Gortex MCP

A code-intelligence engine for agents: builds a project graph and serves symbol lookup, call chains and blast radius, saving context

  • 2,068 ★ on the repository
  • Last commit
  • Apache-2.0
MCP server

Extended access

Why this level

  • Reads and indexes code files
  • Runs a local service and configures the agents
All reasons and checks

zzet/gortex

Install

Manual install

curl -fsSL https://get.gortex.dev | sh

Install the engine on the machine.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Reads and indexes code files
  • Runs a local service and configures the agents

This is third-party code. Review the repository files before installing.

What it does

Gortex indexes code into a graph and serves precise answers through a CLI, an MCP server and an HTTP API. It supports many languages via syntax parsing and works across several repositories at once. The agent gets only what it needs: symbol lookup, call chains, the blast radius of a change, dataflow and clone detection, instead of reading every file. It runs locally, installs via a script, and an init command configures the coding assistants found on the machine.

Who it is for. For developers and coding agents that need precise search over a large codebase without extra context.

Good fit when

  • The agent spends too much context reading code
  • You need to know the blast radius of a change before editing
  • You need symbol and call-chain search across several repositories

Not a fit when

  • The project is small and clear without an index
  • You need to run code rather than analyze it

Example request

With Gortex show what a change to this function affects and find all its call sites

MCP

Transport
stdio, http
Authentication
not required

Limitations

The index has to be built and refreshed, which takes time and space on a large codebase. It runs locally, so it depends on the machine's resources.

How to disable. Remove the gortex binary and the MCP settings added by the init command in the agents' directories.

FAQ

How does the agent connect to Gortex?

The gortex init command writes an .mcp.json in the project and the agent talks to the engine over MCP; a CLI and HTTP API are also available.

How many languages are supported?

Parsing covers hundreds of languages and grammars via syntax analysis.

Discussion

No questions or reviews yet.

Local code graph for agents: an MCP server returns entry points, symbol links and change impact in one call

MCP serverExtended access77.5KRepository stars
Editors’ pick

Indexes a codebase into a knowledge graph and gives the agent call chains, change blast radius and code search over MCP

MCP serverExtended access48.5KRepository stars
Official

An MCP server builds a local code graph so an agent can inspect calls, dependencies and the possible impact of a function change.

MCP serverExtended access817Repository stars

A local codebase index for agents: hybrid search, dependency graphs and change impact analysis

MCP serverExtended access3.4KRepository stars

Selects code context for a coding agent from a repository graph, taking previous file reads and edits into account

CLIExtended access1KRepository stars
Official

An MCP server and CLI for code research: search and understand your project and all of GitHub with fewer tokens

MCP serverExtended access961Repository stars

README in short

The README describes Gortex as a graph-based code-intelligence engine accessed via a CLI, MCP server and HTTP API. It installs with a script, an install command sets up MCP, skills and slash commands, and init connects the engine to a specific repository. It lists MCP tools: symbol lookup, call chains, blast radius, dataflow, clone detection and refactoring. It claims support for many languages and multiple repositories.

README badge

Report a problem