freshcrate
Skin:/
Language:English/įŽ€äŊ“中文
Home > MCP Servers > octocode-mcp

octocode-mcp

MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturally across public & private repos based on your permissions | Transform any accessible codeb

agentaiai-agentsai-toolsclaude-aicode-intelligencecode-searchcontexttypescript
Why this rank:Strong adoptionHealthy release cadenceRelease freshness

Description

MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturally across public & private repos based on your permissions | Transform any accessible codebase/s into AI-optimized knowledge on simple and complex flows | Find real implementations and live docs from anywhere

README

Octocode: Research Driven Development for AI

Octocode Logo

Stop Guessing. Start Knowing.

Empower your AI assistant with the skills of a Senior Staff Engineer.

octocode.ai

Installation

Prerequisites: GitHub authentication required. See Authentication Setup.

Recommended: Octocode CLI

npx octocode-cli install

Interactive setup wizard with GitHub OAuth, MCP server installation, and skills marketplace. Pass --ide <ide> for non-interactive install (e.g. npx octocode-cli install --ide cursor).

Alternative Methods

One-Click Install (Cursor)

Install in Cursor

Manual MCP Configuration

Add to your MCP configuration file:

{
  "mcpServers": {
    "octocode": {
      "command": "npx",
      "args": ["octocode-mcp@latest"]
    }
  }
}
Research Skill (Direct Install) 
npx add-skill https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-research

MCP Server

The Octocode MCP Server connects your AI assistant to code:

  • GitHub & GitLab: Search repositories, find usage patterns, read implementations, explore PRs
  • Local Tools: Search code, browse directories, find files in your local codebase
  • LSP Intelligence: Go to Definition, Find References, Call Hierarchy -- compiler-level understanding
react_vue_comparisson.mp4

Skills

Agent Skills are a lightweight, open format for extending AI agent capabilities. Skills index: skills/README.md

Skill What it does
Researcher Code search & exploration — local LSP + external (GitHub, npm/PyPI)
Research Multi-phase research with sessions, checkpoints, state persistence
Engineer Understand, write, analyze, audit code — AST + LSP + dependency graph
Plan Evidence-based planning: Understand > Research > Plan > Implement
RFC Generator Formal technical decisions with alternatives, trade-offs, and recommendations
PR Reviewer PR & local code review across 7 domains with LSP flow tracing
Roast Brutal code critique with file:line citations and severity levels
Prompt Optimizer Turn weak prompts into enforceable agent protocols
Doc Writer 6-phase pipeline producing 16+ validated docs
octocode-skill.mp4

Documentation

For the full documentation index, start here: docs/README.md

Recommended quick links:

The Manifest

"Code is Truth, but Context is the Map." -- Read the Manifest for Research Driven Development to understand the philosophy behind Octocode.

Contributing

See the Development Guide for monorepo setup, testing, and contribution guidelines.

Built with care for the AI Engineering Community

Release History

VersionChangesUrgencyDate
9.1.1## What's Changed * add releases workflow by @bgauryy in https://github.com/bgauryy/octocode-mcp/pull/237 **Full Changelog**: https://github.com/bgauryy/octocode-mcp/compare/9.1.0...9.1.1Low12/15/2025
9.1.0# Changelog - PR #236: Build System Modernization ## [Unreleased] ### version: "9.1.0" ### Added - **Standalone Binary Distribution** - Pre-compiled binaries for all major platforms without Node.js dependency - macOS (Apple Silicon & Intel) - Linux (x64, ARM64, Alpine/musl) - Windows (x64) - **One-line Installer Script** - `curl -fsSL https://raw.githubusercontent.com/bgauryy/octocode-mcp/main/install/install.sh | sh` - **Bun Build Scripts** - Cross-compilation support via `Low12/15/2025
8.0.0# CHANGELOG - Octocode MCP v8.0.0 > **TL;DR**: Major release introducing local filesystem research capabilities, new license model, and enhanced prompt commands. ## 🚀 New Features ### Local Filesystem Research (`octocode-mcp-local` v1.0.1) New MCP server package for local codebase exploration using native Unix tools. - **`local_ripgrep`** - Fast pattern search with regex, context lines, and pagination - **`local_view_structure`** - Directory tree with file sizes and filtering -Low11/26/2025
7.0.13# PR #211: Prompts Overhaul **Created:** November 20, 2025 ## 📊 Changes Overview | Metric | Value | |--------|-------| | Files Changed | 16 | | Additions | +3,201 | | Deletions | -96 | | Net Change | +3,105 | --- ## đŸŽ¯ What's New ### ✨ New Features #### 🔒 Security Review Prompt (`review_security.ts`) - **New AI-guided security review system** - Implements systematic vulnerability assessment workflow - **Key capabilities:** - Attacker mindset approach for threaLow11/20/2025
7.0.10feat: Add MCP Registry support with automated publishing - Add server.json for MCP Registry registration - Implement automated publishing workflow - Enhance package distribution with proper file inclusion - Add comprehensive CI/CD documentation - Clean up tool output hints This release makes Octocode MCP discoverable in the official MCP Registry and establishes a robust automated publishing pipeline.Low11/10/2025
7.0.0# PR #142: Major Architecture Refactoring - Error Handling, Type System, and Code Organization ## Overview This PR represents a comprehensive refactoring of the codebase focused on improving maintainability, code organization, and developer experience. The changes consolidate error handling, centralize type definitions, and introduce reusable utility patterns across all GitHub API tools. **Version**: 6.3.0 → 7.0.0 (Major version bump) ## Summary Statistics - **Files Changed**: 30 Low10/15/2025
6.3.06.3.0 - Add researchGoal - Improve production monitoring Low10/3/2025
6.2.0## [6.2.0] - 2025-09-29 - Schema Refactoring & Context Improvements ### MAJOR ENHANCEMENT: Schema Architecture Refactoring #### Added - **Centralized Schema Descriptions**: New `schemDescriptions.ts` module consolidates all tool schema descriptions - Eliminates code duplication across individual schema files - Provides consistent, centralized parameter descriptions - Enables easier maintenance and updates of tool documentation - Supports structured categorization (scope, filtLow9/28/2025
6.1.1 Major Changes Schema Complexity Reduction Removed verbose parameter: Eliminated verbose fields from all tool schemas and implementations, reducing schema complexity Simplified base schemas: Consolidated BaseBulkQueryItemSchema and BaseSingleQuerySchema into unified BaseQuerySchema Streamlined parameter validation: Replaced complex flexible array schemas with simpler SimpleArraySchema utilities Parameter Naming Standardization Code Search: queryTerms → keywordsLow9/27/2025
6.0.0### đŸŽ¯ **Overview** This PR implements a comprehensive token reduction and optimization strategy for the Octocode MCP server, focusing on streamlining the codebase and improving response efficiency for AI assistants. ### 🔧 **Major Changes** #### **1. Tool Removal & Simplification** - **Removed NPM/Package Search Tools** (`packageSearch`, `npmViewPackage`) - Eliminated entire NPM ecosystem support (`src/npm/` directory) - Removed package search schemas and command builders - UpdLow9/24/2025
v5.0.0https://github.com/bgauryy/octocode-mcp/pull/116Low8/25/2025
v2.3.28Added MCP features Sampling and Prompts Low8/22/2025

Dependencies & License Audit

Loading dependencies...

Similar Packages

claude-code-safety-net🛡ī¸ Enhance code safety with Claude Code Safety Net, a tool designed to identify and mitigate risks in your codebase effectively.main@2026-06-07
deep-code-reasoning-mcpA Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google's Gemini AImain@2026-06-04
mcp-verified-repo-memoryProvide reliable, repository-scoped memory for AI coding agents with code citations, just-in-time verification, and stale-proof data management.main@2026-06-02
holaOSThe agent environment for long-horizon work, continuity, and self-evolution.main@2026-06-02
crewformBuild your AI team with Crewform. Orchestrate specialized, autonomous agents to collaborate on complex tasks and connect outputs to your stack. — AI Orchestration for Everyonev1.9.3

More in MCP Servers

PlanExeCreate a plan from a description in minutes
agentroveYour own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, GitHub Copilot, OpenRouter), custom skills, and MCP servers.
ProxmoxMCP-PlusEnhanced Proxmox MCP server with advanced virtualization management and full OpenAPI integration.
node9-proxyThe Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.