What types of MCP servers can be integrated?
The server currently supports MCP servers using the stdio transport. SSE (Server‑Sent Events) support is planned for a future release.
@luis1232023
基本信息
Stdio Mcp Server 转为 RestFul,轻松部署与 Web 服务集成, mcp gateway
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。
Nest Llm Argent is an MCP (Model Context Protocol) server that acts as a forwarding layer to integrate MCP tools with existing HTTP‑based web services. It aggregates multiple MCP servers and exposes a unified HTTP API for large language model (LLM) interactions, making it easier to embed MCP capabilities into existing NestJS or other web backends.
The recommended deployment method is to bundle each MCP Server as a private npm package, install it with npm install, and configure integration via a mcp.config.json file. The server provides predefined HTTP endpoints (e.g., POST /api/mcp/tools, POST /api/mcp/agent) that can be called to list tools, invoke tools, access resources, or run an LLM agent.
The server currently supports MCP servers using the stdio transport. SSE (Server‑Sent Events) support is planned for a future release.
MCP servers are packaged as private npm packages and installed via `npm install`. A `mcp.config.json` file defines the paths and arguments for each server, allowing centralized management.
— (Not mentioned in the README.)
Data lives in the individual MCP servers that are integrated. Nest Llm Argent acts as a proxy and does not store the data itself.
All endpoints use HTTP POST. The main ones are `/api/mcp/tools`, `/api/mcp/functools`, `/api/mcp/tools/call`, `/api/mcp/resources`, `/api/mcp/prompts`, `/api/mcp/all`, and `/api/mcp/agent`.
28-tool MCP server for web scraping, crawling, deep research & autonomous extraction — clean Markdown & structured JSON for Claude, Cursor & any MCP client. 1,000 free one-time credits, local-Ollama LLM support.
BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude
FACTANKER serves 1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending, sourced from SEC EDGAR, FFIEC call reports, IRS 990 filings and USAspending. Every value carries its evidence: fil

Amazon Seller Central MCP server. Connect Seller Central, Vendor Central and Amazon Ads to Claude, ChatGPT, Gemini or Cursor, and ask for net profit per SKU with your own COGS, VAT and FBM shipping costs, PPC down to the

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai
评论