What is mcp-server-tree-sitter AGENTS.md?

Repository instructions for an MCP Tree-sitter Server, a Python service that analyses source code using Tree-sitter and connects to AI assistants through MCP.

Use them when setting up the server, modifying its Python code, understanding its language and tool structure, or checking changes before committing.

They collect setup, architecture, configuration, and pre-commit checks in one place, reducing mistakes when changing the project.

How wrale/mcp-server-tree-sitter configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to wrale/mcp-server-tree-sitter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/wrale/mcp-server-tree-sitter/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/wrale/mcp-server-tree-sitter

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wrale/mcp-server-tree-sitter/agents-md/github.svg)](https://agentmods.dev/instructions/wrale/mcp-server-tree-sitter/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/wrale/mcp-server-tree-sitter/agents-md"><img src="https://agentmods.dev/badge/instructions/wrale/mcp-server-tree-sitter/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/wrale/mcp-server-tree-sitter/agents-md"><img src="https://agentmods.dev/badge/instructions/wrale/mcp-server-tree-sitter/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 823 This file is loaded in full into every session.

When invoked 823 The same file — it is already loaded in full.

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.

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 5.1	$0.00823	$0.00823
Opus 5.5	$0.00329	$0.00329
Sonnet 5.5	$0.00165	$0.00165
Haiku 4.5	$0.00082	$0.00082

Measured 2mo ago against content hash 7f25271e860c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server-tree-sitter AGENTS.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 2mo 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.

AGENTS.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working in this repository.

Project Overview

MCP Tree-sitter Server — a Model Context Protocol server providing code analysis via tree-sitter. Python 3.10+, packaged with hatchling, managed with uv.

Setup

uv venv --python 3.12
uv pip install -e ".[dev]"

Before Committing

All of these must pass — CI enforces them:

ruff check src/               # Lint (E, F, I, W, B rules)
ruff format --check src/      # Format check
mypy src/mcp_server_tree_sitter  # Type check
pytest tests/                  # 217+ tests, must all pass

Or use the Makefile: make prepare

Key Architecture

Source: src/mcp_server_tree_sitter/
DI container: di.py — constructs all dependencies; avoid circular imports with it
Config: config.py — ConfigurationManager auto-loads YAML from MCP_TS_CONFIG_PATH or ~/.config/tree-sitter/config.yaml. Precedence: env vars > YAML > defaults
Language registry: language/registry.py — maps file extensions to tree-sitter-language-pack identifiers
Templates: language/templates/ — per-language query templates (one file per language)
Tools: tools/ — MCP tool implementations (analysis, search, ast_operations, file_operations)
Helpers: utils/tree_sitter_helpers.py — includes query_captures() compat wrapper for tree-sitter >= 0.24

tree-sitter API Compatibility

tree-sitter >= 0.24 removed Query.captures(). Always use the query_captures(query, node) wrapper from utils/tree_sitter_helpers.py instead of calling query.captures() directly. This applies to both source and test code.

Adding a New Language

Create language/templates/<lang>.py with a TEMPLATES dict (follow existing patterns like go.py)
Register the file extension in language/registry.py _language_map
Import and register in language/templates/__init__.py
Add default symbol types in tools/analysis.py extract_symbols()
Verify the language identifier works: from tree_sitter_language_pack import get_language; get_language("<id>")

Read the full file on GitHub · 72 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.

2mo ago First seen · 72 lines · 823 tokens per session scan A 7f25271e860c

Subscribe to this mod's changes

mcp-server-tree-sitter AGENTS.md is an instructions file published in the GitHub repository wrale/mcp-server-tree-sitter (311 stars, last pushed 5mo ago), licensed MIT. It adds 823 tokens to every session, about $0.0033 per session on Opus 5.5. 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 2026-08-30.

Debugging ai-assistant ast claude claude-ai claude-desktop code-analysis

mcp-server-tree-sitter AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-server-tree-sitter AGENTS.mdwrale/mcp-server-tree-sitter	Instructions file	311	5mo ago	MIT	A	823	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-server-tree-sitter: Instructions file for Codex