Codegraphcontext MCP Server

🌍 **Help translate CodeGraphContext to your language by raising an issue & PR on [GitHub Issues](https://github.com/CodeGraphContext/CodeGraphContext

Local serverstdioPython

What is the Codegraphcontext MCP server?

If you already use Codegraphcontext, the codegraphcontext mcp server is the piece that lets your assistant work with it directly. 🌍 Help translate CodeGraphContext to your language by raising an issue & PR on GitHub Issues!.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Workflow — 1. Source code is parsed using Tree-sitter or SCIP indexers. 2. Relationships between functions, classes, imports, and calls are extracted. 3. A

Installation

kuzu on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Credentials and setup notes

Configuration is passed through the environment: NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD, CGC_OUTPUT_FORMAT. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Codegraphcontext's toolset — Workflow — is a fair guide to whether it matches your workflow. It is maintained by shashankss1205; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Workflow1. Source code is parsed using Tree-sitter or SCIP indexers. 2. Relationships between functions, classes, imports, and calls are extracted. 3. A knowledge graph is generated and stored in a graph database. 4. Users can q

How to install the Codegraphcontext MCP server

Or add it to your MCP client config:

```json
{
  "mcpServers": {
    "CodeGraphContext": {
      "command": "codegraphcontext",
      "args": ["mcp", "start"],
      "env": {
        "CGC_OUTPUT_FORMAT": "gcf"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
NEO4J_URIConfiguration value read at startup.Optional
NEO4J_USERNAMEConfiguration value read at startup.Optional
NEO4J_PASSWORDConfiguration value read at startup.Optional
CGC_OUTPUT_FORMATConfiguration value read at startup.Optional

Example prompts to try

  • Use Codegraphcontext to Workflow.

Frequently asked questions

It connects Codegraphcontext to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Workflow) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Codegraphcontext directly.