfig.json/jsconfig.json compilerOptions.paths are resolved (including extends chains). SCSS partial resolution (_ prefix convention) is supported.

Python: absolute imports resolve through the import roots implied by the project's pyproject.toml files — root and nested, so uv workspaces get cross-package edges — covering both the src/ layout (packages/<dist>/src/<module>/…, what uv init --lib, hatchling and setuptools generate) and the flat layout beside each manifest, including PEP 420 namespace packages and single-module distributions. A manifest applies to a file only when it sits on that file's ancestor path or an ancestor manifest declares it a [tool.uv.workspace] member, so a sample app, docs project or checked-in sdist carrying its own manifest does not become an import root for unrelated code; only [tool.uv.workspace] is read, so poetry, pdm and hatch path-dependency monorepos get ancestor-path scoping and no cross-package edges; applicable roots are tried nearest first, so a package resolves its own modules before a sibling's. Relative imports and the project-root src//lib/ and sibling-flat conventions are unchanged — the sibling-flat fallback still takes precedence over these roots, matching CPython, which puts the script's own directory at sys.path[0].

PHP: use imports resolve through the PSR-4 prefixes declared in the project's composer.json files — root and nested, so a Composer monorepo's path packages get cross-package edges. Where no prefix matches, they resolve against the namespace and class/interface/trait/enum declarations found in the project itself, which is what reaches a package that ships "autoload": {} and registers its namespaces at run time ($loader->addNamespace(...), the WordPress-plugin norm) — no spl_autoload_register interpretation involved. Comma lists (use A\B, A\C;), groups (use A\{B, C};, including per-member function/const modifiers) and fully-qualified names (use \A\B;) are all read. require/include resolve relative paths, bare paths (source directory first, then the project root), and __DIR__ . '<literal>' / dirname(__FILE__) . '<literal>', the dominant include idiom outside Composer. They are read from the include expressions themselves, so they are found in any position — return require __DIR__ . '/routes.php'; and $config = include 'config.php'; count, while an include mentioned in a comment or quoted inside a string does not. An include joined to a run-time value (ABSPATH . '/x.php', $base . '/x.php') stays unresolved rather than guessed.

Dart: symbols (classes, mixins, enums, extensions, typedefs, functions, getters, setters, operators, constructors including named and factory, and abstract/bodyless members), call sites (method calls, cascades, constructor invocations), main() entry-point detection, and AST chunking are all tree-sitter based; import/export/part edges are extracted via regex. Intra-project package: imports (the Flutter convention) resolve through the project's pubspec.yaml files — root and nested, so pub-workspace/melos monorepos get cross-package edges — via pub's package:<name>/<rest> → <package_root>/lib/<rest> mapping; dart: and unknown package names stay external. The bundled grammar (@ast-grep/lang-dart) predates Dart 3 class modifiers (sealed/base/interface/final/mixin class) and extension type: declarations using those are skipped (with a one-time warning logged) until the upstream grammar is updated, while the rest of each file still indexes normally.

Elixir: .ex and .exs files use the ast-grep grammar for chunking. alias, import, require, and use directives resolve to in-project defmodule declarations; fully qualified calls without one of those directives remain unresolved. defmodule, def, defp, and ordinary calls produce symbols and call edges. Chunking is module-level, with large modules falling back to line windows rather than per-function chunks. defprotocol, defimpl, defguard, defmacro, and defdelegate declarations do not register symbols yet; protocol and implementation scopes are not represented, so functions inside them appear as top-level symbols. Standalone .heex and .eex templates use dedicated tree-sitter grammars for AST chunking, remote-component dependencies, and calls from embedded Elixir expressions; markup and comments are never parsed as Elixir. .leex uses the EEx grammar on a best-effort basis, safely falling back to line chunks and no extracted edges when parsing fails.

Code Graph via Regex + Indexing

Lua (require/dofile/loadfile), SASS, LESS, Stylus (CSS @import/@require extraction)

Indexing Only (hybrid search, line-based chunking)

JSON, YAML, TOML, XML, INI/CFG, Markdown/MDX, RST, SQL, R, Dockerfile, TXT, and any file matching a supported extension or special filename (Dockerfile, Makefile, Gemfile, Rakefile, etc.)

60 file extensions + 8 special filenames supported out of the box.

Extensionless files (Unix scripts, health probes, sourced libraries) are also indexed via content-based language detection when INDEX_EXTENSIONLESS is enabled (the default) — see that environment variable below.

Ignore Rules

The indexer combines three layers of ignore rules:

1. Built-in defaults — node_modules, .git, dist, build, lock files, IDE folders, etc.
2. .gitignore — All .gitignore files in the project (root and nested subdirectories). Set RESPECT_GITIGNORE=false to skip .gitignore processing entirely.
3. .socraticodeignore — Optional file for indexer-specific exclusions. Same syntax as .gitignore.

All three layers also apply to a context artifact that points at a directory, but they are resolved relative to the artifact directory, not the project root. A project-root .gitignore or .socraticodeignore governs the code index and does not reach a directory artifact. What applies to a directory artifact is the built-in defaults, the .gitignore at the artifact root and any nested .gitignore files, and a .socraticodeignore only at the artifact root. Nested .socraticodeignore files are not read. To exclude something from a directory artifact, put the pattern in one of those applicable files.

Note that a directory artifact inherits the built-in defaults in full, not just the build-output ones. Beyond __pycache__, *.pyc, dist and build, that list also covers names an artifact directory might legitimately use: env, vendor, target, out, coverage, *.map, *.log. If a directory artifact needs one of those, re-include it with a ! pattern in the .socraticodeignore at the artifact root, negating the name itself (!env). Gitignore semantics cannot re-include a file whose parent directory is excluded, so !env/** on its own does nothing. target has one additional constraint: its contents can be re-included, but target/ is skipped while discovering nested .gitignore files, so rules from target/.gitignore are not loaded. Put those rules in the .gitignore or .socraticodeignore at the artifact root instead. Files dropped by the ignore rules, by the binary check, or because they could not be read are counted in that artifact's log line when it is indexed. node_modules, .git and dot-files are pruned before the walk sees them, so they appear in no count.

Context Artifacts

Give the AI awareness of project knowledge beyond source code — database schemas, API specs, infrastructure configs, architecture docs, and more.

Setup

Create a .socraticodecontextartifacts.json file in your project root (see .socraticodecontextartifacts.json.example for a starter template):

{
  "artifacts": [
    {
      "name": "database-schema",
      "path": "./docs/schema.sql",
      "description": "Complete PostgreSQL schema — all tables, indexes, constraints, foreign keys. Use to understand what data the app stores and how tables relate."
    },
    {
      "name": "api-spec",
      "path": "./docs/openapi.yaml",
      "description": "OpenAPI 3.0 spec for the REST API. All endpoints, request/response schemas, auth requirements."
    },
    {
      "name": "k8s-manifests",
      "path": "./deploy/k8s/",
      "description": "Kubernetes deployment manifests. Shows how services are deployed, scaled, and networked."
    }
  ]
}

Each artifact has:

• name — Unique identifier (used to filter searches)
• path — Path to a file or directory (relative to project root, or absolute). Directories are read recursively, excluding: dot-files and dot-directories (.pytest_cache/, .tox/); anything matched by the ignore rules resolved against the artifact directory; and binary files, detected by a NUL byte in the first 8 KiB. Excluded files are logged with a per-directory summary count. A path pointing at a single file is read verbatim — no exclusions apply, so a declared binary file is still indexed.
• description — Tells the AI what this artifact is and how to use it

How it works

Artifacts are chunked and embedded into Qdrant using the same hybrid dense + BM25 search as code. On first search, artifacts are auto-indexed. On subsequent searches, staleness is auto-detected via content hashing — changed files are re-indexed transparently.

Because exclusions are applied before the content hash is computed, build output under an artifact directory no longer marks that artifact stale. A directory artifact indexed by an earlier version re-indexes on its next hash check if the walk previously embedded files that are now excluded — expect its chunk count to drop when it does. An artifact with nothing to exclude hashes identically and is left alone.

Usage

1. Discover: codebase_context — lists all defined artifacts and their index status
2. Search: codebase_context_search — semantic search across all artifacts (or filter by name)
3. Re-index: codebase_context_index — force re-index (usually not needed, auto-indexing handles it)
4. Clean up: codebase_context_remove — remove all indexed artifacts

Why this matters: real workflow examples

Without artifacts, the agent only sees source code. With artifacts, it has the full picture and writes code that fits your project from the start.

Database schema — You ask "add a last_login timestamp to users." The agent runs codebase_context_search for "users table", finds the schema uses snake_case columns and every table has an updated_at with a trigger. The migration it writes matches existing conventions instead of guessing.

{
  "name": "database-schema",
  "path": "./docs/schema.sql",
  "description": "Complete PostgreSQL schema — all tables, columns, types, constraints, indexes, and triggers. Check this before writing migrations to match naming conventions and existing patterns."
}

API spec — You ask "add a GET endpoint for user preferences." The agent searches the OpenAPI spec, sees all endpoints use Bearer auth, return { data, meta } wrappers, and paginate with cursor/limit. The new endpoint follows the same patterns automatically.

{
  "name": "api-spec",
  "path": "./docs/openapi.yaml",
  "description": "OpenAPI 3.0 spec for the REST API — all endpoints, request/response schemas, auth, pagination. Check this before adding or modifying endpoints to match existing conventions."
}

Domain glossary (DDD) — You ask "add a way to cancel an order." The agent searches your domain glossary, finds that cancellation is modeled as an OrderVoided event (not "cancelled"), that only orders in Confirmed status can be voided, and that the Fulfillment bounded context must be notified. The implementation uses the correct domain terms and integrates with the right bounded contexts.

{
  "artifacts": [
    {
      "name": "ubiquitous-language",
      "path": "./docs/ubiquitous-language.md",
      "description": "Domain glossary — bounded context terms, their definitions, and relationships. Always check this before naming entities, events, or commands to use the correct domain language."
    },
    {
      "name": "context-map",
      "path": "./docs/context-mapping.md",
      "description": "Bounded context map — context boundaries, relationships (shared kernel, customer-supplier, etc.), and integration patterns. Check before implementing cross-context communication."
    },
    {
      "name": "event-storming",
      "path": "./docs/event-storming/",
      "description": "Event storming output — domain events, commands, aggregates, policies, and read models. Check before adding new domain behaviour to see how it fits the existing event flows."
    }
  ]
}

The description field is the key lever. It tells the AI not just what the artifact is, but when to consult it. Write descriptions that say "check this before doing X" so the agent reaches for the artifact at the right moment.

Example artifacts

Tip: For database schemas, every major database can export its entire schema to a single file: pg_dump --schema-only (PostgreSQL), mysqldump --no-data (MySQL), sqlite3 db.sqlite .schema (SQLite). ORM schemas (Prisma, Rails, Django) are often already in your repo.

Environment Variables

SocratiCode reads configuration from environment variables. The way you pass them depends on your MCP host — the key name and file format differ across the three main config flavours. If env vars appear to be ignored, check the host's config format first — most "it's not picking up my settings" issues are a mismatched key.

Passing env vars by host

Worked examples with a few env vars set:

Standard MCP JSON — Claude Code, Claude Desktop, Windsurf, Cline, Roo Code, Cursor, VS Code Copilot:

"socraticode": {
  "command": "npx",
  "args": ["-y", "socraticode"],
  "env": {
    "QDRANT_MODE": "external",
    "QDRANT_URL": "https://xyz.qdrant.io"
  }
}

OpenCode — note environment, not env:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "socraticode": {
      "type": "local",
      "command": ["npx", "-y", "socraticode"],
      "enabled": true,
      "environment": {
        "QDRANT_MODE": "external",
        "QDRANT_URL": "https://xyz.qdrant.io"
      }
    }
  }
}

OpenAI Codex CLI — env vars go in a separate [mcp_servers.NAME.env] table:

[mcp_servers.socraticode]
command = "npx"
args = ["-y", "socraticode"]

[mcp_servers.socraticode.env]
QDRANT_MODE = "external"
QDRANT_URL = "https://xyz.qdrant.io"

The rest of this section documents the variables themselves. Pass them using whichever syntax matches your host.

Effective Index Profiles

Code and context collections persist the settings that define their stored representation. Existing collections continue using that effective profile for indexing, watcher updates, and search. Search and status resolve an unprofiled legacy collection without writing metadata; the next indexing or update operation persists the resolved profile before changing vectors. A changed embedding provider, model, dimension, context length, query or document prefix, path-inclusion setting, chunk cap, extension-language map, file-size cap, or LiteLLM dimensions flag is reported by codebase_status as pending and does not partially change the collection. Remove the collection with codebase_remove, then run codebase_index to activate the requested profile in a fresh index. Legacy collections remain usable with the released defaults for newly introduced settings; historically unavailable values are marked legacy-unverified.

Embedding Provider

Ollama Configuration (when EMBEDDING_PROVIDER=ollama)

Cloud Provider API Keys

LM Studio Configuration (when EMBEDDING_PROVIDER=lmstudio)

LiteLLM Configuration (when EMBEDDING_PROVIDER=litellm)

Qdrant Configuration

Indexing Behaviour

Important: Existing collections keep their stored effective provider, model, and dimensions when runtime settings change. codebase_status reports requested differences as pending. To activate them, remove the collection with codebase_remove, then create a fresh index with codebase_index. This explicit rebuild is required for activation, not for continued use of the existing index.

Docker Resources

SocratiCode manages Docker containers and persistent volumes:

In QDRANT_MODE=external mode, the Qdrant container and volume are not created or started — SocratiCode connects directly to the configured remote endpoint. Server-side BM25 inference (used for hybrid search) requires Qdrant v1.15.2 or later. The managed container runs v1.17.0. If you bring your own Qdrant instance, ensure it meets this minimum.

All containers use --restart unless-stopped for automatic recovery.

Why non-standard ports? SocratiCode intentionally uses non-default ports for its managed containers — 16333/16334 instead of Qdrant's defaults (6333/6334), and 11435 instead of Ollama's default (11434). This avoids conflicts with any Qdrant or Ollama instance you may already be running locally. All ports are overridable via environment variables if needed.

Testing

SocratiCode has a comprehensive test suite across unit, integration, and end-to-end layers.

Prerequisites

• Unit tests: No external dependencies required.
• Integration & E2E tests: Require Docker running with Qdrant and Ollama containers. Containers are managed automatically by the test infrastructure.

Running Tests

# Run all tests
npm test

# Run only unit tests (no Docker needed)
npm run test:unit

# Run integration tests (requires Docker)
npm run test:integration

# Run end-to-end tests (requires Docker)
npm run test:e2e

# Watch mode (re-runs on file changes)
npm run test:watch

# With coverage report
npm run test:coverage

Test Architecture

Integration and E2E tests that require Docker are automatically skipped when Docker is not available.

Why Not Just Grep?

Modern evaluations on real repositories show that hybrid lexical + semantic code search consistently outperforms plain grep once you care about natural-language queries, large codeb