Skip to main content
Glama

Audit an MCP server

test_mcp_server

Start an audit of a remote MCP server (Streamable HTTP) from the outside. It checks initialize, version negotiation, sessions, tools/list schemas and their token cost, ping, error codes, resources, prompts, CORS, Origin handling and latency, then scores the server out of 100 with fixes. Returns an id; read the report with get_mcp_test after about 30 seconds. Only audit servers you run or are allowed to test.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "test_mcp_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesMCP endpoint URL, e.g. https://example.com/mcp.
probe_toolNoOptional real tool call: {name, arguments}.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / probe_tool / description
      Previous value: -"Optional real call: {name, arguments}"New value: +"Optional real tool call: {name, arguments}."
    • addedInput schema / properties / probe_tool / properties / arguments / description
      Added value: +"Arguments for that tool."
    • addedInput schema / properties / probe_tool / properties / name / description
      Added value: +"Tool name on the audited server."
    • changedInput schema / properties / url / description
      Previous value: -"MCP endpoint URL, e.g. https://example.com/mcp"New value: +"MCP endpoint URL, e.g. https://example.com/mcp."
  2. Changed1 schema field changed
    • addedInput schema / properties / probe_tool
      Added value: +{
      +  "description": "Optional real call: {name, arguments}",
      +  "properties": {
      +    "arguments": {
      +      "type": "object"
      +    },
      +    "name": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "name"
      +  ],
      +  "type": "object"
      +}
  3. Added

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover network scope and non-idempotency, but the description adds material context they cannot: the audit is asynchronous and returns an id rather than a result, the report is available after roughly 30 seconds, the output is a 0-100 score with fixes, and the endpoint must be one the caller is authorized to test. This is exactly the extra information an agent needs to sequence calls correctly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences: what it does, what it returns plus the follow-up tool and delay, then the authorization caveat. Front-loaded with the action and zero repetitive wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an asynchronous launcher with no output schema, the description sufficiently explains that the return value is an id and where the actual report lives. Remaining gaps are minor: nothing about failure modes (unreachable endpoint, invalid URL) or whether concurrent audits are allowed, and probe_tool is never mentioned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including the nested probe_tool object with its name and arguments fields, so the schema carries parameter meaning itself. The description adds no further information about URL format or the optional real tool-call probe, which is the most behavior-affecting parameter. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'Start an audit of a remote MCP server (Streamable HTTP) from the outside' — and then enumerates exactly what the audit covers (initialize, sessions, tools/list token cost, CORS, latency, scoring out of 100). An agent can distinguish this launcher from get_mcp_test, the report reader, without inspecting either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent to the sibling consumer: 'read the report with get_mcp_test after about 30 seconds', plus a scope-of-use constraint ('Only audit servers you run or are allowed to test'). It does not state when this tool should be preferred over unrelated siblings, but for this workflow the alternative and timing are unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.