mcp_server_evaluate
Check that a live MCP server over Streamable HTTP speaks the protocol, 2026-07-28 or earlier: handshake or server/discover, tools/list and its definitions, error codes, one tools/call, structuredContent against outputSchema, latency. Returns PASS/FIX/BLOCK with a 0-100 score, or INCONCLUSIVE (score null) when authorization is required. The verdict covers the PROTOCOL, never whether tools answer correctly: what_this_does_not_prove lists what was not measured. Called: only test_tool_name, or a tool annotated readOnlyHint: true. A refusal of invented arguments is not scored (tool_behaviour: refused_placeholder); pass test_tool_args to exercise the tool. Private addresses and stdio are out of reach: paste tools/list into mcp_server_health_check.
Example tool call
This call uses example arguments supplied in the tool’s input schema.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "https://www.ia-qa.com/mcp"
},
"name": "mcp_server_evaluate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public URL of the MCP endpoint (e.g. https://mcp.example.com/mcp). An origin alone (https://www.ia-qa.com) tries /mcp, then /. | |
| test_tool_args | No | Real arguments, sent to the tested server. Without them, required ones are invented. | |
| test_tool_name | No | Tool to call. Default: a read-only one, preferring no required arg. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | ||
| score | No | ||
| checks | No | ||
| server | No | ||
| latency | No | ||
| verdict | No | ||
| endpoint | No | ||
| next_steps | No | ||
| tool_behaviour | No | ||
| what_this_proves | No | ||
| what_this_does_not_prove | No |