ForkFree

MCP servers

CodeNib

by sysevol-ai

CodeNib builds a local search index and a graph of symbols for a code repository, then exposes it to AI coding agents such as Claude Code and Codex through MCP. It helps the agent find relevant source code with file and line references and follow references between functions across many languages.

Worth a lookEstablished, with a few things to check (listed below).

View on GitHubProject website

Stars
90
Licence
Apache-2.0
Runs on
Your computer
Setup
Moderate
Language
Python
Age
603 days

What you can do with it

  • Ask your coding agent in plain language where a behaviour is implemented and get cited files and lines
  • Trace incoming and outgoing references for a function or type across a repository
  • Export a Wiki of a codebase with source citations to GitHub Pages

Make money with it

A freelancer could offer codebase audits or legacy-code onboarding documentation, using the generated Wiki and reference tracing to work faster.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Cut the time developers spend finding their way around an unfamiliar or legacy codebase, so fixes and features ship faster
  • Give a freelance developer faster, better-cited answers when taking on client projects in several languages

Can you use it commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

Add it to Claude Code

claude mcp add codenib -- uvx codenib

From the official MCP Registry (ai.codenib/codenib). Only connect MCP servers you trust: they can act on your behalf.

Getting it running

Install with pip (python -m pip install "codenib[graph,mcp]") and run "codenib codegraph init" on a clean Git repository; language toolchains may also be needed.

Follow the official instructions in the project README.

Things to check

  • Needs a separate Claude Code or Codex subscription for the agent's own model
  • Optional grep-to-Jev route sends selected code to remote models via OpenRouter and needs an API key
  • Reference tracing may miss external and dynamic relationships
  • Language setup requirements and coverage vary

Checked 02 Nov 2026. Summary drafted by AI from the project's README.

More in MCP servers

kanzo emanuele-em
Hidden gem

Kanzo is a small kanban board that runs in your browser and also works as an MCP server, so you and your AI coding agents share the same task list. All data sits in one local folder, which can be synced between machines through a private git repository.

717 stars +145 a day AGPL-3.0
earshot Leonxlnx
New and promising

Earshot is a toolkit that lets AI coding agents analyse and describe audio, check how well sound fits a description or a video, and create their own sound effects in code. It runs locally on a CPU as a command-line tool, a Python library or an MCP server.

3.5k stars +83 a day MIT
cueframe-mcp cueframe-ai
New and promising

CueFrame is a hosted video service that lets an AI assistant, a command-line tool or a REST API create, edit, caption and render video as editable projects. This repository holds the connection tools and skill packs that link agents such as Claude Code, Codex and Cursor to that service.

2 stars Apache-2.0