"Keep a Changelog" matching MCP servers:

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

Enables coding agents to query the dependency graph of a GitHub backlog, retrieve ordered ready work and prerequisite chains, atomically claim issues, and report blockers—so agents work in the correct order and safely in parallel.

Local stdio MCP server (npx -y caveat-lang mcp) with five tools that validate, check, test and explain programs in Caveat, a rules language whose decisions keep their evidence, grounds and caveats. It also finds what depends on a piece of evidence, so a withdrawn input still leaves a past decision's original basis on record.

Discover and connect your agents with other agents via A2A protocol. Share resources for free or fee.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

Hand a human a rich interactive UI by URL from any MCP client and get structured data back: forms, approvals, surveys, pickers, editable lists. Round-trip human-in-the-loop for agents.

Enables AI agents to participate in meetings by pulling pending requests, reading context, and submitting answers through a Supabase-based MCP server.

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.

Mandatory human approval gate for autonomous AI agents. Before any critical, irreversible, or financially significant action executes — file deletion, production deployment, financial transaction — the agent calls oracle_validate. A human receives a real-time Telegram notification with full context and taps Approve or Reject. The agent waits for the decision before proceeding.

An MCP server that enables local AI models to receive guidance from remote 'senior' AI providers like OpenAI, Anthropic, and Gemini to solve programming problems. It features intelligent multi-turn dialogue management, context synchronization, and automated session history tracking.

Enables a host AI agent to trigger a multi-agent debate, running N-rounds where agents critique each other's answers, then synthesizes a consensus recommendation with ranked options.

Technical Preview: local-first decision memory for AI agents. Agents can keep an answer while losing why it was chosen, what was rejected, and what failed; ShadowGraph stores that reasoning and lets callers review decisions against stored facts. Local stdio MCP; install from GitHub with Node.js 20+.

A machine-enforced workflow protocol for AI coding agents that eliminates false progress. Tasks require verifiable evidence to close, while decisions, assumptions, and open questions persist in a versioned reasoning graph for seamless agent handoffs. Designed to keep deep, long-running projects coherent across sessions, agents, and months.

Provides a hybrid memory architecture with a thin SQLite index and Markdown cold storage, enabling AI agents to write, query, link, and rebuild long-term memories via MCP tools, model-agnostic and zero third-party dependencies.

Lets separate coding-agent sessions coordinate through a shared, role-addressed mailbox instead of a human relaying every message, over a single local SQLite file or a hosted server with many isolated channels. Messages can be sent as tracked obligations that stay open until one side resolves and the other confirms, alongside threads, full-text search, work statuses, and an append-only versioned pin system where protected changes require recorded agreement from every declared role.

Exposes the local Claude Code CLI as a subagent for Codex, enabling background review and implementation jobs with two fixed permission tiers.

Enables agents to start and check monotonic elapsed-time timers so they can verify whether a user-requested minimum task duration has been met, including during tool waits.

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

Enables AI agents to discover, compare, and select the best AI models across multiple providers based on pricing, performance, and capabilities, with real-time cost estimation and benchmarking.

A multi-user AI group chat server via MCP that lets multiple users' AI agents join a shared discussion room to debate topics and reach convergence.