EvalGate
Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"evalgate": {
"url": "https://www.evalgate.com/api/mcp"
}
}
}Remote endpoints
https://www.evalgate.com/api/mcpstreamable-httpWhat it can do
Tool inventory
Tools (12)
🟢project_inspect(projectKey)
Snapshot the evaluations and project keys in the authenticated organization. Use it first to orient in an unfamiliar workspace or to resolve a projectKey. Returns evaluation summaries, a bounded count and a web link; changes nothing.
Input Schema
{
"type": "object",
"properties": {
"projectKey": {
"description": "Exact project key to filter the first 50 organization evaluations; omit to inspect that entire snapshot.",
"type": "string",
"minLength": 1
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"projectKey": {
"type": [
"string",
"null"
]
},
"organizationId": {
"type": "string"
},
"evaluationCount": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991,
"description": "Count in this bounded snapshot, not a total across the organization."
},
"evaluations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"name": {
"type": "string"
},
"projectKey": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string"
},
"type": {
"type": "string"
},
"updatedAt": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
}
},
"required": [
"id",
"name",
"projectKey",
"status"
],
"additionalProperties": false
}
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
},
"deepLink": {
"type": "string",
"description": "EvalGate web path or absolute URL for inspecting these results."
}
},
"required": [
"projectKey",
"organizationId",
"evaluationCount",
"evaluations",
"explanation",
"deepLink"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢project_plan(target)
Plan the next steps for connecting a repository, reviewing an evaluation, or ingesting traces. Use it when deciding what to set up next. Returns an ordered advisory step list and a web link; it never runs, writes or accepts anything.
Input Schema
{
"type": "object",
"properties": {
"target": {
"default": "repository",
"description": "Workflow to plan: local repository setup, hosted evaluation review, or trace ingestion. Defaults to repository; never executes the plan.",
"type": "string",
"enum": [
"repository",
"evaluation",
"traces"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"target": {
"type": "string",
"enum": [
"repository",
"evaluation",
"traces"
]
},
"mutates": {
"type": "boolean",
"const": false
},
"steps": {
"type": "array",
"items": {
"type": "string"
}
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
},
"deepLink": {
"type": "string",
"description": "EvalGate web path or absolute URL for inspecting these results."
}
},
"required": [
"target",
"mutates",
"steps",
"explanation",
"deepLink"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢evaluations_list(limit, cursor, status)
List the organization's evaluations, optionally filtered by lifecycle status. Use it to find an evaluationId before calling runs_list or baseline_lineage. Returns one page of evaluation summaries and a nextCursor for the following page.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"description": "Maximum results in this page, from 1 to 50; defaults to 20.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"cursor": {
"description": "Opaque nextCursor from the preceding page of this tool. Omit for the first page.",
"type": "string"
},
"status": {
"description": "Restrict evaluations to this lifecycle status; omit to include all statuses.",
"type": "string",
"enum": [
"draft",
"active",
"archived"
]
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"evaluations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"name": {
"type": "string"
},
"projectKey": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string"
},
"type": {
"type": "string"
},
"updatedAt": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
}
},
"required": [
"id",
"name",
"projectKey",
"status"
],
"additionalProperties": false
}
},
"nextCursor": {
"description": "Opaque continuation cursor; null means no further page.",
"type": [
"string",
"null"
]
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
},
"deepLink": {
"type": "string",
"description": "EvalGate web path or absolute URL for inspecting these results."
}
},
"required": [
"evaluations",
"nextCursor",
"explanation",
"deepLink"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"error": {
"type": "string",
"const": "invalid_cursor"
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
}
},
"required": [
"error",
"explanation"
],
"additionalProperties": false
}
]
}🟢runs_list(evaluationId, limit, cursor, status)
List the runs of one evaluation, newest first, optionally filtered by status. Use it to find a runId or check recent results and regression signals. Returns one page of run summaries and a nextCursor for the following page.
Input Schema
{
"type": "object",
"properties": {
"evaluationId": {
"description": "Evaluation ID returned by evaluations_list in the authenticated organization. Accepts a positive safe integer or its canonical decimal string (e.g. 8 or \"8\").",
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
{
"type": "string",
"pattern": "^[1-9]\\d*$"
}
]
},
"limit": {
"description": "Maximum results in this page, from 1 to 50; defaults to 20.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"cursor": {
"description": "Opaque nextCursor from the preceding page of this tool. Omit for the first page.",
"type": "string"
},
"status": {
"description": "Exact persisted run status to filter by; omit to include all statuses, including incomplete runs.",
"type": "string"
}
},
"required": [
"evaluationId"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"evaluationId": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"runs": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"evaluationId": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"status": {
"type": "string"
},
"totalCases": {
"anyOf": [
{
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"passedCases": {
"anyOf": [
{
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"failedCases": {
"anyOf": [
{
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"baselineVersion": {
"type": [
"string",
"null"
]
},
"environment": {
"type": [
"string",
"null"
]
},
"createdAt": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
},
"startedAt": {
"anyOf": [
{
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
},
{
"type": "null"
}
]
},
"completedAt": {
"anyOf": [
{
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
},
{
"type": "null"
}
]
}
},
"required": [
"id",
"evaluationId",
"status",
"totalCases",
"passedCases",
"failedCases",
"baselineVersion",
"environment",
"createdAt",
"startedAt",
"completedAt"
],
"additionalProperties": false
}
},
"nextCursor": {
"description": "Opaque continuation cursor; null means no further page.",
"type": [
"string",
"null"
]
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
},
"deepLink": {
"type": "string",
"description": "EvalGate web path or absolute URL for inspecting these results."
}
},
"required": [
"evaluationId",
"runs",
"nextCursor",
"explanation",
"deepLink"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"error": {
"type": "string",
"const": "invalid_cursor"
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
}
},
"required": [
"error",
"explanation"
],
"additionalProperties": false
}
]
}🟢run_explain(runId)
Explain why one run passed or failed. Use it after runs_list when you need the failing cases and where the evidence came from. Returns the run's status, its failed cases with result metadata, an evidence-lineage summary, or not_found.
Input Schema
{
"type": "object",
"properties": {
"runId": {
"description": "Run ID returned by runs_list; must belong to the authenticated organization. Accepts a positive safe integer or its canonical decimal string (e.g. 3 or \"3\").",
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
{
"type": "string",
"pattern": "^[1-9]\\d*$"
}
]
}
},
"required": [
"runId"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"run": {
"type": "object",
"properties": {
"id": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"evaluationId": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"status": {
"type": "string"
},
"totalCases": {
"anyOf": [
{
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"passedCases": {
"anyOf": [
{
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"failedCases": {
"anyOf": [
{
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"baselineVersion": {
"type": [
"string",
"null"
]
},
"environment": {
"type": [
"string",
"null"
]
},
"createdAt": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
},
"startedAt": {
"anyOf": [
{
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
},
{
"type": "null"
}
]
},
"completedAt": {
"anyOf": [
{
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
},
{
"type": "null"
}
]
}
},
"required": [
"id",
"evaluationId",
"status",
"totalCases",
"passedCases",
"failedCases",
"baselineVersion",
"environment",
"createdAt",
"startedAt",
"completedAt"
],
"additionalProperties": false
},
"failedCases": {
"type": "array",
"items": {
"type": "object",
"properties": {
"result": {
"type": "string"
},
"testCase": {
"type": "string"
},
"metadata": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "Available result metadata; keys vary by evaluator and evidence type."
}
},
"required": [
"result",
"testCase",
"metadata"
],
"additionalProperties": false
}
},
"lineage": {
"anyOf": [
{
"type": "object",
"properties": {
"nodeCount": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"edgeCount": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"nodeCount",
"edgeCount"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
},
"deepLink": {
"type": "string",
"description": "EvalGate web path or absolute URL for inspecting these results."
}
},
"required": [
"run",
"failedCases",
"lineage",
"explanation",
"deepLink"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"error": {
"type": "string",
"const": "not_found"
},
"runId": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
}
},
"required": [
"error",
"runId",
"explanation"
],
"additionalProperties": false
}
]
}🟢baseline_lineage(evaluationId)
Show which run is the published baseline for an evaluation and where its evidence came from. Use it before comparing a new run against the baseline. Returns the baseline run and version, a lineage summary, or not_found.
Input Schema
{
"type": "object",
"properties": {
"evaluationId": {
"description": "Evaluation ID returned by evaluations_list in the authenticated organization. Accepts a positive safe integer or its canonical decimal string (e.g. 8 or \"8\").",
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
{
"type": "string",
"pattern": "^[1-9]\\d*$"
}
]
}
},
"required": [
"evaluationId"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"evaluation": {
"type": "object",
"properties": {
"id": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"name": {
"type": "string"
},
"projectKey": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string"
},
"updatedAt": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
}
},
"required": [
"id",
"name",
"projectKey",
"status",
"updatedAt"
],
"additionalProperties": false
},
"baseline": {
"type": "object",
"properties": {
"publishedRunId": {
"anyOf": [
{
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"publishedVersion": {
"anyOf": [
{
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"lineageAvailable": {
"type": "boolean"
}
},
"required": [
"publishedRunId",
"publishedVersion",
"lineageAvailable"
],
"additionalProperties": false
},
"lineage": {
"anyOf": [
{
"type": "object",
"properties": {
"nodeCount": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"edgeCount": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"nodeCount",
"edgeCount"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
},
"deepLink": {
"type": "string",
"description": "EvalGate web path or absolute URL for inspecting these results."
}
},
"required": [
"evaluation",
"baseline",
"lineage",
"explanation",
"deepLink"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"error": {
"type": "string",
"const": "not_found"
},
"evaluationId": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
}
},
"required": [
"error",
"evaluationId",
"explanation"
],
"additionalProperties": false
}
]
}🟢docs_search(query, limit)
Search EvalGate's public REST API operations by keyword. Use it to find the right endpoint before writing an API call. Returns matching operations with method, path, summary and operationId; for product guides use the documentation MCP instead.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "Search terms for the public OpenAPI operation catalog (1–200 characters); all whitespace-separated terms must match."
},
"limit": {
"description": "Maximum matching operations, from 1 to 20; defaults to 10.",
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"path": {
"type": "string"
},
"method": {
"type": "string",
"enum": [
"GET",
"POST",
"PUT",
"PATCH",
"DELETE",
"HEAD",
"OPTIONS"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"operationId": {
"type": [
"string",
"null"
]
}
},
"required": [
"path",
"method",
"summary",
"operationId"
],
"additionalProperties": false
}
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
},
"deepLink": {
"type": "string",
"description": "EvalGate web path or absolute URL for inspecting these results."
}
},
"required": [
"query",
"results",
"explanation",
"deepLink"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢connector_health(connectorKey)
Show the latest persisted connector-readiness reports, optionally for one connector. Use it to check whether an integration was set up and scored. Returns each report's status, score and timestamp; it is not a live credential or provider check.
Input Schema
{
"type": "object",
"properties": {
"connectorKey": {
"description": "Exact report key or metadata connector key to filter the latest 50 persisted reports; omit for all reports in that snapshot. Requires admin:org.",
"type": "string",
"minLength": 1
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"connectorKey": {
"type": [
"string",
"null"
]
},
"configured": {
"type": "boolean",
"description": "Whether this query found persisted readiness reports; not a live credential or provider-health check."
},
"reports": {
"type": "array",
"items": {
"type": "object",
"properties": {
"reportKey": {
"type": "string"
},
"status": {
"type": "string"
},
"score": {
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"manifestHash": {
"type": [
"string",
"null"
]
},
"createdAt": {
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
}
},
"required": [
"reportKey",
"status",
"score",
"manifestHash",
"createdAt"
],
"additionalProperties": false
}
},
"explanation": {
"type": "string",
"description": "Human-readable interpretation and evidence limitations."
},
"deepLink": {
"type": "string",
"description": "EvalGate web path or absolute URL for inspecting these results."
}
},
"required": [
"connectorKey",
"configured",
"reports",
"explanation",
"deepLink"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢connections_list(q, source, limit, cursor)
List the workspace's current connections with their source restrictions and freshness. Use it to see what is already connected before planning a new one. Returns connection metadata and a continuation cursor; never secrets, and it grants no source access.
Input Schema
{
"type": "object",
"properties": {
"q": {
"description": "Case-insensitive connection name or service search; up to 200 characters.",
"type": "string",
"maxLength": 200
},
"source": {
"description": "Filter by canonical store; direct metadata still requires admin role and scope.",
"type": "string",
"enum": [
"gateway",
"provider-key"
]
},
"limit": {
"description": "Maximum connections in one page; defaults to 25, capped at 100.",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"cursor": {
"description": "Opaque nextCursor from this caller and inventory revision; refresh if the inventory changes.",
"type": "string",
"maxLength": 512
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"sources": {
"type": "object",
"properties": {
"gateway": {
"type": "string"
},
"direct": {
"type": "string"
}
},
"required": [
"gateway",
"direct"
],
"additionalProperties": false
},
"complete": {
"type": "boolean"
},
"hasMore": {
"type": "boolean"
},
"nextCursor": {
"type": [
"string",
"null"
]
},
"observedAt": {
"type": "string"
}
},
"required": [
"items",
"sources",
"complete",
"hasMore",
"nextCursor",
"observedAt"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢connections_catalog
Inspect every connector definition and its exact installed setup path. Use it to choose a connector or find how to install one. Returns connector definitions with setup paths; blueprints that are unavailable and live verification are reported as separate facts.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"registryVersion": {
"type": "string",
"const": "connections-v1"
},
"liveVerified": {
"type": "boolean",
"const": false
},
"connectors": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
}
},
"required": [
"registryVersion",
"liveVerified",
"connectors"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢connections_roots(q, limit, cursor)
Page through the configured account roots (top-level connected accounts) using current administrator authority. Use it to audit which accounts are configured. Returns root metadata and a continuation cursor; never secrets, and no claim that a connector works.
Input Schema
{
"type": "object",
"properties": {
"q": {
"description": "Literal case-insensitive root name/driver search; wildcard characters have no special meaning.",
"type": "string",
"maxLength": 200
},
"limit": {
"description": "Bounded page size; defaults to 25 and is capped at 100.",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"cursor": {
"description": "Opaque nextCursor for the same caller, workspace, search, limit and observed metadata revision; refresh after changes.",
"type": "string",
"maxLength": 1024
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"name": {
"type": "string"
},
"driverId": {
"type": "string"
},
"revision": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"authorityEpoch": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"selectionEpoch": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"configurationVersion": {
"type": "number",
"const": 1
},
"status": {
"type": "string",
"const": "configuration_only"
},
"lifecycleState": {
"type": "string",
"enum": [
"configured",
"paused",
"revoked"
]
}
},
"required": [
"id",
"name",
"driverId",
"revision",
"authorityEpoch",
"selectionEpoch",
"configurationVersion",
"status",
"lifecycleState"
],
"additionalProperties": false
}
},
"hasMore": {
"type": "boolean"
},
"nextCursor": {
"type": [
"string",
"null"
]
},
"dispatchEnabled": {
"type": "boolean",
"const": false
}
},
"required": [
"items",
"hasMore",
"nextCursor",
"dispatchEnabled"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢connections_graph(id)
Read how connections link to resources: canonical connection references and the exact resource revisions currently visible. Use it to trace which source revision a connection points at. Returns references and revisions; it grants no source access and runs nothing.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "Stable graph UUID returned by connections.backfill, not a credential ID."
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"source": {
"anyOf": [
{
"type": "object",
"properties": {
"source": {
"type": "string",
"enum": [
"gateway",
"provider-key"
]
},
"sourceId": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"source",
"sourceId"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"configuration": {
"anyOf": [
{
"type": "object",
"properties": {
"schemaVersion": {
"type": "number",
"const": 1
},
"accountScope": {
"type": "string"
},
"placement": {
"oneOf": [
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"const": "public"
}
},
"required": [
"kind"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"const": "private"
},
"runnerId": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"environment": {
"type": "string",
"enum": [
"dev",
"staging",
"prod"
]
}
},
"required": [
"kind",
"runnerId",
"environment"
],
"additionalProperties": false
}
]
},
"fields": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"schemaVersion",
"accountScope",
"placement",
"fields"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"driverId": {
"type": "string"
},
"name": {
"type": "string"
},
"lifecycleState": {
"type": "string",
"enum": [
"configured",
"paused",
"revoked"
]
},
"revokedAt": {
"anyOf": [
{
"type": "string",
"format": "date-time",
"pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
},
{
"type": "null"
}
]
},
"revision": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"authorityEpoch": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"selectionEpoch": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"endpoints": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
},
"purpose": {
"type": "string",
"enum": [
"management",
"runtime",
"retrieval"
]
},
"bindingKey": {
"type": "string"
},
"nativeScope": {
"type": [
"string",
"null"
]
},
"egressStatus": {
"type": "string",
"enum": [
"canonical_owner",
"unbound"
]
},
"credential": {
"type": "object",
"properties": {
"store": {
"type": "string",
"enum": [
"gateway_config",
"provider_key"
]
},
"id": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"version": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"store",
"id",
"version"
],
"additionalProperties": false
},
"current": {
"type": "boolean"
}
},
"required": [
"id",
"purpose",
"bindingKey",
"nativeScope",
"egressStatus",
"credential",
"current"
],
"additionalProperties": false
}
},
"selectedResourceRevisionIds": {
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
}
},
"selectionVisibility": {
"type": "string",
"enum": [
"complete",
"restricted"
]
},
"dispatchEnabled": {
"type": "boolean",
"const": false
}
},
"required": [
"id",
"source",
"configuration",
"driverId",
"name",
"lifecycleState",
"revokedAt",
"revision",
"authorityEpoch",
"selectionEpoch",
"endpoints",
"selectedResourceRevisionIds",
"selectionVisibility",
"dispatchEnabled"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Community
Evidence