CICADA

Official

by wende · Python

Code intelligence MCP server for 17+ programming languages.

CICADA (io.github.wende/cicada) — Model Context Protocol (MCP) Server

The io.github.wende/cicada server provides code intelligence for AI assistants across 17+ programming languages. It focuses on contextual analysis, discovery, and attribution, using context compaction to deliver token-efficient access to languages such as Elixir, Python, TypeScript, JavaScript, and Rust.

🛠️ Key Features

Code intelligence with contextual analysis, discovery, and attribution
Context compaction for AI code assistants
Access to 17+ programming languages

🚀 Use Cases

Enable structured, token-efficient code context for AI assistants
Support code understanding across multiple languages (e.g., Elixir, Python, Rust)

⚡ Developer Benefits

Designed for tighter context via compaction (token-efficiency is emphasized in the source)

⚠️ Limitations

No tool count or specific tool behavior is provided in the available server data

Topics

aielixirindexermcpragcode-intelligencetoolscode-searchdevtoolslocal-firstpython

README.md18 KBView on GitHub

image

CICADA

WARNING

⚠️ Disclaimer — Today's AI agents operate completely differently from when this project was conceived. In current benchmarks, using a code intelligence tool yields little to no advantage for frontier models. CICADA is discontinued, and I'd advise against using it or any other "code intelligence" tool.

Code Intelligence: Contextual Analysis, Discovery, and Attribution

Context compaction for AI code assistants – Give your AI structured, token-efficient access to 17+ languages including Elixir, Python, TypeScript, JavaScript, Rust, and more.

Up to 50% less waiting · Up to 70% less tokens · Up to 99% less explanations to do Tighter context = Better Quality

Elixir Support Python Support TypeScript Support JavaScript Support Rust Support

Quick Install · Security · Developers · AI Assistants · Docs

Why CICADA?

The core problem: AI code assistants waste context on blind searches. Grep dumps entire files when you only need a function signature, leaving less room for actual reasoning.

The Context Compaction Approach

Instead of raw text dumps, CICADA gives your AI structured, pre-indexed knowledge:

Traditional Search	CICADA
Grep dumps entire files	Returns only signatures + call sites
Misses aliased imports	Tracks all reference types
No semantic understanding	Keyword search finds `verify_credentials` when you ask for "authentication"

What You Get

AST-level indexing – Module/function/class definitions with signatures, specs, docs
17+ language support – Elixir, Python, TypeScript, JavaScript, Rust, Go, Java, Kotlin, Scala, C/C++, Ruby, C#, Visual Basic, Dart, PHP, Erlang (beta)
Complete call-site tracking – Aliases, imports, dynamic references across all supported languages
Semantic search – Find code by concept with keyword extraction or embeddings (Ollama integration)
Git + PR attribution – Surface why code exists, not just what
Dependency analysis – Bidirectional tracking (what calls this, what does this call)
Automatic language detection – Works seamlessly across polyglot codebases

Install

bash

# 1. Install uv (if needed)
# curl -LsSf https://astral.sh/uv/install.sh | sh
uv tool install cicada-mcp

# In your repo
cicada claude   # or: cicada cursor, cicada vs, cicada gemini, cicada codex, cicada opencode, cicada zed

Try before installing permanently

Runs CICADA on demand (worse indexing quality, but zero install).

bash

uvx cicada-mcp claude   # or cursor, vs

code

claude mcp add cicada uvx cicada-mcp

code

gemini mcp add cicada uvx cicada-mcp

code

codex mcp add cicada uvx cicada-mcp

code

kimi mcp add --transport stdio cicada -- cicada-mcp

Uses your editor's built-in MCP management to install CICADA.

Available commands after installation:

cicada [claude|cursor|vs|gemini|codex|opencode|zed] - One-command interactive setup per project
cicada-mcp - MCP server (auto-started by editor)
cicada serve - Start REST API server for HTTP access to all MCP tools
cicada status - Show index status, PR index, link status, agent files, MCP configs
cicada stats [repo] - Display usage statistics (tool calls, tokens, execution times)
cicada watch - Watch for file changes and automatically reindex
cicada index - Re-index code with custom options (-f/--force, --keywords, --embeddings, --watch)
cicada index-pr - Index pull requests for PR attribution
cicada run [tool] - Execute any of the 7 MCP tools directly from CLI
cicada agents install - Install Claude Code agents to ./.claude/ directory
cicada link [parent_dir] - Links current repository to an existing index
cicada clean - Completely removes cicada integration from your folder as well as all settings

Ask your assistant:

code

# Elixir
"Show me the functions in MyApp.User"
"Where is authenticate/2 called?"

# Python
"Show me the AuthService class methods"
"Where is login() used in the codebase?"

# Both languages
"Find code related to API authentication"

Privacy & Security

100% local: parsing + indexing happen on your machine; no external access.
No telemetry: CICADA doesn't collect usage or any telemetry.
Read-only tools: MCP endpoints only read the index; they can't change your repo.
Optional GitHub access: PR features rely on gh and your existing OAuth token.

Data layout:

code

~/.cicada/projects/<repo_hash>/
├─ index.json      # modules, functions, call sites, metadata
├─ config.yaml     # indexing options + mode
├─ hashes.json     # incremental indexing cache
└─ pr_index.json   # optional PR metadata + reviews

Your repo only gains an editor config (.mcp.json, .cursor/mcp.json, .vscode/settings.json, .gemini/settings.json, .codex/mcp.json, or .opencode.json).

For Developers

Wire CICADA into your editor once, and every assistant session inherits the context.

Install & Configure

bash

cd /path/to/project
cicada claude   # or cicada cursor / cicada vs / cicada gemini / cicada codex / cicada opencode / cicada zed

Enable PR Attribution (optional)

bash

brew install gh    # or apt install gh
gh auth login
cicada index-pr .     # incremental
cicada index-pr . --clean   # full rebuild

Unlocks questions like "Which PR introduced line 42?" or "What did reviewers say about billing.ex?"

Automatic Re-indexing with Watch Mode

Enable automatic reindexing when files change by starting the MCP server with the --watch flag:

** .mcp.json**

json

{
  "mcpServers": {
    "cicada": {
      "command": "cicada-mcp",
      "args": ["--watch"],
      "env": {
        "CICADA_CONFIG_DIR": "/home/user/.cicada/projects/<hash>"
      }
    }
  }
}

When watch mode is enabled:

A separate process monitors .ex, .exs (Elixir) and .py (Python) files for changes
Changes are automatically reindexed (incremental, fast)
2-second debounce prevents excessive reindexing during rapid edits
The watch process stops automatically when the MCP server stops
Excluded directories: deps, _build, node_modules, .git, assets, priv, .venv, venv

CLI Cheat Sheet

Note: Language detection is automatic – CICADA detects Elixir (mix.exs) and Python (pyproject.toml) projects automatically.

Command	Purpose	Run When
`cicada claude`	Configure MCP + incremental re-index	First setup, after local changes
`cicada status`	Check index health, link status, agent files	After setup, troubleshooting
`cicada stats`	View usage statistics and token metrics	Monthly reviews, optimization
`cicada watch`	Monitor files and auto-reindex on changes	During active development
`cicada index --keywords .`	Rebuild with keyword indexing	After large refactors or enabling keywords mode
`cicada index --embeddings .`	Rebuild with embeddings (semantic search)	When you want Ollama-powered semantic analysis
`cicada index-pr .`	Sync PR metadata/reviews	After new PRs merge

Troubleshooting

"Index file not found"

Run the indexer first:

bash

cicada index /path/to/project

Ensure indexing completed successfully. Check for ~/.cicada/projects/<hash>/index.json.

"Module not found"

Use the exact module name as it appears in code (e.g., MyApp.User, not User).

If module was recently added, re-index:

bash

cicada index .

MCP Server Won't Connect

Troubleshooting checklist:

Verify configuration file exists:

bash

# For Claude Code
ls -la .mcp.json

# For Cursor
ls -la .cursor/mcp.json

# For VS Code
ls -la .vscode/settings.json

Check paths are absolute:

bash

cat .mcp.json
# Should contain: /absolute/path/to/project
# Not: ./project or ../project

Ensure index exists:

bash

ls -la ~/.cicada/projects/
# Should show directory for your project

Restart editor completely (not just reload window)
Check editor MCP logs:
- Claude Code: --debug
- Cursor: Settings → MCP → View Logs
- VS Code: Output panel → MCP

PR Features Not Working

Setup GitHub CLI:

bash

# Install GitHub CLI
brew install gh  # macOS
sudo apt install gh  # Ubuntu
# or visit https://cli.github.com/

# Authenticate
gh auth login

# Index PRs
cicada index-pr

Common issues:

"No PR index found" → Run cicada index-pr .
"Not a GitHub repository" → Ensure repo has GitHub remote
Slow indexing → First-time indexing fetches all PRs; subsequent runs are incremental
Rate limiting → GitHub API has rate limits; wait and retry if you hit limits

Force rebuild:

bash

cicada index-pr --clean

Keyword Search Not Working

Error: "Keyword search not available"

Cause: Index was built without keyword extraction.

Solution:

bash

# Re-index with keyword extraction
cicada index .  # or --keywords

Verify:

bash

cat ~/.cicada/projects/<hash>/config.yaml
# Should show:
# indexing:
#   mode: keywords

More detail: PR Indexing, Incremental Indexing.

Python Indexing

Requirements:

Node.js (for scip-python indexer)
Python project with pyproject.toml

First-time setup: CICADA automatically installs scip-python via npm on first index. This may take a minute.

Known limitations (Beta):

First indexing may be slower than Elixir (SCIP generation step)
Large virtual environments (.venv) are automatically excluded
Some dynamic Python patterns may not be captured

Performance tips:

bash

# Ensure .venv is excluded
echo "/.venv/" >> .gitignore

# Use keywords mode for quickest indexing
cicada index --keywords .

Report issues: GitHub Issues with "Python" label

For AI Assistants

CICADA ships 7 focused MCP tools designed for efficient code exploration across Elixir, Python, and Erlang codebases.

🧭 Which Tool Should You Use?

Need	Tool	Notes
Start exploring	`query`	🚀 START HERE - Smart discovery with keywords/patterns + filters (scope, recent, path)
View a module's complete API	`search_module`	Functions, signatures, specs, docs. Use `what_calls_it`/`what_it_calls` for bidirectional analysis
Find where a function is used	`search_function`	Definition + all call sites. Supports wildcards (`*`) and OR (`\|`) patterns
Track git history	`git_history`	Unified tool: blame, commits, PRs, function evolution (replaces 4 legacy tools)
Drill down into results	`expand_result`	Auto-expands modules or functions from query results
Advanced index queries	`query_jq`	Custom jq queries for power users

Want to see these tools in action? Check out Complete Workflow Examples with pro tips and real-world scenarios.

Core Tools

query - Smart code discovery (your starting point)

Automatically detects keywords vs patterns
Filters: scope (public/private), recent (last 14 days), filter_type (modules/functions), match_source (docs/strings)
Returns snippets with smart next-step suggestions
Use path_pattern to filter by location

search_module - Deep module analysis

View complete API: functions, signatures, specs, docs
For Python: Shows classes with method counts and signatures
For Elixir: Shows functions with arity notation
Bidirectional analysis:
- what_calls_it=true → See who uses this module (impact analysis)
- what_it_calls=true → See what this module depends on
Supports wildcards (Elixir: MyApp.*, Python: api.handlers.*) and OR patterns (MyApp.User|MyApp.Post)
Filter by visibility (public/private/all)

search_function - Function usage tracking

Find definitions and all call sites
what_calls_it=true (default) → See all callers
what_it_calls=true → See all dependencies
Include code examples with include_usage_examples=true
Filter by usage_type: source, tests, or all

Git History (Unified Tool)

git_history - All git operations in one tool

Single line: git_history("file.ex", start_line=42) → blame + PR
Line range: git_history("file.ex", start_line=40, end_line=60) → grouped blame
Function tracking: git_history("file.ex", function_name="create_user") → evolution
File history: git_history("file.ex") → all PRs/commits
Time filtering: recent=true (14d), recent=false (>14d), recent=null (all)
Author filtering: author="john"
Automatic PR index integration when available

Additional Tools

expand_result - Drill down from query results

Auto-detects module vs function
Shows complete details with usage examples
Configure what to include: code, dependencies, callers
Convenient wrapper around search_module and search_function

query_jq - Advanced index queries

Direct jq queries against the index
Schema discovery with | schema
Compact (default) or pretty output
Sample mode for large results

Detailed parameters + output formats: MCP_TOOLS_REFERENCE.md.

Token-Friendly Responses

All tools return structured Markdown/JSON snippets (signatures, call sites, PR metadata) instead of full files, keeping prompts lean.

New in v0.5.1: All tools now use compact output by default to minimize token usage. Use verbose=true for detailed output with full docs and specs.

Documentation

Codebook – Complete feature reference and user guides
Workflows – Real-world examples chaining tools together
Installation – Step-by-step setup for all editors
Contributing – Development guidelines and architecture
CHANGELOG.md – Release notes

Deep Dives:

Keyword Extraction Analysis – Semantic search internals
PR Indexing – GitHub integration details
MCP Tool Call Benchmarking – Token/time benchmarks
Tool Discoverability – UX improvements research

Roadmap

Current Status

Production Ready:

✅ Elixir (tree-sitter)
✅ Python (SCIP)
✅ TypeScript (SCIP)
✅ JavaScript (SCIP)
✅ Rust (SCIP)

Beta:

🚧 Erlang (tree-sitter)
🚧 Go (SCIP)
🚧 Java/Kotlin/Scala (SCIP)
🚧 C/C++ (SCIP)
🚧 Ruby (SCIP)
🚧 C#/Visual Basic (SCIP)
🚧 Dart (SCIP)
🚧 PHP (SCIP)

Comparison to Alternatives

Feature	CICADA	Serena	Codicil (Elixir-only)
Analysis Method	SCIP (static index)	LSP (real-time server)	LLM summaries + embeddings
Code Editing	❌	✅	❌
Git Context	✅ PR history, blame, evolution	❌	❌
Resource Usage	Low (read from disk)	High (persistent server processes)	Medium (API calls)
Privacy	100% local	100% local	Requires external LLM APIs
Semantic Search	Local Ollama or keywords	❌	OpenAI/Anthropic embeddings
Call Graph	Bidirectional with alias resolution	LSP-based	❌

When to choose CICADA: You want local-first operation with rich git context (PR attribution, blame, function evolution tracking) and efficient token usage.

When to choose Serena: You need code editing capabilities through LSP and can accept higher resource usage.

When to choose Codicil: You have an Elixir project and prefer LLM-powered semantic summaries (Elixir-only).

Contributing

bash

git clone https://github.com/wende/cicada.git
cd cicada
uv sync
pytest

Before submitting a PR:

Run black cicada tests
Ensure tests + coverage pass (pytest --cov=cicada --cov-report=term-missing)
Update docs if behaviour changes

We welcome issues/PRs for:

New language grammars
Tool output improvements
Better onboarding docs and tutorials

License

MIT – see LICENSE.

Stop wasting context on blind searches. Give your AI CICADA.

Get Started · Report Issues

Install

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "cicada": {
      "command": "uvx",
      "args": [
        "cicada-mcp"
      ]
    }
  }
}

CICADA (io.github.wende/cicada) — Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

CICADA

Code Intelligence: Contextual Analysis, Discovery, and Attribution

Why CICADA?

The Context Compaction Approach

What You Get

Install

Privacy & Security

For Developers

Install & Configure

Enable PR Attribution (optional)

Automatic Re-indexing with Watch Mode

CLI Cheat Sheet

Troubleshooting

For AI Assistants

🧭 Which Tool Should You Use?

Core Tools

Git History (Unified Tool)

Additional Tools

Token-Friendly Responses

Documentation

Roadmap

Current Status

Comparison to Alternatives

Contributing

License

Install

Related servers