CodeNib logo

CodeNib

Ranked repository context retrieval and typed symbol-graph navigation for coding agents.

Install CodeNib

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "codenib": {
      "command": "uvx",
      "args": [
        "codenib"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

CodeNib connects coding agents to a local repository for ranked source retrieval and typed symbol navigation. Its `explore_context` tool returns bounded code context with file and line references, while `dependency_subgraph` follows static incoming and outgoing references across indexed symbols. The CodeGraph workflow runs locally without a separate model, API key, or GPU, using the model already provided by the agent. Reach for it when text search is insufficient for tracing definitions, callers, and multi-hop code relationships.

Use cases

  • Locate the implementation of a behavior and cite its source lines
  • Trace callers and dependencies across several symbol hops
  • Inspect definitions and static references in an unfamiliar repository
  • Compare ranked context retrieval with native grep and file reads

Key features

  • Ranked source-context retrieval
  • File and line citations
  • Typed symbol-graph navigation
  • Static dependency subgraphs up to depth 8
  • Multi-language graph backends
  • Local model-free CodeGraph workflow

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

32/32 checks healthy over the last 102d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · codenib (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars107Stargazers on the source repository.
Last commitTodayMost recent push to the default branch.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How CodeNib works

What CodeNib does

CodeNib gives coding agents structured ways to locate and inspect source code in a local repository. It combines ranked retrieval with a typed symbol graph, allowing an agent to start from a code question, receive source anchors, and then follow definitions or static references. Results include file and line references so the agent can inspect the underlying evidence before describing an implementation or call path.

The CodeGraph workflow supports graph backends for Python, Go, Rust, C and C++, C#, Java, Ruby, PHP, Kotlin, Scala, JavaScript, and TypeScript. Swift and Lua support chunking and retrieval. Language coverage, provider prerequisites, and graph behavior vary by language.

How it works

CodeNib builds local search views and an indexed symbol graph from a clean repository. explore_context provides ranked, bounded context for a question or investigation. dependency_subgraph follows incoming and outgoing static references, with a single request able to traverse relationships up to depth 8. Graph relationships are resolved through SCIP or language-server indexers and can represent calls, fields, type uses, and function values.

The graph describes statically indexed relationships rather than guaranteed runtime behavior. Dynamic or external relationships may be absent, and a reference that looks like a call still requires source inspection to establish how it is used. Native agent search and file reads remain useful for known strings or files.

Setup and configuration

Install the graph and MCP components with Python 3.10 or newer:

bash
python -m pip install "codenib[graph,mcp]"
codenib codegraph init /path/to/your/repo

The setup requires Git, a clean repository, and an MCP-capable agent such as Claude Code or Codex. After initialization, ask the agent to use explore_context or another CodeNib tool for a repository investigation. CodeNib itself does not require a model, API key, or GPU; the connected agent supplies the model.

Indexing and rebuild costs depend on the repository and language tooling. The product reuses or rebuilds views, while file-level delta repair is not enabled. An optional grep-to-Jev route can use OpenRouter for planning and reranking; selected code is sent to remote models, and authorization previews are opt-in.

Tools and capabilities

  • Retrieve ranked, bounded source context with file and line citations through explore_context.
  • Navigate definitions and statically indexed references across symbols.
  • Trace multi-hop dependency relationships with dependency_subgraph.
  • Use one retrieval and navigation workflow across supported programming languages.
  • Export a cited local Wiki to GitHub Pages or browse generated local and public examples.

Limitations and notes

CodeNib is in beta, so public interfaces may change. Graph results reflect indexed static relationships and can miss dynamic behavior, external dependencies, or relationships not resolved by the configured language backend. Coverage and setup requirements differ between languages. The optional remote reranking route has different privacy and model-use characteristics from the local, model-free CodeGraph workflow.

Written by AllMCPs with AI assistance from the project’s README and listing data. How we build listings

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about CodeNib

CodeNib is an MCP server that connects coding agents to a local repository through ranked source-context retrieval and typed symbol navigation. Its main tools include `explore_context` for bounded, cited code context and `dependency_subgraph` for traversing static incoming and outgoing references across indexed symbols. It supports multi-hop code investigation.

Install it with `python -m pip install "codenib[graph,mcp]"`, then run `codenib codegraph init /path/to/your/repo`. Python 3.10+, Git, and a clean repository are required. The documented quickstart uses Claude Code or Codex as the connected agent.

Yes, CodeNib's quickstart supports Claude Code. Install the graph and MCP components, initialize the target repository with `codenib codegraph init`, and ask Claude Code to use tools such as `explore_context` for repository investigation.

Yes, Codex is supported by the documented quickstart. After installing CodeNib and initializing a clean repository, Codex can use its MCP tools for ranked context retrieval and typed static-symbol navigation.

CodeNib has graph backends for Python, Go, Rust, C and C++, C#, Java, Ruby, PHP, Kotlin, Scala, JavaScript, and TypeScript. Swift and Lua support chunking and retrieval. Backend coverage and setup prerequisites vary by language.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewCodeNib AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/codenib?style=directory)](https://allmcps.com/mcp/codenib)
HTML Embed
<a href="https://allmcps.com/mcp/codenib"><img src="https://allmcps.com/api/badge/codenib?style=directory" alt="CodeNib on AllMCPs" /></a>