AnythingMCP lets AI agents connect to external services through dynamically generated MCP tools. Discover available integrations, configure API connections, and invoke service-specific actions without manually building a separate MCP server for each provider.
Codex is OpenAI's coding agent for the terminal. It reads MCP servers from its config and signs in to remote ones with OAuth.
This guide connects Anything MCP to Codex through MewCP, so Codex can use Anything MCP's 8 tools, like anythingmcp_list_connectors, anythingmcp_search_tools and anythingmcp_describe_tool, without your Anything MCP credentials ever reaching the app.
Anything MCP signs in through managed OAuth. MewCP stores the token encrypted, refreshes it before it expires and injects it only at call time. Your agent never holds it, so it can never leak it.
More apps
TinyFish MCP for running AI-driven browser automation tasks, deep web research, persistent browser login profiles, remote CDP browser sessions, and agentic wallet payments.
Manage repositories, pull requests, issues, branches and development workflows on GitHub. Automate software delivery and collaborate across engineering projects.
Connect to external APIs, webhooks and internet services through standard HTTP requests. Build integrations with virtually any platform that exposes a web-based interface.
Give AI coding agents access to a curated library of real-world website designs, screenshots, design systems, and reusable UI components. Search visual references, find similar designs, analyze layouts, extract colors and typography, compare websites, and retrieve copy-ready JSX components for building better interfaces
Other clients
Anything MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Anything MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Run this and approve access in the browser window.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
List the connectors (APIs, databases, applications) this connection can use in the user's AnythingMCP workspace, with how many tools each has and whether they read or write.
Search the tools of the user's workspace by keyword, connector or access (read or write). Returns each tool's name, connector, a short description and whether it reads or writes. Call anythingmcp_describe_tool next for its parameters.
Full description, input schema and annotations of one tool of the user's workspace, and which run tool to use for it.
Run a tool of the user's workspace that only reads data (its access is "read" in anythingmcp_search_tools). Tools that change data are refused here.
Run a tool of the user's workspace that creates, changes, deletes or sends something (its access is "write"). Tell the user what it will do and get their confirmation before each call.
The workspace's own notes on its connectors: what the data means, which tool to use when, and the workflows the workspace approved. Read it before first using a connector.
Knowledge graph of the user's workspace: given an entity or a parameter you need (e.g. "customer_id", "order"), returns which tools produce or relate to it across the connectors of this connection, plus the workspace skills that use it, so you can chain tool calls.
Link to the AnythingMCP dashboard where the user adds, removes or configures connectors, plus the direct URL of each of their MCP servers.
