MCP.so
登录

FlowMCP

@FlowMCP

关于 FlowMCP

FlowMCP is a framework for adapting existing web APIs into a standardized Model Context Protocol (MCP) interface, enabling structured, testable, and semantically consistent access for AI systems.

基本信息

分类

其他

许可证

MIT license

运行时

node

传输方式

stdio

发布者

FlowMCP

配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块,请前往代码仓库查看安装说明。

代码仓库

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is FlowMCP?

FlowMCP is a schema-based framework that bridges existing web APIs (REST or GraphQL) with AI systems by standardizing interaction through the Model Context Protocol (MCP). It abstracts complex APIs into clean, structured schema definitions, enabling seamless AI-driven communication with external services.

How to use FlowMCP?

Create a schema in a .mjs file exporting a const schema = {} object with keys like namespace, routes, and handlers, then use FlowMCP.activateServerTools({ server, schema, serverParams }) to connect to an MCP server via a StdioServerTransport. Parameters are defined inline with Zod validation, and modifiers allow pre/post/execute-phase logic injection.

Key features of FlowMCP

  • Schema-based integration with structured route definitions
  • Modifier system for pre-, post-, and execute-phase handlers
  • Inline parameters with Zod type enforcement
  • Embedded test cases to verify real-world API interactions
  • Text-based, human-readable output
  • Activation via standard MCP server tools

Use cases of FlowMCP

  • Integrate APIs like Chainlink, CoinGecko, or Etherscan with AI agents
  • Test API interactions before deployment using built-in test cases
  • Generate valid schemas automatically using an AI-based schema generator
  • Bridge existing REST/GraphQL endpoints into the Model Context Protocol

FAQ from FlowMCP

What does FlowMCP do that alternatives don't?

FlowMCP provides a standardized schema format with versioned contracts, inline Zod validation, embedded tests, and a modifier system for pre/post processing—all optimized for AI-driven consumption via MCP.

What are the runtime requirements?

FlowMCP runs on Node.js and requires the @modelcontextprotocol/sdk and zod packages. Schemas are .mjs files exported with a specific structure.

Where does data live and how is authentication handled?

Data is fetched from external APIs at runtime; no local storage is used. Authentication is managed via environment variables specified in requiredServerParams, which are substituted into headers or root URLs as {{...}} placeholders.

Are there any known limits?

Multiline parameter definitions are not valid in version 1.2.2—all parameters must be single-line. Schema formatting must follow strict indentation (4 spaces) and line spacing rules.

What transport does FlowMCP use?

FlowMCP connects via StdioServerTransport from the MCP SDK, allowing local integration with MCP hosts over standard input/output.

评论

其他 分类下的更多 MCP 服务器