"github" matching MCP servers:

GitHub's official MCP Server

MCP Server for the GitHub API, enabling file operations, repository management, search functionality, and more.

Connects LLMs and AI agents directly to GitHub repositories, enabling repository inspection, file and tree exploration, code search, commit history, issues, pull requests, and releases for both public and private repos.

Enables LLMs to interact with GitHub via the Model Context Protocol, providing tools for repository management and other GitHub operations.

This read-only MCP Server allows you to connect to GitHub data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Enables querying GitHub Security Advisories from a local cloned advisory database using tools like list_advisories and get_advisory.

Search, document and execute authenticated API calls across all your apps (Gmail, Slack, Stripe, Notion, GitHub, and more) through 4 universal tools whose context footprint stays constant no matter how many connections you add. Hosted remote server with OAuth at https://mcp.withone.ai/mcp, or run locally via npx @withone/mcp.

AgentAvow scans any MCP server, package (npm/PyPI/crates/Docker/Hugging Face), or GitHub repo and returns a signed, offline-recomputable 0–100 trust score with a plain safe / needs-review verdict. Authless and read-only, no account.

Enables MCP clients such as GitHub Copilot, Codex, Claude... to explore a SQL Server 2017+ database read-only: databases, schemas, tables, views, procedures, functions, indexes and dependency graphs, plus filtered, grouped, sampled and paginated queries capped by row limits.

Enables querying the DPC Zettelkasten knowledge base with full-text search, note retrieval, and structural GraphQL queries, each answer backed by pinned GitHub source citations.

An AI conversation management layer that enables creating chat sessions, persisting message history to GitHub, and performing semantic searches over past interactions. It supports multi-turn threading and context injection to integrate external memory sources into Claude conversations.

AI-powered website feedback and visual bug reporting MCP server that lets AI coding assistants access Vynix projects, annotations, and create GitHub issues with rich debugging context.

Read-only MCP server providing AI access to verifiable web, GitHub, and local sources, plus a managed fantasy entity catalog, with strong security and provenance tracking.

Enables AI to read and analyze repository incident scan results, including file diffs and summaries, to help investigate suspicious changes. It is read-only and does not execute code or send data externally.

Serves organizational context to MCP-capable AI agents from a local folder or GitHub repository, and lets agents propose changes that require human approval.

Enables AI assistants to query end-to-end encrypted memories from Cognia workspace via MCP. Supports search, retrieval, and action execution against connected services like Slack, Notion, and GitHub.

Deploy and manage Bult.ai cloud hosting projects from MCP clients like Cursor, Claude Desktop, and Claude Code. Create projects and services, deploy GitHub repositories or Docker images, manage routes and volumes, inspect logs, and troubleshoot deployments from your AI assistant.

Enables agents to deploy software via GitHub Actions only with a signed receipt, providing gated tools to resolve refs, list deployments/environments, and dispatch pipelines for a specific commit.

SassyMCP is a comprehensive MCP server that replaces 75+ individual servers with one 34MB executable. It provides 274 tools for file operations, shell, desktop automation, GitHub/Git, Android interaction, network/security auditing, SSH, OCR, and Windows system management.

Enables any MCP client to look up CVE intelligence — severity summaries, filtered searches, and full per-CVE detail fusing NVD, MITRE-CNA pre-NVD, CISA KEV, EPSS, and GitHub GHSA data — alongside a Shodan-derived internet-exposure footprint showing how many internet-facing services run a version mapping to a given CVE. It is free, keyless, and read-only, and distinguishes verified zeros from unassessed or failed lookups.