Skip to main content
Glama

Check an MCP server Clerk OAuth setup

check_mcp_server

Read an instance's registered MCP servers, the OAuth settings MCP clients depend on, and the latest public discovery check for one registered MCP server URL. Never changes Clerk OAuth settings. Pass force_recheck: true to start a new checker observation instead of reading the cached one: the checker sends unauthenticated GET requests to the MCP endpoint and reads public protected-resource metadata and Clerk issuer discovery documents. It never forwards Clerk credentials to the resource URL and is not end-to-end OAuth verification.

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": {
      "application_id": "<application_id>",
      "instance": "<instance>"
    },
    "name": "check_mcp_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
check_idNoA specific check to read instead of the latest one. Cannot be combined with force_recheck.
instanceYesInstance to target: "development", "production", or a full instance ID (ins_…).
resource_urlNoRegistered MCP server URL to check. Optional when exactly one is registered.
force_recheckNoStart a new public discovery check instead of reading the cached one. Defaults to false.
application_idYesClerk application ID (app_…).

Output Schema

NameRequiredDescriptionDefault
noteYes
checkYes
mcp_serverNo
next_stepsYes
instance_idYes
resource_urlNo
setup_promptNo
configurationYes
application_idYes
end_to_end_verifiedYes
authorization_serverNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • removedOutput schema / properties / authorization_server / properties / issuer / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / authorization_server / properties / issuer / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / check / properties / freshness / properties / age_seconds / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / check / properties / freshness / properties / age_seconds / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / check / properties / freshness / properties / checked_at / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / check / properties / freshness / properties / checked_at / type
      Added value: +[
      +  "string",
      +  "null"
      +]
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false and openWorldHint=true, and the description goes well beyond them: it discloses that the checker sends unauthenticated GET requests to the MCP endpoint, reads public protected-resource metadata and issuer discovery documents, never forwards Clerk credentials to the resource URL, and creates a new observation when force_recheck is set. That explains the non-read-only, open-world profile rather than contradicting it.

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?

Purpose is front-loaded in the first sentence and every subsequent sentence carries distinct information (mutation disclaimer, mode switch, checker behavior, credential safety, scope limit). The force_recheck sentence is long and clause-heavy, but no sentence is filler.

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

Completeness5/5

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

An output schema exists, so return values need not be described, and the description instead covers the parts that matter for an open-world, non-read-only tool: what the checker contacts, what it does not do with credentials, and the limits of verification. Nothing essential for correct invocation appears missing given five parameters, 100% schema coverage, and supplied annotations.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema for force_recheck by explaining the outbound request behavior and the cached-versus-new tradeoff. It does not elaborate on check_id or resource_url beyond what the schema already states.

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?

The description opens with a specific verb-plus-resource statement: reads an instance's registered MCP servers, the OAuth settings MCP clients depend on, and the latest public discovery check for one registered MCP server URL. It also implicitly separates itself from the mutating sibling configure_mcp_server by stating 'Never changes Clerk OAuth settings.'

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?

It clearly explains the two operating modes: read the cached check by default, or pass force_recheck: true to run a new observation, and it scopes out what the tool is not ('not end-to-end OAuth verification'). It gives no explicit guidance about when to choose this versus configure_mcp_server or check_domain_dns, so alternatives are left implicit.

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.

Resources