What is codebase-context-mcp CLAUDE.md?

A project instruction file for codebase-context-mcp, a TypeScript Model Context Protocol (MCP) server that indexes and searches source code locally. It documents the project’s stack, structure, and development commands.

Use it when developing or maintaining codebase-context-mcp, including its tree-sitter parsers, code index, search tools, and build process.

It gives coding agents the repository context needed to make changes without first rediscovering how the server, parsers, index, and search work.

codebase-context-mcp CLAUDE.md — Instructions file by Jhackman2019

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.

agentmods

npx agentmods add instructions/jhackman2019/codebase-context-mcp/claude-md

Clone the repo

git clone --depth 1 https://github.com/Jhackman2019/codebase-context-mcp

Per session 1,253 This file is loaded in full into every session.

When invoked 1,253 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.01253	$0.01253
Opus 5	$0.00626	$0.00626
Sonnet 5	$0.00251	$0.00251
Haiku 4.5	$0.00125	$0.00125

Measured yesterday against content hash fcfc1e82e5c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-context-mcp CLAUDE.md 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 yesterday.

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.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — codebase-context-mcp

ARM64-compatible MCP server for codebase indexing and search using WASM-based tree-sitter. Zero native bindings.

Repo: github.com/Jhackman2019/codebase-context-mcp
Package: codebase-context-mcp on npm
Registry name: io.github.jhackman2019/codebase-context-mcp
License: MIT
Author: Finit Solutions

Tech Stack

TypeScript (ESM), tsup bundler, Node 20+
web-tree-sitter (WASM) + tree-sitter-wasms (pre-built grammars)
@modelcontextprotocol/sdk (stdio transport)
BM25 search (pure JS), JSON file index at ~/.codebase-context-mcp/

Project Structure

src/
  index.ts              # Entry: McpServer + StdioServerTransport
  server.ts             # 5 tool registrations (index, search_symbols, search_code, outline, summary)
  parsers/
    index.ts            # Extension -> language mapping (LANGUAGE_CONFIGS)
    tree-sitter.ts      # WASM init, AST parsing, symbol extraction, VB.NET/XML regex parsers
  indexer/
    indexer.ts           # File walker + incremental indexing pipeline
    store.ts             # JSON read/write to ~/.codebase-context-mcp/
    search.ts            # BM25 scoring + symbol matching + outline/summary
  utils/
    files.ts             # Glob, .gitignore, file filtering, safety limits

Build & Run

npm install
npm run build          # tsup -> dist/index.js
npm run dev            # Watch mode
npm start              # Run the MCP server (stdio)

Key Patterns

tsup.config.ts: All runtime deps MUST be listed in external array — bundling them breaks MCP stdio
Language support: C#/TS/JS/Python/CSS/JSON use tree-sitter WASM; VB.NET and XML use regex parsers (no WASM grammars available)
web-tree-sitter imports: Use named imports { Parser, Language } — NOT default import
Incremental indexing: Files with unchanged SHA-256 hash are skipped on re-index

Supported Languages

TypeScript, TSX, JavaScript, Python, C#, VB.NET, XML, CSS, JSON

Read the full file on GitHub · 132 lines

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.

yesterday First seen · 132 lines · 1,253 tokens per session scan A fcfc1e82e5c8

Subscribe to this mod's changes

codebase-context-mcp CLAUDE.md is an instructions file published in the GitHub repository Jhackman2019/codebase-context-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 1,253 tokens to every session, about $0.0063 per session on Opus 5. 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 2026-08-31.

Data and AI Languages Research

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codebase-context-mcp CLAUDE.md