Skip to main content
Glama
Sign In
mcp-compliance

mcp-compliance

by YawLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

mcp_compliance_test

Read-onlyIdempotent

Run the MCP spec compliance suite against a server URL to receive an A–F grade, score, and detailed results covering transport, lifecycle, tools, resources, prompts, and security.

Instructions

Run the MCP compliance test suite against a server URL — the spec suite for the server's MCP revision, 2025-11-25 or 2026-07-28, auto-detected unless specVersion pins one. Returns grade (A-F), score, and detailed results covering transport, lifecycle, tools, resources, prompts, errors, schema validation, and security.

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": "mcp_compliance_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe MCP server URL to test (must be HTTP or HTTPS)
authNoAuthorization header value (e.g., "Bearer tok123")
onlyNoOnly run tests matching these categories or test IDs
skipNoSkip tests matching these categories or test IDs
headersNoAdditional headers to include on all requests (e.g., {"X-Api-Key": "abc"})
retriesNoNumber of retries for failed tests (default: 0, max: 10)
timeoutNoRequest timeout in milliseconds (default: 15000, max: 300000)
specVersionNoMCP spec revision to test against. "auto" (default) probes the server and grades it against the newest revision it speaks; pin "2025-11-25" or "2026-07-28" to force one suite.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.21.2

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new context: the return payload (grade A-F, score, detailed results) and the test categories covered, which matters because there is no output schema. It stops short of describing runtime duration, side effects on the target server, or result severity semantics.

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

Conciseness4/5

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

A single dense, front-loaded sentence: action first, then version handling, then the return contract. Every clause earns its place, though the trailing enumeration of test categories is long and could be trimmed.

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 eight-parameter tool with no output schema, the description supplies the missing return-shape information and version-selection behavior, while annotations cover safety and network exposure. What remains unstated — expected runtime, whether the target server is mutated, and how to interpret a failing grade — is minor but not negligible.

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%, so all eight parameters including auth, headers, only/skip, retries, timeout and specVersion are documented in the schema. The description only restates the specVersion auto-detect/pin behavior already present there, adding essentially no meaning beyond the schema. Baseline 3 applies.

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

Purpose4/5

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

States a specific verb and resource: "Run the MCP compliance test suite against a server URL," and scopes it to spec revisions 2025-11-25 or 2026-07-28. It does not name the sibling mcp_compliance_explain or clarify the division of labor, so an agent must infer that this tool executes rather than interprets.

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

Usage Guidelines3/5

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

Usage is only implied — you run it to grade a server's MCP compliance. There is no explicit when-to-use/when-not guidance, no mention of when to call mcp_compliance_explain instead, and no stated prerequisites. The specVersion auto-vs-pin behavior is the closest thing to decision guidance.

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

Deploy Server

Other Tools