Create and run AI evaluations, record traces, and inspect results with scoped organization access.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Authenticate with an EvalGate organization API key.
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.
Show the published baseline anchor and its evidence lineage.
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").
Show the published baseline anchor and its evidence lineage.
| Argument | Type | Description |
|---|---|---|
| evaluationId* | any | 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"). |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"evaluationId"
],
"properties": {
"evaluationId": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"pattern": "^[1-9]\\d*$"
}
],
"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\")."
}
}
}Inspect all connector definitions and exact installed setup paths. Unavailable blueprints and live verification are separate facts.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}Read canonical connection references and currently visible exact resource revisions. No source access grant or execution.
| Argument | Type | Description |
|---|---|---|
| id* | string | Stable graph UUID returned by connections.backfill, not a credential ID. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id"
],
"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)$",
"description": "Stable graph UUID returned by connections.backfill, not a credential ID."
}
}
}List current workspace connection metadata, with source restrictions, freshness and bounded continuation. Does not reveal secrets or grant source access.
| Argument | Type | Description |
|---|---|---|
| q | string | Case-insensitive connection name or service search; up to 200 characters. |
| limit | integer | Maximum connections in one page; defaults to 25, capped at 100. |
| cursor | string | Opaque nextCursor from this caller and inventory revision; refresh if the inventory changes. |
| source | string | Filter by canonical store; direct metadata still requires admin role and scope. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"q": {
"type": "string",
"maxLength": 200,
"description": "Case-insensitive connection name or service search; up to 200 characters."
},
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Maximum connections in one page; defaults to 25, capped at 100."
},
"cursor": {
"type": "string",
"maxLength": 512,
"description": "Opaque nextCursor from this caller and inventory revision; refresh if the inventory changes."
},
"source": {
"enum": [
"gateway",
"provider-key"
],
"type": "string",
"description": "Filter by canonical store; direct metadata still requires admin role and scope."
}
}
}Page independent configured account roots using current administrator authority. Does not list secrets or imply verified connector availability.
| Argument | Type | Description |
|---|---|---|
| q | string | Literal case-insensitive root name/driver search; wildcard characters have no special meaning. |
| limit | integer | Bounded page size; defaults to 25 and is capped at 100. |
| cursor | string | Opaque nextCursor for the same caller, workspace, search, limit and observed metadata revision; refresh after changes. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"q": {
"type": "string",
"maxLength": 200,
"description": "Literal case-insensitive root name/driver search; wildcard characters have no special meaning."
},
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Bounded page size; defaults to 25 and is capped at 100."
},
"cursor": {
"type": "string",
"maxLength": 1024,
"description": "Opaque nextCursor for the same caller, workspace, search, limit and observed metadata revision; refresh after changes."
}
},
"additionalProperties": false
}Show the latest connector-readiness reports for the organization.
| Argument | Type | Description |
|---|---|---|
| connectorKey | string | Exact report key or metadata connector key to filter the latest 50 persisted reports; omit for all reports in that snapshot. Requires admin:org. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"connectorKey": {
"type": "string",
"minLength": 1,
"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."
}
}
}Search the published OpenAPI operation catalog for relevant help.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum matching operations, from 1 to 20; defaults to 10. |
| query* | string | Search terms for the public OpenAPI operation catalog (1–200 characters); all whitespace-separated terms must match. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Maximum matching operations, from 1 to 20; defaults to 10."
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Search terms for the public OpenAPI operation catalog (1–200 characters); all whitespace-separated terms must match."
}
}
}List evaluations with a stable cursor for the organization.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum results in this page, from 1 to 50; defaults to 20. |
| cursor | string | Opaque nextCursor from the preceding page of this tool. Omit for the first page. |
| status | string | Restrict evaluations to this lifecycle status; omit to include all statuses. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Maximum results in this page, from 1 to 50; defaults to 20."
},
"cursor": {
"type": "string",
"description": "Opaque nextCursor from the preceding page of this tool. Omit for the first page."
},
"status": {
"enum": [
"draft",
"active",
"archived"
],
"type": "string",
"description": "Restrict evaluations to this lifecycle status; omit to include all statuses."
}
}
}Inspect the evaluations and project keys available in the authenticated organization.
| Argument | Type | Description |
|---|---|---|
| projectKey | string | Exact project key to filter the first 50 organization evaluations; omit to inspect that entire snapshot. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"projectKey": {
"type": "string",
"minLength": 1,
"description": "Exact project key to filter the first 50 organization evaluations; omit to inspect that entire snapshot."
}
}
}Return a non-mutating next-step plan for connecting a repository, evaluation, or trace source.
| Argument | Type | Description |
|---|---|---|
| target | string | Workflow to plan: local repository setup, hosted evaluation review, or trace ingestion. Defaults to repository; never executes the plan. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"target": {
"enum": [
"repository",
"evaluation",
"traces"
],
"type": "string",
"default": "repository",
"description": "Workflow to plan: local repository setup, hosted evaluation review, or trace ingestion. Defaults to repository; never executes the plan."
}
}
}Explain a run using its status, failed-case metadata, and evidence-lineage summary.
| Argument | Type | Description |
|---|---|---|
| runId* | any | 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"). |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"runId"
],
"properties": {
"runId": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"pattern": "^[1-9]\\d*$"
}
],
"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\")."
}
}
}List evaluation runs with stable cursors and regression signals.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum results in this page, from 1 to 50; defaults to 20. |
| cursor | string | Opaque nextCursor from the preceding page of this tool. Omit for the first page. |
| status | string | Exact persisted run status to filter by; omit to include all statuses, including incomplete runs. |
| evaluationId* | any | 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"). |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"evaluationId"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Maximum results in this page, from 1 to 50; defaults to 20."
},
"cursor": {
"type": "string",
"description": "Opaque nextCursor from the preceding page of this tool. Omit for the first page."
},
"status": {
"type": "string",
"description": "Exact persisted run status to filter by; omit to include all statuses, including incomplete runs."
},
"evaluationId": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"pattern": "^[1-9]\\d*$"
}
],
"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\")."
}
}
}