Runway (runway.team)
Drive mobile release management: releases, checklists, fix requests, Build Distro.

618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
65 of 618 connectors in Developer ToolsShow all
Drive mobile release management: releases, checklists, fix requests, Build Distro.
Query, create, publish and release structured content.
Pull production errors into a coding agent.
Operate Speko voice AI from your agent: inspect calls and transcripts, manage phone numbers and knowledge bases…
Give your AI agent a persistent, hardware-isolated Linux sandbox it can create, run commands in, checkpoint and destroy.
Search public Stack Overflow questions and pull answer threads into an AI agent.
Manage Stytch projects, redirect URLs, email templates, SDK config and API secrets from an AI assistant.
Open the real production session recording — events, screenshots, DOM, console, network — to find root cause.
Run SQL, apply migrations, deploy Edge Functions and manage projects from an AI assistant.
Publish APIs and developer portals from an AI agent.
Official MCP demo server rendering interactive WebGL scenes in the chat.
Give a coding agent your team's Slack, Jira, GitHub and wiki context.
Drive Vercel's v0 app builder: create chats, send prompts, approve the agent's plans and permissions, fetch previews.
Search Vercel docs, inspect deployments, read logs, deploy to production and buy domains.
Give a coding agent version-accurate Vuetify component APIs, install guides and v3-to-v4 migration notes.
Build pages, manage CMS content and publish Webflow sites.
Build and edit a WeWeb no-code app against your live project.
Product names and logos belong to their owners. Each connector is built by its own developer, and Agentman is not affiliated with them. The ones Agentman builds and runs are marked “Built and run by Agentman”.
A server that exposes a tool’s capabilities over the Model Context Protocol, so an AI agent can call them directly. It is the standard way to let an assistant act in a system rather than just describe it.
Each server page carries its connection URL, which works in any MCP-compatible client. In Agentman Studio connecting is one click and there is no config file to edit.
Most are not. Each is built by its own developer, and each page names them and links to their documentation. The few Agentman builds and runs are marked “Built and run by Agentman”. Every page lists what the server exposes and cites the sources its factual claims come from.
Each page lists the tools the server exposes. Where we could read the server directly, every tool carries the safety label its vendor gave it: read-only, acts, or destructive. Each page also has a Limits section; read both before connecting anything to a production system.
Connect any of these once and your agents call their tools on their own: on a schedule, in a workflow, with nobody at the keyboard.