codebase-synapse
Click on "Install 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., "@codebase-synapseWhat's the impact of updatinghandleLoginin terms of callers and dependent files?"
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.
π§ Codebase Synapse
Give your AI agent a deep understanding of your entire codebase.
An MCP server that indexes your codebase into a local knowledge graph with 52 AI tools β semantic search, call-graph traversal, git archaeology, blast-radius analysis, and more.
Works with Claude Code Β· Cursor Β· Windsurf Β· Zed Β· Any MCP client
The Problem
AI coding agents (Claude, Cursor, etc.) are powerful β but they work with limited context. They can only see the files you open or feed them. Ask about call chains, architectural patterns, or blast-radius impact, and they guess.
Codebase Synapse fixes this. It indexes your entire repo into a local knowledge graph stored in SQLite, giving your AI agent real answers backed by structural analysis β not hallucinations.
How it works
graph LR
A["π Your Codebase"] -->|Tree-sitter| B["π§© Parser"]
B -->|Symbols & Edges| C["πΈοΈ Knowledge Graph"]
C -->|SQLite| D["πΎ Local DB"]
D -->|52 MCP Tools| E["π€ AI Agent"]
style A fill:#1a1b26,stroke:#7aa2f7,color:#c0caf5
style B fill:#1a1b26,stroke:#bb9af7,color:#c0caf5
style C fill:#1a1b26,stroke:#9ece6a,color:#c0caf5
style D fill:#1a1b26,stroke:#e0af68,color:#c0caf5
style E fill:#1a1b26,stroke:#f7768e,color:#c0caf5Related MCP server: codeweave-mcp
β‘ Quick Start
1. Index your project (CLI, Zoekt-style)
codebase-synapse index /path/to/your/repoIndexing runs as a separate CLI command and writes into ~/.codebase-synapse/codebase.db. The first index is the slow one; re-running it only re-indexes changed files. The MCP server never indexes β it only reads the pre-built index.
2. Start the MCP server
npx codebase-synapseThat's it. No Docker. No database setup. No cloud. The server starts via stdio and serves the pre-built index to your MCP client.
Configure your client
Add to your claude_desktop_config.json or mcp_servers.json:
{
"mcpServers": {
"codebase-synapse": {
"command": "npx",
"args": ["-y", "codebase-synapse"]
}
}
}Add to your .cursor/mcp.json:
{
"mcpServers": {
"codebase-synapse": {
"command": "npx",
"args": ["-y", "codebase-synapse"]
}
}
}Any MCP client that supports stdio transport works. Just point it at:
npx -y codebase-synapse⨠What It Does
π Search & Discovery
Tool | Description |
| Vector similarity search using local embeddings (all-MiniLM-L6-v2) |
| Full-text search across code (FTS5 + BM25 ranking) |
| Find functions, classes, types by name or pattern |
| Combined semantic + lexical search with RRF fusion |
| Find structurally similar code using MinHash + LSH |
| Locate a symbol across all indexed projects |
πΈοΈ Knowledge Graph
Tool | Description |
| Navigate the call graph in either direction |
| Trace dependency chains |
| Compute blast radius before editing a file |
| Find the shortest connection between two symbols |
| Detect unreachable functions and unused exports |
| Identify the most critical nodes in your architecture |
| Run Cypher-like queries against the knowledge graph |
ποΈ Architecture
Tool | Description |
| Full project architecture overview (languages, entry points, hotspots) |
| Directory tree with symbol annotations |
| High-level summary with key metrics |
| Extract HTTP routes and their handler mappings |
| Detect module boundaries via Leiden clustering |
| Validate cross-module dependencies against defined boundaries |
| Community detection across the codebase |
π¬ Git Archaeology
Tool | Description |
| Deep history analysis of a file (authors, churn, evolution) |
| Files with highest complexity Γ change frequency |
| Files that always change together |
| Semantically meaningful recent changes |
| Build temporal analysis from git log |
π§ Memory & Context
Tool | Description |
| Persistent notes, facts, and decisions across sessions |
| Short-term memory within a session |
| Budgeted context preparation for AI agents |
| Focused context for a specific file edit |
| Recently accessed and modified files |
| Architecture Decision Records management |
π‘οΈ Codebase Guard
Included as a bonus: codebase-guard is a PreToolUse hook for Claude Code that blocks writes to high-impact files until the agent runs impact_analysis first.
It uses PageRank scores and blast-radius data from the knowledge graph to identify architectural hubs. No more accidental edits to core files.
π§ Technical Details
Language | Rust (compiled native binary) |
Transport | MCP stdio (JSON-RPC) |
Storage | SQLite (WAL mode, zero config) |
Embeddings | all-MiniLM-L6-v2 via Candle (offline, local, lazy-loaded) |
Parsing | Tree-sitter (10 languages) |
Distribution | npm with prebuilt binaries (Windows, macOS, Linux Γ x64, arm64) |
Supported Languages
Rust Β· Python Β· TypeScript Β· JavaScript Β· Go Β· Java Β· C# Β· PHP Β· C Β· C++
Architecture
src/
βββ parser/ # Tree-sitter parsing & entity extraction
βββ graph/ # Knowledge graph, PageRank, Leiden clustering
βββ indexer/ # Repository indexing pipeline
βββ search/ # BM25 full-text + vector cosine + hybrid RRF
βββ embedding/ # Candle-based local embeddings (feature-gated)
βββ memory/ # Persistent & session memory stores
βββ mcp/ # MCP protocol transport + 52 tool handlers
βββ git/ # Git archaeology, intent classification, hotspots
βββ context/ # Budgeted context preparation for AI
βββ cypher/ # Nom-based Cypher parser β SQL CTE planner
βββ similarity/ # MinHash + LSH structural similarity
βββ semantic/ # Multi-signal scoring (tokens, directory, AST)
βββ cli/ # Interactive TUI installer + artifact export/importπ€ Contributing
Contributions are welcome! The project uses standard Rust tooling:
# Run tests
cargo test
# Lint
cargo clippy -- -D warnings
# Format
cargo fmt --allπ License
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityFmaintenanceAn MCP server that transforms codebases into intelligent, queryable knowledge bases, enabling AI assistants to perform semantic search, explore architecture, and analyze code relationships.Last updated165
- Alicense-qualityBmaintenanceAn MCP server that gives AI agents structured code understanding and precise code intelligence via local indexing of AST, call graphs, and semantic search.Last updated964Apache 2.0
- AlicenseAqualityAmaintenanceA local knowledge graph MCP server that provides AI agents with permanent, structured memory about codebases, enabling semantic search, blast radius analysis, and convention enforcement.Last updated82MIT
- Alicense-qualityCmaintenanceMCP server for semantic code search and dependency graph analysis. Indexes codebases into a knowledge graph with vector embeddings for AI-powered code understanding.Last updated16MIT
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/iwiels/codebase-synapse'
If you have feedback or need assistance with the MCP directory API, please join our Discord server