Skip to main content
Glama

BRAINIAC GraphQL Federation Security

Audit federation subgraph exposure

graphql-security_federation-subgraph-exposure-audit

Compare caller-supplied subgraph endpoints, router authentication, network rules, and service or ingress labels with the intended public subgraph list. audit_status is clean, findings_detected, incomplete, or invalid. risk_level is low, medium, high, or critical. A public label is not evidence that an endpoint is reachable. No URL is probed. Price $0.05 USDC. POST /api/v1/graphql-security/federation-subgraph-exposure-audit. Unpaid calls return 402 and do not run.

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": {
      "subgraphs": "<subgraphs>"
    },
    "name": "graphql-security_federation-subgraph-exposure-audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
routerNo
subgraphsYes
networkRulesNo
publicEndpointsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does so well: it explicitly states no URL is probed, that a public label does not prove reachability, that unpaid calls return 402 without running, and it enumerates the audit_status and risk_level outcome values. Gaps remain: it never says the operation is side-effect free/read-only in so many words, and it does not describe what findings or evidence get returned.

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?

The definition is short, front-loaded with the purpose, and every sentence carries information: enum outcomes, the label-vs-reachability caveat, the no-probing guarantee, and the price/endpoint/402 operational facts. The enum listings read as terse fragments rather than prose, but no sentence is filler.

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 a nested four-parameter tool with no output schema and 0% schema description coverage, the description compensates by documenting both result enums and the key behavioral guarantee that nothing is actively probed. It is slightly thin on the shape of individual findings and on how incomplete versus invalid is decided, but an agent can call it correctly from what is given.

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 0%, so the description must compensate, and it partially does by naming the four input categories (subgraph endpoints, router authentication, network rules, public subgraph list). It adds nothing about the remaining nested fields such as developmentMode, federationFields, acceptsDirectClients, or the 32/128 item caps, leaving an agent to rely entirely on enum names in the schema.

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 first sentence names a specific verb (compare) and the exact inputs compared: caller-supplied subgraph endpoints, router authentication, network rules, and service/ingress labels against the intended public subgraph list. The scope statement 'A public label is not evidence that an endpoint is reachable' plus 'No URL is probed' separates it from active-probing or authorization-focused siblings such as federation-authorization-audit.

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 context is implied rather than stated: the agent can infer this is for static, non-invasive exposure review because no URL is probed, but there is no explicit 'use this when / use X instead' routing to the sibling authorization or field-coverage audits. Payment and 402 behavior is documented, which helps invocation preconditions, but that is not the same as when-to-use guidance.

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