mcp servers on Function Compute
mcp servers on Function Compute
当前市场中存量 MCP Server 绝大部分采用 STDIO 传输机制实现，为了能够实现存量的 MCP Server 代码无需任何改变即可转为 SSE 模式，我们设计了 mcp-proxy，工作原理如下图:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| brave-search | [start-mcp-brave-search](./start-mcp-brave-search/src) |
| ever-art | [start-mcp-ever-art](./start-mcp-ever-art/src) |
| sequentialthinking | [start-mcp-sequentialthinking](./start-mcp-sequentialthinking/src) |
| everything | [start-mcp-everything](./start-mcp-everything/src) |
| quickchart | [start-mcp-quickchart](./start-mcp-quickchart/src) |
| firecrawl | [start-mcp-firecrawl](./start-mcp-firecrawl/src) |
| agentql | [start-mcp-agentql](./start-mcp-agentql/src) |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Google search for agents: web, news, images, places, shopping, Scholar. Paid per call over x402.
Read any public web page as clean Markdown for LLMs, with its metadata. Paid per call, x402.
MCP server (stdio): fetch web pages as clean readable markdown via the AgentForge API
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.