Skip to main content
Glama
mcp-protocol-conformance

mcp-protocol-conformance

runOauthPkceFlow

Read-onlyIdempotent

Tests OAuth 2.1 PKCE S256 authorization against a target MCP server, using a mock authorization server by default or a real tenant when real OAuth mode is enabled.

Instructions

Exercise OAuth 2.1 PKCE S256 flow against the target. Mock-AS by default; real-tenant when --oauth-mode=real.

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": {
      "target": "<target>",
      "clientId": "<clientId>",
      "redirectUri": "<redirectUri>"
    },
    "name": "runOauthPkceFlow"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopesNo
targetYes
clientIdYes
redirectUriYes
specVersionNo2025-06-18
authorizationServerUrlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / target / additionalProperties
      Removed value: -false
    • addedInput schema / properties / target / properties / headers / propertyNames
      Added value: +{
      +  "type": "string"
      +}
  2. First observedv0.2.1

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is largely covered. The description adds the genuinely useful behavioral fact that the default runs against a mock authorization server rather than a live one. It does not explain what the tool returns (tokens? assertions? pass/fail?), how long a real-tenant run takes, or that "real-tenant" mode implies external network traffic that sits awkwardly with openWorldHint=false.

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?

Two compact sentences, front-loaded with the operation and followed by the default-mode caveat; nothing is padded. The only cost is that the second sentence's flag syntax is unactionable rather than merely terse.

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

Completeness2/5

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

With no output schema, no parameter descriptions, and a real-tenant mode mentioned but not addressable through any argument, an agent cannot reliably invoke this tool or predict its effects. For a 6-parameter, nested-object tool whose mode selection is central to safety, the description leaves too much unspecified.

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

Parameters2/5

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

Schema description coverage is 0% across 6 parameters, including a nested target object and a specVersion enum, so the description carries the full explanatory burden and supplies almost none of it: no meaning for target, clientId, redirectUri, scopes, or authorizationServerUrl. Worse, it introduces "--oauth-mode=real", a value that has no corresponding parameter, which can send an agent looking for a knob that isn't there.

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?

"Exercise OAuth 2.1 PKCE S256 flow against the target" gives a specific verb (exercise/run a flow), a specific protocol and code-challenge method (OAuth 2.1 PKCE S256), and a specific target. That distinguishes it well from siblings like runTransportSuite or runJsonRpcCompliance, though it never explicitly contrasts itself with them.

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

Usage Guidelines2/5

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

It states a default ("Mock-AS by default") and an alternative ("real-tenant when --oauth-mode=real"), which is usage-shaped guidance. But the switch is expressed as a CLI flag that does not exist anywhere in the input schema, so an agent has no actionable way to select the mode, and there is no guidance on when this suite should be run instead of the other run* suites.

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