MCP deployability diagnostic > developer readiness scorecard > signed server self-attestation (composite A-F grade).
run_mcp_deployability_diagnostic{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "run_mcp_deployability_diagnostic",
"arguments": {}
},
"id": 1
}
attest_mcp_server{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "attest_mcp_server",
"arguments": {}
},
"id": 1
}
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this whole workflow on the server and check one field that answers a real question.
Question: We are about to publish a server. What grade does its self-attestation pack earn today?
Run the AINumbers MCP tool `run_chain` with {"chain":"mcp-server-attestation"} and read `art-33-mcp-server-self-attestation-pack.composite_grade`.
Re-run with `inputs` for `art-33-mcp-server-self-attestation-pack`, reusing the values that result echoed, with `tool_definition` changed so the inputSchema is dropped from the tool definition. Compare the same field.
Verify: call `verify_execution_hash` (https://mcp.ainumbers.co/mcp) with `claimed_hash` set to `composite_execution_hash` and the full `composite_artifact`.
Ledger, for a human re-check: https://ledger.ainumbers.co/
PII rule: send synthetic or anonymised inputs only. The MCP server runs these kernels and logs no payloads.
Chain page: https://ainumbers.co/chaingraph/chains/mcp-server-attestation.html