extract-mcp-servers-from-url

Extract MCP servers from a specified URL to collect and organize server information from web sources.

Instructions

Extract MCP Servers from a URL

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes

Implementation Reference

src/mcp_server_collector/server.py:66-117 (handler)

Main tool handler function (@server.call_tool()). For 'extract-mcp-servers-from-url', fetches content from URL via helper, then extracts MCP servers using shared logic and returns as text.

@server.call_tool()
async def handle_call_tool(
    name: str, arguments: dict | None
) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
    if not arguments:
        raise ValueError("Missing arguments")

    content = None
    
    match name:
        case "extract-mcp-servers-from-url":
            url = arguments.get("url")
            if not url:
                raise ValueError("Missing url")

            content = await call_fetch_tool(url)
            
        case "extract-mcp-servers-from-content":
            content = arguments.get("content")
            
        case "submit-mcp-server":
            url = arguments.get("url")
            avatar_url = arguments.get("avatar_url") or ""
            result = await submit_mcp_server(url, avatar_url)
            content = json.dumps(result)

            return [
                types.TextContent(
                    type="text",
                    text=content,
                )
            ]
        case _:
            raise ValueError(f"Unknown tool: {name}")

    if not content:
        raise ValueError("Missing content")

    logger.info(f"Fetched content from {url}: {content}")

    mcp_servers = await extract_mcp_servers_from_content(content)
    if not mcp_servers:
        raise ValueError("Extracted no MCP Servers")

    logger.info(f"Extracted MCP Servers from {url}: {mcp_servers}")

    return [
        types.TextContent(
            type="text",
            text=mcp_servers,
        )
    ]

src/mcp_server_collector/server.py:24-30 (schema)
Input schema definition for 'extract-mcp-servers-from-url' tool: requires a 'url' string property.
```
inputSchema={
    "type": "object",
    "properties": {
        "url": {"type": "string"},
    },
    "required": ["url"],
},
```

src/mcp_server_collector/server.py:20-31 (registration)

Registration of the tool in @server.list_tools(): defines name, description, and input schema.

return [
    types.Tool(
        name="extract-mcp-servers-from-url",
        description="Extract MCP Servers from a URL",
        inputSchema={
            "type": "object",
            "properties": {
                "url": {"type": "string"},
            },
            "required": ["url"],
        },
    ),

src/mcp_server_collector/extract.py:8-29 (helper)

Helper function to extract MCP servers from content using OpenAI LLM in JSON object response format with custom prompt.

async def extract_mcp_servers_from_content(content: str) -> str | None:
    client = OpenAI(
        api_key=os.getenv("OPENAI_API_KEY"),
        base_url=os.getenv("OPENAI_BASE_URL"),
    )

    user_content = extract_mcp_servers_prompt.format(content=content)

    logger.info(f"Extract prompt: {user_content}")

    chat_completion = client.chat.completions.create(
        messages=[
            {
                "role": "user",
                "content": user_content,
            }
        ],
        model=os.getenv("OPENAI_MODEL"),
        response_format={"type": "json_object"},
    )

    return chat_completion.choices[0].message.content

src/mcp_server_collector/fetch.py:10-24 (helper)

Helper function to fetch raw content from URL by invoking external 'mcp-server-fetch' via MCP client.

async def call_fetch_tool(url: str):
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()

            result = await session.call_tool(
                "fetch",
                arguments={
                    "url": url,
                    "max_length": 100000,
                    "raw": True
                }
            )

            return result.content[0].text

mcp-server-collector