What is mcp-graphql-forge?
It is a lightweight MCP server that transforms a GraphQL endpoint into a set of MCP tools, where each tool is defined in a YAML file specifying the query and its parameters.
@UnitVectorY-Labs
基本信息
A lightweight, configuration-driven MCP server that exposes curated GraphQL queries as modular tools, enabling intentional API interactions from your agents.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
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。
mcp-graphql-forge is a lightweight, configuration-driven MCP server that exposes curated GraphQL queries as modular tools, enabling intentional API interactions from your agents. It lets you turn any GraphQL endpoint into an MCP server whose tools are defined in YAML files that specify the GraphQL queries and their parameters.
Install by downloading a pre-compiled executable from GitHub Releases for macOS, Linux, or Windows, or via go install github.com/UnitVectorY-Labs/mcp-graphql-forge@latest. Configure with the --forgeConfig command line parameter (or FORGE_CONFIG environment variable) pointing to a folder containing forge.yaml (server URL, optional token command) and tool definition YAML files. Run in stdio mode by default; add --http 8080 for streamable HTTP mode.
--http flag.It is a lightweight MCP server that transforms a GraphQL endpoint into a set of MCP tools, where each tool is defined in a YAML file specifying the query and its parameters.
Authentication is handled via an optional `token_command` in `forge.yaml` that fetches a Bearer token. If no token command is provided, the Authorization header from the incoming MCP request is passed through to the GraphQL endpoint.
The server supports three output formats: `raw` (pass-through), `json` (minimized), and `toon` (Token-Oriented Object Notation, which can reduce token usage by 30-60% for tabular data).
By default it runs in stdio mode. It can also run in streamable HTTP mode by specifying `--http <port>`, which exposes an endpoint at `http://localhost:<port>/mcp`.
Each instance can only connect to a single GraphQL server at a single URL. All GraphQL queries are exposed as tools, not as resources.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
评论