Enables coding agents to publish HTML pages and small sites over MCP, returning a stable link and keeping every version, with access limited to specific people, an organization, or anyone with the link.
۩ Plan your projects with THC!
MLLM planning harness for Software Engineering, modifiable for other purposes, released as an MCP server.
Bring your own API keys.
Open-Source now, my dear! :D
Connects AI agents to The Agents Hub, visualizing them as pixel characters on a tile-based property with tools for state, assets, inboxes, and multi-agent orchestration.
Enables multiplexing multiple MCP servers behind a single gateway connection that lazily loads only the tool schemas needed for the current turn, cutting context usage while providing OAuth authentication, circuit breakers, and hot reload.
Enables AI agents to send and receive structured, cryptographically-verifiable messages, with tools for inbox management, task delegation, and agent discovery.
Enables MCP hosts such as Claude and Cursor to dispatch tasks to live marketplace agents, poll or wait for verified settled results, list available agents by capability, and retrieve live protocol statistics with atomic settlement on Tempo.
498 MCP tools across 12 industry verticals. Marketplace, escrow, DeFi, legal, healthcare, insurance, construction, and trades. USDC payments on Base L2.
Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.
Extensible MCP server that aggregates multiple backends (email, browser, todoist, etc.) behind a single endpoint, with secure deployment via Cloudflare Tunnel and Workers.
Agent registry, arena reputation system, and Latent Credits economy. Register agents, earn Elo via duels, transact credits, and make x402 micropayments.
A Model Context Protocol server that enables seamless interaction between LLM-based agents and Apple Health data, allowing users to query, analyze, and manage health records through natural language commands.
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.
Local-first MCP server that enables multiple Claude agents to coordinate through a shared message bus with SQLite persistence and real-time clock anchoring.
Enables Claude Desktop, Claude Code, and Codex to send approved coding tasks to separate Oh My Pi sessions on Windows, monitor their progress, and wake the assistant when work finishes.
A self-hosted MCP browser service that lets AI agents drive a real headful Chromium, patchright, or camoufox session — navigating, reading accessibility snapshots, clicking, typing, and taking screenshots — with scheduled keepalive visits and Google Meet notetaking. When a CAPTCHA, cookie wall, or 2FA appears, it hands the live tab to a human via a phone-friendly link and resumes the agent afterwards.
Gives AI agents their own email address with inbound parsing, classification, extraction, and prompt injection screening, plus tools to manage mailboxes, send/receive emails, and handle draft approval workflows.
Human-in-the-loop approval inbox for AI agents: an agent proposes an action (send email, post comment, run a command), a human approves, rejects, or edits it from a web, mobile, or Slack/Discord/Telegram inbox, and the agent only runs on approval. Full audit trail, self-hostable (MIT).
A Model Context Protocol server that provides real-time Caltrain schedule information, allowing AI assistants to look up train departures between any stations and access station information using GTFS data.
Connects Claude Code to the Perplexity Comet browser to enable autonomous web browsing and agentic research. It features multi-tab management, smart completion detection, and a specialized tool set for organized information retrieval.
Provides AI assistants with real-time access to the AGNO framework documentation by enabling them to browse, search, and fetch documentation pages. This server allows users to query information about AGNO's Agents, Teams, and Workflows directly through MCP-compatible clients.
Enables selecting a saved Codex or Claude Code session from the same PC and importing its recent context into the other tool, so work can continue across clients with source and omission information.
A server implementing Model Context Protocol that enables LLMs to interact with the ZenML platform, providing access to pipeline data, stack information, and the ability to trigger new pipeline runs.
A TypeScript server implementing the Model Context Protocol (MCP) that provides datetime and timezone information to AI agents and chat interfaces, allowing them to access current time in various timezones.
Enables real-time web search with source citations by leveraging Perplexity AI's Sonar models through SAP AI Core. It integrates with Claude Code to provide deep analysis, reasoning, and up-to-date information from the web.
A simple server that implements the Model Context Protocol, allowing AI models like Claude to fetch real-time weather information for any location using the wttr.in API.
The AgentOps MCP server provides access to observability and tracing data for debugging complex AI agent runs. This adds crucial context about where the AI agent succeeds or fails.
A Model Context Protocol server that allows AI assistants to interact with the VRChat API, enabling retrieval of user information, friends lists, and other VRChat data through a standardized interface.
Enables AI assistants to connect over streamable HTTP with bearer authentication to tools for agent lifecycle, email, phone, platform, vault, and browser extension management.
Cloud file storage with an email address for every bucket, for humans and AI agents. Store and share files through authorized account and bucket access, keep versions, and read incoming messages and attachments. Connect through the hosted MCP server with OAuth.
Enables AI agents to build, activate, and run human-in-the-loop workflows in which real reviewers respond to tasks from a mobile app, then retrieve their answers as run results. Provides tools for managing workflow steps and input fields, monitoring or retrying runs, issuing join codes, and inviting reviewers by email.
Provides an email inbox for AI agents, enabling them to read mail that awaits a reply, respond in-thread, and retrieve attachments or their extracted text.
Enables AI agents from different platforms to read and post replies directly into group or one-on-one chats, with tools for messaging, chat history, and owner approvals instead of email.
Publishes the app your coding agent built so your coworkers can use it: a private address behind email sign-in, its own database, scheduled jobs and email reminders, with tools to invite people, read logs, roll back and export data.
Drive Clearcote, a Chromium build with its fingerprint protection patched into the engine, from any MCP client: about 20 tools to navigate, read, extract, click, fill, screenshot and keep sessions, plus a CDP endpoint that hands the same browser to Playwright or Puppeteer. The server lives in the repo's mcp/ folder (npx clearcote-mcp or pip install clearcote-mcp).
Gives AI agents a wallet, email, phone number, and instant access to paid MCP tools including web search, image/video/music generation, email, SMS, voice calls, and code execution.
Keeps large tool outputs out of an agent's context window by spilling them to disk and handing back a short pointer instead. Lets the agent pull only what it needs — exact numbered line ranges read directly from disk, or verbatim relevant lines returned by a small model answering a question about the stored output, plus tools to open, list, and close documents.
Enables managing multiple MCP service nodes over SSE or stdio and aggregating them into a single unified SSE endpoint, allowing compatible clients to access all integrated MCP tools through one address.
Connects AI agents and MCP clients to Gorgias through the PipMCP gateway, where tools are discovered with real hosted schemas and calls run under workspace, policy, approval and usage controls. Enables tasks such as finding existing customers and creating customer records with email channels using a single PipMCP API key.
Enables agents to discover peers on the same host or across connected hosts, exchange messages with them, wait for their replies, and spin up new agents with a task. Messages are tagged with the sender's address so recipients can answer back, with cross-host traffic relayed end-to-end encrypted.
A transparent message ferry between Claude Desktop and Claude Code CLI, enabling task delegation with any MCP configuration without the bridge needing to know about specific MCPs.
Enables Claude Code to delegate subagent model routing and to answer yes/no, choice, and score questions about entire files using a small, cheap external model, so large numbers of files can be screened without filling the main context window.
Cross-CLI agent messaging: let Claude Code / Codex / Pi / ZCode terminal agents message each other like email. File-based mailboxes with a resident delivery hub that picks the channel per recipient (tmux injection / native queue / daemon queue / pull), federated across hosts over ssh.
A persistent 24/7 background daemon that aggregates all downstream MCP servers into one unified connection and layers on a real-time notification gateway so AI agents can receive events from X/Twitter, Slack, Email, and webhooks.
Enables Cursor agents to communicate via a shared chat room, allowing them to ask questions, share status, and warn about conflicts while collaborating on the same repo.
Lets AI agents announce task completion through a Windows desktop notification and a spoken message in a locally generated voice, with offline language detection across many languages and voices. Agents can call it with a short summary of what they finished so you hear about it without watching the screen.
Enables email-only AI agents to call tools by attaching JSON-RPC 2.0 request files and a token to an email, receiving summarized results back as .result.json files in a threaded reply.
Provides a standardized protocol for tool invocation, enabling an AI system to search the web, retrieve information, and provide relevant answers through integration with LangChain, RAG, and Ollama.
Enables an AI assistant to run tasks on a hosted cloud desktop that belongs to the user, with a browser that stays signed in to their accounts, its own email address, and its own files, so it can fill forms, download and edit documents, and carry out long jobs that outlast a chat reply, returning answers with screenshots and recordings. It also exposes tools for checking current activity, task history, sent mail, interrupting a run, and saving or recalling notes, reached over OAuth-authenticated Streamable HTTP or a stdio bridge.
An MCP App message bridge that connects the AI living in a ChatGPT web conversation to your own home system, so chatbots, bots, and scheduled tasks can send it messages that it sees and answers right inside the conversation. It also exposes every home MCP server (search, notes, email, and more) through the single home_tools / home_call toolbox, letting one window reach all your tools.
Enables AI agents across a team to message each other over MCP like email, with notes to offline agents held in an inbox until read, plus tools for listing contacts, setting aliases, sending notes, and marking them handled. Access is scoped to an organisation's GitHub members and guests, and the server can be self-hosted on one container with Postgres.