Paid GraphQL Federation Security API via x402. Unpaid tool calls return 402.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Compare @authenticated, @requiresScopes, @policy, and caller-defined authorization directives across supplied subgraph SDL. @requires, @key, @external, @provides, and @shareable are inspected for schema-level differences. audit_status is clean, findings_detected, invalid, or incomplete. risk_level is low, medium, high, or critical. A difference is not a runtime authorization result. No gateway is contacted. Price $0.05 USDC. POST /api/v1/graphql-security/federation-authorization-audit. An unpaid call returns the x402 payment terms and does not run.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http graphql-security https://www.brainiac.software/mcp/graphql-security
Compare @authenticated, @requiresScopes, @policy, and caller-defined authorization directives across supplied subgraph SDL. @requires, @key, @external, @provides, and @shareable are inspected for schema-level differences. audit_status is clean, findings_detected, invalid, or incomplete. risk_level is low, medium, high, or critical. A difference is not a runtime authorization result. No gateway is contacted. Price $0.05 USDC. POST /api/v1/graphql-security/federation-authorization-audit. An unpaid call returns the x402 payment terms and does not run.
| Argument | Type | Description |
|---|---|---|
| expected | array | |
| subgraphs* | array | |
| supergraph | string | |
| authorizationDirectives | array |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"subgraphs"
],
"properties": {
"expected": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"type": "string",
"pattern": "^[_A-Za-z][_0-9A-Za-z]{0,79}$"
},
"field": {
"type": "string",
"pattern": "^[_A-Za-z][_0-9A-Za-z]{0,79}$"
},
"scopes": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 16,
"minItems": 1
},
"maxItems": 8,
"minItems": 1
},
"policies": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 16,
"minItems": 1
},
"maxItems": 8,
"minItems": 1
},
"subgraph": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,79}$"
},
"authenticated": {
"type": "boolean"
}
},
"additionalProperties": false
},
"maxItems": 32
},
"subgraphs": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"sdl"
],
"properties": {
"sdl": {
"type": "string",
"maxLength": 60000,
"minLength": 1
},
"name": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,79}$"
},
"federationVersion": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,39}$"
}
},
"additionalProperties": false
},
"maxItems": 8,
"minItems": 1
},
"supergraph": {
"type": "string",
"maxLength": 80000,
"minLength": 1
},
"authorizationDirectives": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"semantics"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[_A-Za-z][_0-9A-Za-z]{0,79}$"
},
"argument": {
"type": "string",
"pattern": "^[_A-Za-z][_0-9A-Za-z]{0,79}$"
},
"semantics": {
"enum": [
"authenticated",
"scopes",
"policy"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 32
}
},
"additionalProperties": false
}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 $0.05 USDC. POST /api/v1/graphql-security/federation-subgraph-exposure-audit. An unpaid call returns the x402 payment terms and does not run.
| Argument | Type | Description |
|---|---|---|
| router | object | |
| subgraphs* | array | |
| networkRules | array | |
| publicEndpoints | array |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"subgraphs"
],
"properties": {
"router": {
"type": "object",
"properties": {
"sandbox": {
"type": "boolean"
},
"introspection": {
"type": "boolean"
},
"authenticationToSubgraphs": {
"enum": [
"required",
"disabled",
"per_subgraph",
"unknown"
],
"type": "string"
}
},
"additionalProperties": false
},
"subgraphs": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,79}$"
},
"ingress": {
"type": "object",
"required": [
"audience"
],
"properties": {
"audience": {
"enum": [
"public",
"internal",
"unknown"
],
"type": "string"
}
},
"additionalProperties": false
},
"service": {
"type": "object",
"required": [
"exposure"
],
"properties": {
"exposure": {
"enum": [
"cluster_local",
"internal",
"public",
"unknown"
],
"type": "string"
}
},
"additionalProperties": false
},
"endpoint": {
"type": "string",
"maxLength": 500,
"minLength": 1
},
"introspection": {
"type": "boolean"
},
"authentication": {
"enum": [
"required",
"disabled",
"unknown"
],
"type": "string"
},
"developmentMode": {
"type": "boolean"
},
"federationFields": {
"type": "object",
"properties": {
"service": {
"enum": [
"router_only",
"exposed",
"unknown"
],
"type": "string"
},
"entities": {
"enum": [
"router_only",
"exposed",
"unknown"
],
"type": "string"
}
},
"additionalProperties": false
},
"acceptsDirectClients": {
"type": "boolean"
}
},
"additionalProperties": false
},
"maxItems": 32,
"minItems": 1
},
"networkRules": {
"type": "array",
"items": {
"type": "object",
"required": [
"subgraph",
"source",
"action"
],
"properties": {
"action": {
"enum": [
"allow",
"deny"
],
"type": "string"
},
"source": {
"enum": [
"router",
"public",
"cluster",
"any"
],
"type": "string"
},
"subgraph": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,79}$"
}
},
"additionalProperties": false
},
"maxItems": 128
},
"publicEndpoints": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,79}$"
},
"maxItems": 32
}
},
"additionalProperties": false
}Count object and interface fields in the supplied subgraph SDL and mark a field when its line, or its type line, contains one of the supplied directive names. Coverage is the share of marked fields. This is a text count. It does not compose a supergraph or decide whether a request would be allowed. Price $0.04 USDC. POST /api/v1/graphql-security/field-authorization-coverage. An unpaid call returns the x402 payment terms and does not run.
| Argument | Type | Description |
|---|---|---|
| subgraphs* | array | |
| protected_directives* | array |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"protected_directives",
"subgraphs"
],
"properties": {
"subgraphs": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"sdl"
],
"properties": {
"sdl": {
"type": "string",
"maxLength": 50000,
"minLength": 1
},
"name": {
"type": "string",
"maxLength": 80,
"minLength": 1
}
}
},
"maxItems": 10,
"minItems": 1
},
"protected_directives": {
"type": "array",
"items": {
"type": "string",
"pattern": "^@[A-Za-z][A-Za-z0-9]*$"
},
"maxItems": 10,
"minItems": 1
}
}
}Walk object-type references in the supplied SDL, starting at Query when that type is present. Scalars are ignored and a repeated type is not walked again. The index is that depth. The risk score rises when the depth passes the supplied limit, and when introspection is enabled. No router is contacted. Price $0.04 USDC. POST /api/v1/graphql-security/subgraph-complexity. An unpaid call returns the x402 payment terms and does not run.
| Argument | Type | Description |
|---|---|---|
| sdl* | string | |
| max_depth* | integer | |
| introspection* | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"sdl",
"max_depth",
"introspection"
],
"properties": {
"sdl": {
"type": "string",
"maxLength": 50000,
"minLength": 1
},
"max_depth": {
"type": "integer",
"maximum": 20,
"minimum": 1
},
"introspection": {
"enum": [
"enabled",
"disabled"
],
"type": "string"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 19, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.