GhostLink

A security-hardened MCP server that gives AI coding agents safe, deterministic access to local repositories.

What is GhostLink?

GhostLink is a local-first Model Context Protocol server that exposes your codebase to AI coding agents through a small set of policy-gated tools. It solves a specific problem: AI agents need to search, read, patch, and verify code, but giving them raw shell access is a liability. GhostLink provides a sandboxed capability plane where every tool call is confined to a single repository root, every output follows a deterministic JSON shape, and every invocation is audit-logged.

Why GhostLink?

Tools

Every tool returns a ToolEnvelope:

{
  "ok": true,
  "data": { ... },
  "provenance": { "tool": "repo.search", "timestamp": "2026-02-24T...", "duration_ms": 42 }
}

On error, "error": { "code": "...", "message": "..." } replaces "data". Full tool schemas: docs/TOOLS.md.

Quick Start

Prerequisites

• Node.js 18+
• ripgrep (brew install ripgrep)
• A git repository to expose

Install and Build

git clone https://github.com/bgorzelic/ghostlink.git
cd ghostlink
npm install
npm run build

Smoke Test (Raw STDIO)

GhostLink speaks JSON-RPC 2.0 over STDIO. Test it directly:

echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | \
  GHOSTLINK_REPO_ROOT=/path/to/target/repo node dist/index.js

This returns all 6 tools and their schemas.

npm Package

npm install @bgorzelic/ghostlink

Client Configuration

GhostLink works with any MCP client that supports STDIO transport.

Claude Code

Create .mcp.json in the target repo root:

{
  "mcpServers": {
    "ghostlink": {
      "command": "node",
      "args": ["/absolute/path/to/ghostlink/dist/index.js"],
      "env": {
        "GHOSTLINK_REPO_ROOT": "/path/to/target/repo"
      }
    }
  }
}

Then run claude in that directory. GhostLink tools appear as available MCP tools.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "ghostlink": {
      "command": "node",
      "args": ["/absolute/path/to/ghostlink/dist/index.js"],
      "env": {
        "GHOSTLINK_REPO_ROOT": "/path/to/target/repo"
      }
    }
  }
}

Restart Claude Desktop. GhostLink tools appear in the tool picker.

Cursor, Windsurf, Cline, and Other MCP Clients

Add to your client's MCP server configuration:

{
  "ghostlink": {
    "command": "node",
    "args": ["/absolute/path/to/ghostlink/dist/index.js"],
    "env": {
      "GHOSTLINK_REPO_ROOT": "/path/to/target/repo"
    }
  }
}

Consult your client's documentation for the exact config file location. The transport is always STDIO.

Prompt Templates

docs/PROMPTS.md contains ready-to-use prompts for high-autonomy agent operation, including orchestrator prompts, sub-agent role definitions (Protocol Engineer, Toolsmith, Security Reviewer, Test Engineer, Docs Engineer), and multi-instance coordination patterns.

Security Model

GhostLink enforces defense-in-depth at every layer:

• Repo-root sandbox -- All file operations confined to GHOSTLINK_REPO_ROOT. Path traversal, symlink escape, null bytes, and absolute paths outside the root are all rejected before any filesystem access.
• No shell execution -- repo.run uses spawn with shell: false. Commands are limited to a fixed allowlist (test, lint, typecheck, build, smoke) with per-command argument allowlists. Environment is stripped to six safe variables.
• Output caps -- Every tool that returns bulk data enforces hard maximums (200 search results, 10MB file reads, 200KB stdout/stderr, 2MB diffs). Truncation is flagged, never silent.
• Atomic patch rollback -- repo.apply_patch validates all paths and computes all patches before writing anything. If any write fails, completed writes are rolled back to their original state.
• Timeout enforcement -- repo.run kills processes at configurable timeouts (default 120s, hard cap 300s) with SIGTERM then SIGKILL.

Full threat model and mitigations: docs/SECURITY.md.

Audit Logging

Every tool call produces a JSONL audit entry: {ts, tool, ok, duration_ms, error_code?, repo_root}.

Set via environment variable:

GHOSTLINK_LOG=file GHOSTLINK_REPO_ROOT=/path/to/repo node dist/index.js

Development

npm install          # Install dependencies
npm test             # Run test suite (108 tests via Vitest)
npm run lint         # ESLint
npm run typecheck    # TypeScript strict mode check
npm run build        # Compile to dist/
npm run dev          # Dev mode with auto-reload (tsx watch)

Full verification after edits:

npm test && npm run lint && npm run typecheck && npm run build

Documentation

Architecture

GhostLink is a three-layer stack designed for extensibility without core changes:

Transport (src/index.ts)        STDIO now, HTTP/SSE in Phase 2
    |
Server Factory (src/server.ts)  Transport-agnostic tool registration via MCP SDK + Zod schemas
    |
Tools (src/core/tools/*)        Six tools, each returning ToolEnvelope<T> through shared policy
    |
Policy (src/core/policy/*)      Sandbox enforcement, audit logging, output caps

The createServer() factory knows nothing about transport. Adding HTTP/SSE in Phase 2 means writing a new transport binding and auth middleware -- the server factory and all tool implementations remain unchanged. Phase 3 (agent runtime) adds memory resources and orchestration as consumers of GhostLink, not modifications to it.

Roadmap

Phase 1 -- Local STDIO [Shipped, v0.1.0]

Deterministic tool surface, repo-root sandbox, curated command execution, 108 tests, JSONL audit logging, npm package published.

Phase 2 -- Remote Transport [Planned]

HTTP/SSE transport, OAuth 2.1 authentication, multi-user tenant separation, per-tenant rate limiting, schema versioning, structured audit logging with correlation IDs.

Phase 3 -- Agent Runtime [Future]

Persistent memory resources exposed via MCP, optional policy-gated memory write tools, orchestration layer (external to GhostLink), evaluation loops, sub-agent coordination framework.

License

ISC