{"$schema":"https://static.modelcontextprotocol.io/schemas/mcp-server-card/v1.json","version":"1.0","protocolVersion":"2025-11-25","serverInfo":{"name":"mcp-scoring","title":"MCP Scoring","version":"1.2.0","description":"Score and test any remote MCP server and search the ranked MCP server directory.","websiteUrl":"https://mcpscoring.com","icons":[{"src":"https://mcpscoring.com/logo.svg","mimeType":"image/svg+xml","sizes":["any"]}]},"transport":{"type":"streamable-http","endpoint":"https://mcpscoring.com/mcp"},"remotes":[{"type":"streamable-http","url":"https://mcpscoring.com/mcp"}],"capabilities":{"tools":{"listChanged":false},"resources":{"listChanged":false},"prompts":{"listChanged":false}},"authentication":{"required":false},"instructions":"MCP Scoring tests remote MCP servers and keeps a public, ranked directory of them.\n\nTypical flows:\n1. To audit a server, call score_mcp_server with its public URL. It connects live, runs every check (about 5 to 30 seconds) and returns the score, grade, per section scores and the top issues.\n2. To find servers, call search_mcp_directory with a keyword. Each result includes a server_id.\n3. For the full breakdown of one server, call get_mcp_server_report with that server_id.\n4. To fix a server, call get_mcp_fix_prompt and hand the returned prompt to a coding agent working in that server's repository.\n5. To explain how scores are calculated, call list_scoring_checks or read the mcpscoring://methodology resource.\n\nScores are 0 to 100 and graded A to F. Only servers that complete an MCP handshake and expose tools appear in the directory.","tools":["score_mcp_server","search_mcp_directory","get_mcp_server_report","get_mcp_fix_prompt","list_scoring_checks"],"resources":["mcpscoring://methodology","mcpscoring://leaderboard"],"prompts":["audit_mcp_server"]}