"Open Collective" matching MCP servers:

A registry that enables MCP clients to discover and install MCP servers.

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 Claude to delegate web search, page reading, text drafting, and parallel multi-model image generation to cheaper helper models on any OpenAI-compatible backend. Claude stays in charge of planning and final decisions while consuming fewer of its own tokens.

Swarm intelligence for AI agents, enabling collective decision-making through weighted consensus voting.

Routes every Claude Code/Hermes prompt through a local LLM planner and Open-Jev probe, injecting calibrated probability context while failing open if local services are unavailable.

Open source MCP server for Vectara

Connects Claude Code and Codex to Jev-compatible System One services for context compaction, completion verification, and decision tasks like screening, classification, and gating.

The first open catalog and community for AI agents. Register, search, share skills, find partners. REST API + MCP. Free and open forever. First Czech MCP server included.

Open-source shared rooms for AI agent conversations across Claude Code, Codex, Pi, OpenCode, and DeepSeek Harness. The Apache-2.0 core provides messaging, room history, MCP integrations, and self-hosting on Cloudflare.

Open source AI agent platform with MCP server, browser automation, knowledge packs, and workflow engine. Works with Claude Code, ChatGPT, Cursor, and any MCP client.

Enables multiple MCP agents to read and write a single user-controlled, local-first fact layer under one user identity with explicit scopes, preserving sources, versions, permissions, and audit history. Supports structured memories such as preferences, facts, task state, and decisions, plus structured handoff capsules so one agent can resume another's work by task ID.

Enables AI agents to file review jobs that real human reviewers open, return pinned comments and verdicts on, and approve, so agents can iterate on built sites, videos, and other artifacts based on genuine human feedback.

Enables Codex to operate your already-open Firefox tabs via local MCP tools for status, tab management, navigation, interaction, and screenshots on Windows x64 with Firefox 140+.

An open-source MCP server that turns real business workflows into reviewed, agent-callable commands, enabling safe execution through REST and MCP.

Enables AI agents and IDEs to discover, install, and execute skills over Model Context Protocol via stdio or SSE, with semantic search and framework bridges.

Run the open-source n8n-mcp locally and connect your n8n instance to MCP-compatible AI agents like Codex and Claude Code.

Open coordination network for AI agents and their humans. 13 tools for structured coordination, job marketplace, reputation system. Dual-protocol: MCP + A2A. MIT licensed.

Open-source MCP server for collaborative AI agents, providing a shared mailbox, identity model, and notification fabric.

Connect your AI to social media. Open-source platform for AI agents.

Open-source MCP server hosting tools, agents, extensions, connectors, hooks, and storage for the TAI ecosystem, implementing the tai42-contract interfaces.

An open source registry and proxy that federates MCP, A2A, and REST/gRPC APIs with centralized governance, discovery, and observability. It optimizes agent and tool calling, and supports plugins.

Enables HTTP-based MCP clients like Open WebUI to control a real logged-in browser via a tray app, secured with bearer-token and CIDR authentication.

Lets Codex, Claude Code, and other local MCP agents control tabs in already-open Chrome profiles using existing website logins, with setup handled through the coding agent.

Provides MCP tools to query device status, customer data, orders, and open incidents, and draft incident notes using mock SAP data.

Enables AI agents to control Chrome, Edge, Brave and other Chromium browsers through an extension and native messaging host, exposing a Claude-in-Chrome-compatible tool set for real clicks, typing, screenshots, accessibility-tree reading, page text, form filling, JavaScript execution, console and network inspection, file uploads and GIF recording. Agent sessions run in isolated tab groups with per-site permission prompts, activity logging and a global stop control.

Provides seamless access to 200+ AI models through OpenRouter's unified API, featuring multi-model collaboration, vision support, intelligent benchmarking, and collective intelligence capabilities for enhanced decision-making.

Unofficial open-source MCP bridge that gives Cursor agents hands in your real Chrome browser. Enables navigation, clicking, filling, screenshots, and other browser actions with permission modes.

Hosted shared knowledge base for AI agents. Store, search, and retrieve structured knowledge using semantic search. Agents contribute to a growing collective intelligence that compounds over time. No install — just a URL.

MCP server enabling LLMs to perform browser tasks via SSE transport, allowing clients like Cursor.ai and Claude to open websites and interact with web content through natural language commands.

Enables AI agents to control a live Blender session through the Model Context Protocol, including scene and object manipulation, rendering, PolyHaven asset access, and runtime switching between multiple LLM backends.