Context Bunker MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Context Bunker MCPFind unused exports in the current project."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Context Bunker MCP ποΈ
Stop wasting tokens on orientation. Pre-computed codebase intelligence for AI coding tools. One command. Code never leaves your machine.
What is this?
AI coding agents spend ~80% of tokens just figuring out where things are β re-reading files, tracing imports, grepping for symbols. Every. Single. Session.
Context Bunker fixes this. It's an MCP server that indexes your codebase using tree-sitter AST parsing and gives your AI tools instant access to structural intelligence β dependency graphs, call trees, dead code, cross-session diffs β all from a local SQLite database.
One call replaces 8-16 grep/read calls. ~90% token savings. Zero cloud. Zero API keys.
Works with Claude Code, Cursor, Windsurf, Copilot, and any MCP-compatible client.
Why not just grep? Grep finds text. Context Bunker understands structure β dependency graphs, cross-session memory, dead code detection, and token-efficient summaries. Things grep structurally can't do. Full comparison.
Related MCP server: reposynapse
Setup
Install
# Run directly β no install needed
bunx context-bunker-mcp /your/project
# Or install globally
bun install -g context-bunker-mcp
# No Bun? npx / npm work tooAdd to your AI tool
Claude Code:
# With a project (auto-indexes on startup)
claude mcp add context-bunker -- bunx context-bunker-mcp /your/project
# Without a project (AI calls set_project dynamically)
claude mcp add context-bunker -- bunx context-bunker-mcp
# No Bun? npx work tooCursor / Windsurf / VS Code β add to settings.json:
{
"mcpServers": {
"context-bunker": {
"command": "bunx",
"args": ["context-bunker-mcp", "/your/project"]
}
}
}Tools (16)
Tool | What it does |
π₯ | What changed since the AI last looked. No more re-orientation. |
π₯ | Dead code detection β exported but never imported anywhere. |
π₯ | Find dead internal code β functions, classes, variables, types never referenced. |
π₯ | File overview in ~50 tokens. Scan 10 files for the cost of 1. |
π₯ | Find structural patterns: HTTP calls, env access, error handlers, async, TODOs. |
π§ | Full file context in 1 call β imports, exports, dependents, types, tests. |
π§ | "If I change this, what breaks?" β transitive import graph with depth control. |
π§ | AST-aware symbol search by name, kind, and scope. Not text matching. |
π§ | Where a symbol is used, classified by kind (import, call, type annotation). |
π§ | What a function calls, recursively, as a tree. |
π§ | Extract one definition β not the whole file. 80% token savings. |
π§ | Architecture overview: modules, public APIs, relationships. |
π§ | Point the index at any project directory on the fly. |
π§ | Semantic search via local TF-IDF. No API keys needed. |
π§ | Force re-index of the codebase or a single file. |
π§ | Index health, file counts, token savings estimate. |
π₯ Unique π§ Core Intelligence π§ Housekeeping
Language Support
TypeScript, JavaScript (TSX/JSX/MTS/CTS), Python, Go, Rust, Java, C#
Powered by tree-sitter WASM grammars. Adding a new language = one extractor file in src/languages/.
Tech Stack
Runtime | Bun (Node.js fallback) β |
MCP |
|
AST |
|
Storage | SQLite (WAL mode) β single file, survives restarts |
Search | TF-IDF (local) β zero API keys, no cloud |
Watch |
|
Storage
The index lives in your OS cache directory β not inside the project. No .gitignore needed.
Platform | Location |
macOS |
|
Linux |
|
Windows |
|
Want it inside the project instead? Use --local or set { "storage": "local" } in .context-bunker.json.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
Repository knowledge graph MCP server for codebase understanding and debugging.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that gives AI agents structured code understanding and precise code intelligence via local indexing of AST, call graphs, and semantic search.46 npm4Apache 2.0
- AlicenseAqualityDmaintenanceUniversal MCP server that analyzes any codebase and provides structured context to AI assistants. Dynamic, accurate, and token-efficient.1811 npmMIT
- FlicenseBqualityBmaintenanceA local MCP server that indexes codebases using Tree-sitter AST parsing and LanceDB, enabling AI models to search across repositories with sub-second latency.5-
- AlicenseNot gradedqualityCmaintenanceMCP server for semantic codebase navigation that builds an AST index of symbols, imports, and exports, providing AI agents with tools to search, explore, and understand code.MIT