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.
Encrypted at rest, isolated from the model
Resolved from an AES-256-GCM vault at the moment of the call and attached to the request — the model never sees the secrets.
Try asking
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.
One endpoint, the same key, whichever client you use.
~/Library/Application Support/Claude/claude_desktop_config.json (Mac) · %APPDATA%\Claude\claude_desktop_config.json (Windows)
Replace API_KEY with your own key.
Already have an "mcpServers" section in your config? Just add the server entry inside it.
Discovery, routing, credentials, tool scoping and execution logs all happen at the gateway→connections stay ACTIVE with no work from you
Anything MCP runs through a gateway that holds the credentials, scopes the access and records every call.
Managed auth, hosted MCP servers, and every Anything MCP tool your agent needs.
Free to start.