"Automating Testing and Debugging for LLMs in Production" matching MCP servers:

Enables LLM agents to manage projects, track issues, log work, and integrate with Git. Provides 23 MCP tools for full project management capabilities.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.

A modular monolith MCP server connecting multiple providers (Redash, PostgreSQL, GitHub) with unified permission, security, and auditing, enabling secure data access and tool execution.

An MCP server providing live GitHub repository and issue search tools, with production-grade features like config validation, structured logging, authentication, and support for both stdio and HTTP transports.

Enables Codex and other MCP clients to read kickoff cards, acceptance criteria, Git evidence, and next steps, then append validated, audited progress events for resumable project handoffs.

Enables agents to read a project's kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, and to append validated, audited progress events with matching Git commits through short-lived scoped credentials.

Self-hosted MCP coding server and unified local Control Center for ChatGPT web, enabling file editing, command execution, Git operations, and optional upstream MCP tools with conversation access controls.

Enables Codex agents to read a project's kickoff card, acceptance criteria, handoff package, progress, Git trail and next step, then append validated, audited, idempotent progress events that become matching project-record Git commits. Access is scoped to one workspace and project through short-lived, revocable, hash-stored credentials that cannot touch members, keys, deletion, publication or deployment.

It enables AI agents to retrieve Git-backed project context, handoff packages, and next actions, then append validated, audited progress events as project-record commits.

It lets AI coding clients read a project’s kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, then append a validated, audited, idempotent progress event with a matching project-record Git commit.

Enables Codex to read a project's kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, and to append validated, audited, idempotent progress events with a matching Git commit.

Enables AI agents and humans to read a project's kickoff card, acceptance criteria, handoff package, progress, Git trail, and next step, then append audited, idempotent progress events that are committed to the project's Git record. Access is scoped per project through short-lived, revocable credentials, keeping high-risk actions outside the tool surface for human approval.

Enables users to safely read, write, edit, create directories, and list trees within a structured local Windows environment, with strict path validation and Git-based undo/version control.

Enables Codex projects to read Git-backed context, acceptance criteria, progress, and handoff packages, and to append validated, audited progress events with matching project-record commits.

Enables Codex users to retrieve Git-backed project context and append validated, audited progress events as matching Git commits, so work can resume safely across sessions.

Enables Codex agents to read a project's context — kickoff card, acceptance criteria, handoff package, progress, Git trail, and next step — over MCP, and to append one validated, audited, idempotent progress event that is committed to a Git-backed project record using scoped, short-lived credentials.

It reads a project's kickoff card, acceptance criteria, AGENTS rules, progress, Git trail, and handoff package, and appends validated, audited progress events tied to project-record Git commits. This gives Codex agents scoped, credential-bound access to resumable project context and safe handoffs.

Enables AI agents to read a project's kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, then append validated, audited, idempotent progress events that are recorded as a matching Git commit. This keeps project truth in Git so work stays visible, resumable, and safely handable between humans and agents through scoped, short-lived credentials.

A workspace of six MCP servers—grounded-cv (hybrid RAG with citations), repo-intel (GitHub repo intelligence), web-research (safe web search/extraction), ats-jobs (unified ATS job boards), outcome-ledger (durable task ledger), and coding-workflows (code review & planning)—purpose-built for agentic hiring evaluations.

Manages isolated Git worktrees for each ZCode thread, enabling safe parallel development with automatic setup, snapshot-based removal, PR review, and background agent orchestration.

Enables users to manage self-hosted Git repositories from ChatGPT and compatible Codex clients via OAuth-secured connections, with independent browser approval for write actions. Supports repository, file, branch, issue, pull request, release, and workflow operations while excluding administrative tools.

A FastMCP-based server designed for the banking and fintech domains, providing tools for database queries, Git operations, and deployment management. It features a modular architecture with reusable prompt templates and integrated security practices for sensitive data handling.

Enables searching GitHub users and repositories, fetching details, and performing stock market technical analysis via AlphaVantage.

Integrates Cline with Azure DevOps services, enabling access to work items, repositories, and pull requests through configurable MCP tools.

Provides AI assistants with comprehensive access to Azure DevOps services including work items, repositories, pull requests, wikis, builds, pipelines, and test plans through 25+ MCP tools with multi-project support.

Provides ChatGPT read-only access to inspect repositories, code, merge requests, pipelines, and CI logs on self-managed GitLab instances, including those reachable only from a private network or VPN.

A free, local room where multiple MCP-compatible AI coding agents collaborate on one codebase — collisions prevented, human in command.

Empowers AI assistants with real-world capabilities including note management, Gmail integration, Google Calendar and Tasks management, and Git repository operations through the Model Context Protocol.

Enables remote access to GitHub REST and GraphQL APIs via dynamically generated and universal tools, with support for Actions log retrieval, schema introspection, and read-only Git clone/fetch.

Enables comprehensive GitHub workflow automation including Actions monitoring, PR management, code search, file operations, and repository management through a code-first architecture that reduces token usage by 98%.

An MCP server that integrates AI assistants like Claude with GitLab's merge requests, allowing them to review code changes, add comments, and approve/unapprove merge requests directly through the GitLab API.

Enables people to open a shared group chat as a card inside their own AI chat, where they and their AIs talk together and post, claim, and confirm tasks on a self-organizing board. Its tools also let any AI read the repository's code and submit a proposed change that becomes a pull request.

MCP server that enables AI assistants to manage Azure DevOps resources including Work Items, Git repositories, pipelines, and user identities.

An MCP server that enables AI models to securely read and manage GitHub issues with authenticated access, confirmation prompts for write operations, and metrics tracking for tool-call reliability.

Provides MCP tools for GitHub code search, Jira sprint status, pull request risk analysis, and project metrics, enabling agentic workflows for developer productivity.

Enables LLMs to efficiently navigate and analyze large diff files by providing pattern-based chunk navigation, allowing direct access to relevant changes without loading entire diffs into context.

MCP server for TNL (Typed Natural Language): per-feature English contracts for AI coding agents. 6 tools — get_impacted_tnls, retrieve_tnl, trace, propose_tnl_diff, approve_tnl_diff, verify — let agents look up relevant contracts, propose contract edits, and verify implementations against them. Drop-in via npx typed-nl init for Claude Code, Codex, Gemini.

A Model Context Protocol server that provides Git version control operations as structured tools for AI coding agents. It enables LLMs to programmatically manage repositories through actions like committing changes, rolling back code, and comparing diffs.

Enables LLMs to search Flux HelmReleases and Argo Applications from kubesearch.dev, and temporarily clone repos to review actual manifests.

Enables LLMs to create animated, narrated tours of GitHub pull requests, with a local browser viewer showing diffs and code highlights while speaking the narration aloud.