MCP server · Flow AI

flowai-harness

flowai-harness can expose its runtime tools as Model Context Protocol (MCP) servers, so an MCP-aware client (Claude, IDEs, agents) can call the data-agent tools defined in a Flow AI runtime. This is a capability of the harness rather than a single hosted endpoint operated by Flow AI - each host deploys its own server bound to its runtime and tenant.

Open docs → Flow AI provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Flow AI Type: Documentation link Transport: Host: flow-ai.com

Documentation

https://flow-ai.com/docs/guides/mcp

Documentation link · transport

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.