"Search for HITL (Human-in-the-Loop or other possible acronyms)" matching MCP servers:

Enables human-in-the-loop AI development where Trello tickets drive analysis, implementation, commits, and board sync in Cursor.

MCP server that inspects older repos, identifies stale guidance, and installs a managed foundation for better Copilot work including instructions, objectives, specialist agents, and insights.

Enables Claude Code sessions to wait for a durable, exact-head GitHub pull-request review and continue the same review/fix/push loop without polling, using Supabase durable state and Realtime wake-ups via ordinary stdio MCP.

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.

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.

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 cross-repository code search over a local mirror of a self-hosted Gitea or Forgejo instance, covering file contents, file paths, and commit messages across all repositories and branches. It also lets users read a single file from the mirror and list mirrored repositories, all without network access during search or read.

Provides Claude with a persistent, auditable memory stored as markdown and YAML files in a private GitHub repo. Enables reading, appending, organizing, and messaging between agent conversations through MCP tools.

Enables AI agents to find public GitHub repositories matching plain-language project descriptions, filter low-quality results by ranking, and fetch a repository's README.

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.

Clones a Git repo into a temp directory so MCP clients can search and read files from another repo for context.

Provides natural language search capabilities for Spryker GitHub repositories, packages, and public documentation. It enables code-level searches across Spryker organizations to help developers find relevant modules and technical information.

An MCP server that enables natural language search capabilities for Spryker packages and code across GitHub repositories, allowing users to find Spryker modules and documentation using conversational queries.

Enables LLMs to perform advanced GitHub code searches with intelligent filtering and content retrieval using Playwright automation, optimized for DeepSeek integration.

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 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.

Enables AI agents to perform unified web searches, GitHub, and GitLab searches with caching, reranking, and fallback across multiple providers.

Enables searching the langchain-ai/langchainjs GitHub repository for TypeScript/JavaScript/Markdown code snippets using the search_langchain tool.

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