Skip to main content
Glama

api_discovery

Probe a domain for common API, spec, and debug paths to discover exposed endpoints and sensitive surfaces while returning only status codes, not sensitive bodies.

Instructions

Probe common API/spec/debug paths on a domain (light, non-intrusive).

Checks OpenAPI/Swagger, GraphQL, OIDC, JWKS, security.txt, robots, actuator and a few known-sensitive paths. Sensitive bodies are never returned, only status.

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": {
      "domain": "<domain>"
    },
    "name": "api_discovery"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
domainYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden, and it does disclose two meaningful traits: the probing is 'light, non-intrusive' and 'sensitive bodies are never returned, only status.' That redaction policy is exactly the kind of behavior an agent needs to know before acting. It stops short of stating rate limits, redirect handling, or what constitutes a 'hit,' which keeps it below 5.

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 short lines, front-loaded with the core action and scope, followed by the concrete checklist and the safety caveat. No filler sentences and nothing repeated from the title or schema.

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

Completeness3/5

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

There is no output schema and no annotations, so the description must convey both behavior and result shape; it partly does via the 'only status is returned' note. It leaves the 'limit' parameter unexplained and does not describe what the response looks like per checked path or how results are aggregated, which is a real gap for a two-parameter tool with zero schema documentation.

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% for both parameters. 'domain' is largely self-evident from the prose, but 'limit' (default 60) is never mentioned in the description and its unit is ambiguous - number of paths probed, number of results, or response size. With zero schema coverage, the description needed to compensate and does not.

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 ('Probe') and resource ('common API/spec/debug paths on a domain') and then enumerates the exact artifacts checked (OpenAPI/Swagger, GraphQL, OIDC, JWKS, security.txt, robots, actuator). This clearly separates it from siblings like dns_lookup or crtsh_subdomains, which query different data sources.

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 implied by the enumerated path list and the '(light, non-intrusive)' qualifier, so an agent can infer this is a surface-recon step on a single domain. However, there is no explicit when-to-use vs. when-not, no stated prerequisite (e.g., authorization to probe a domain), and no routing to an alternative tool for deeper crawling or DNS-based recon.

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