agentmods.dev

code-graph-mcp

code-graph-mcp is a plugin for Claude Code from sdsrss/code-graph-mcp. Its manifest loads nothing; the 2 skills, 1 agent, 6 hooks, 1 MCP server it bundles cost 127 tokens per session together, scanned A, original, MIT.

A code-navigation add-on that builds a map of a codebase from its structure and relationships. It supports semantic search, showing which functions call others, tracing web routes, and checking what a change may affect.

In plain words
What is it for?
Use it to find related code by meaning, follow call chains, trace an HTTP request through the code, and inspect the likely impact of a change.
Why use it?
It reduces the time spent hunting through unfamiliar code and helps reveal connections that simple text search can miss. This makes it easier to understand where a change starts and what it may touch.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 84repo changed 7d ago A scan tokens not measured original MIT

Good fit Use it to find related code by meaning, follow call chains, trace an HTTP request through the code, and inspect the likely impact of a change.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add sdsrss/code-graph-mcp
/plugin install code-graph-mcp
View source ↗ sdsrss/code-graph-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/sdsrss/code-graph-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-graph-mcp

README.md
[![agentmods](https://agentmods.dev/badge/plugins/sdsrss/code-graph-mcp/claude-plugin/github.svg)](https://agentmods.dev/plugins/sdsrss/code-graph-mcp/claude-plugin)
Your own site
<a href="https://agentmods.dev/plugins/sdsrss/code-graph-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/sdsrss/code-graph-mcp/claude-plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for code-graph-mcp

Your own site · 80×15
<a href="https://agentmods.dev/plugins/sdsrss/code-graph-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/sdsrss/code-graph-mcp/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 2 skills, 1 agent, 6 hooks, 1 MCP server cost 127 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

code-graph-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude-plugin/.claude-plugin/plugin.json · 16 lines

What it actually says

{
  "name": "code-graph-mcp",
  "description": "AST knowledge graph for intelligent code navigation — auto-indexes your codebase and provides semantic search, call graph traversal, HTTP route tracing, and impact analysis via MCP tools",
  "author": {
    "name": "sdsrs"
  },
  "version": "0.169.0",
  "keywords": [
    "code-graph",
    "ast",
    "navigation",
    "mcp",
    "knowledge-graph"
  ]
}
Contents

What it installs

The manifest is a name and a version. 2 skills, 1 agent, 6 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 127 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago Changed ddcb317ffa6a
  2. 8d ago Changed eea9aa12d172
  3. 9d ago Changed 2640b32154d6
  4. 16d ago Changed 27b98ec362ad
  5. 17d ago Changed 07be07578561
  6. 18d ago Changed 011075c8ef97
  7. 19d ago Changed 7c1bf7260d5d
  8. 20d ago Changed f37a06dda2d6
  9. 1mo ago Changed 4205a5d35a09
  10. 1mo ago First seen · 16 lines scan A 213ad415f598

Subscribe to this mod's changes

code-graph-mcp is a plugin published in the GitHub repository sdsrss/code-graph-mcp (84 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeDebuggingastcall-graphclaude-code-plugincode-navigationknowledge-graph
Related

Other plugins, from other repositories

gograph

Claude Code workflow guidance for local gograph: AST-aware call graphs, impact, security-flow candidates, and 61 query, analysis, and workflow capabilities through a separately registered MCP server.

ozgurcd/gograph · not measured

codeweb

See what your AI edits affect. Structural checks for AI code changes. Local call/import graphs and 28 MCP tools for impact, callers, and duplication. No LLM in the checks.

GhostlyGawd/codeweb · not measured

token-master

Token-efficient code-understanding harness. Routes structural questions (callers, callees, impact, inheritors) to a prebuilt code graph instead of repeated grep and file-reads, cutting cumulative context tokens. Type /token-master in a repo to build the index and turn on routing.

All-The-Vibes/TokenMasterX · not measured

meeba-brain

Ground-truth code graph context for your own private codebase — exact callers, callees, symbol definitions, and file dependencies, from a real parsed graph, not text-similarity guessing.

meemoprasad/meeba-brain-marketplace · not measured

python-clang-mcp

C/C++ code introspection via libclang — fills gaps that clangd-via-LSP cannot expose (macro expansion at use-site, record layout, predicate-based AST queries, bitfield audits, attribute audits, call-site argument patterns).

dlebed/python-clang-mcp · not measured

7xuanlu-wenlan marketplace

Plugin marketplace listing 1 plugin: wenlan.

7xuanlu/wenlan · not measured