"A GitHub repository for agent guardrails" matching MCP servers:

A prompt-injection-aware MCP server demonstrating guardrails for agentic tool use, including permission tiers, untrusted-content quarantine, and heuristic injection detection, with a fictional ticket-triage assistant.

Exposes GitHub issue and pull-request triage capabilities to any MCP client: fetching repository context, classifying and prioritizing requests, finding duplicates, and applying labels, comments, assignments, closures, or reopenings. All writes are policy-gated, dry-run by default, and destructive actions require explicit two-step human confirmation.

Enables real-time assessment of GitHub repository health by exposing tools and resources for repository metadata, open issues, recent commits, and GitHub Actions workflow runs, plus prompts for health reports and issue triage.

Enables Claude to read and organize Trello boards by name, with archive-only writes and no guessing on ambiguous names.

Enables autonomous triage of GitHub issues and pull requests through MCP, with classification, deduplication, prioritization, and safe human-in-the-loop actions.

Enables MCP clients like Claude to query Chinese A-share market data, including K-line charts with forward/backward adjustment, limit-up and limit-down pools, per-stock fund flows, index quotes, and stock news, with automatic symbol normalization and retry handling for throttled data sources.

Provides A-share (Chinese stock market) quantitative analysis through tools for stock screening, northbound capital flow tracking, dragon-tiger list analysis, margin trading, sector analysis, technical indicators, IPO info, and limit-up/down statistics using akshare data.

A secure MCP server for interacting with GitHub issues, pull requests, repository files, and search, supporting both github.com and GitHub Enterprise Server.

Codebase Q&A agent with git-history awareness. Explore a repo with list_files, read_file, and search, plus git log, blame, and diff and a repo map to answer "why did this change?" questions. Runs locally as an MCP server for Claude Code and other MCP clients.

MCP server that exposes GitHub operations as tools for AI agents, enabling code search, issue management, and PR review.

Enables natural-language queries about public GitHub repositories, including issues, pull requests, repo metadata, and READMEs, via the GitHub API.

An MCP server that turns any public GitHub repository into a PDF report containing a codebase summary, the most recent commits, and suggested improvements — generated locally by an Ollama model.

An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.

A stateless HTTP MCP service that exposes GitHub organization member management tools (list, view, add, update role, remove members, and manage invitations) as MCP tools consumable by Claude and other MCP clients.

Enables searching and retrieving GitHub portfolio repositories and their READMEs through natural language.

Read-only MySQL MCP server that lets AI agents list tables, describe schemas, and run SELECT/SHOW/EXPLAIN queries with a row cap, bound to a single database for safety.

MCP server that searches, scores, and ranks GitHub developers for technical recruiting.

Generates daily GitHub work summaries by analyzing commits across all repositories a user owns or contributes to. It provides tools to fetch today's commit activity and deduplicate repository-specific updates for easy reporting.

Automates GitHub workflows (branch creation, testing, commit/push, PR) through natural language instructions in Claude Code.

MCP server exposing GitHub tools for issues, pull requests, and code browsing via the GitHub REST API. Designed for local LLM clients with flat arguments and streamable HTTP support.