MCP Tree-sitter Server

Created By
wralea year ago
MCP Server for Tree-sitter
Overview

What is MCP Tree-sitter Server?

MCP Tree-sitter Server is a Model Context Protocol (MCP) server that provides code analysis capabilities using tree-sitter, designed to give intelligent access to codebases with appropriate context management.

How to use MCP Tree-sitter Server?

To use the MCP Tree-sitter Server, install it via pip and configure it with Claude Desktop either through the MCP CLI or manually. You can register projects and analyze code using various commands.

Key features of MCP Tree-sitter Server?

  • Flexible exploration of code at multiple levels of granularity.
  • Context management to provide relevant information without overwhelming the user.
  • Language agnostic, supporting multiple programming languages.
  • Structure-aware with AST-based understanding.
  • Searchable code patterns using text search and tree-sitter queries.
  • Caching for optimized performance.
  • Symbol extraction and dependency analysis.
  • State persistence between invocations.
  • Built-in security features.

Use cases of MCP Tree-sitter Server?

  1. Analyzing code structure and syntax trees.
  2. Searching for specific code patterns.
  3. Extracting symbols and analyzing code dependencies.
  4. Managing projects and their configurations.

FAQ from MCP Tree-sitter Server?

  • What languages does it support?

It supports many programming languages including Python, JavaScript, TypeScript, Go, Rust, C, C++, Swift, Java, Kotlin, Julia, and APL.

  • Is it easy to install?

Yes! You can install it using pip with a simple command.

  • Can it run as a standalone server?

Yes! You can run it as a standalone server using the provided command.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
wrale
Star
32
Language
Python
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago