MCP Metrics

The Gateway MCP Metrics Query API provides a flexible way to query Gateway MCP server and tool metrics: methods invoked, tools called, latency, errors, and traffic mix. You can retrieve either distribution (aggregated) or timeseries results with powerful filtering and grouping.

This page covers datasource: "mcpMetrics". For other datasources, see Model, Guardrail, Cache, Routing, and Agent metrics.

All requests go to a single endpoint:

POST https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query

Send JSON with Authorization: Bearer <your_api_key> and Content-Type: application/json.

Access control

Access to metrics is governed by the data access rules configured by your tenant. The server applies these rules automatically based on the caller’s identity—you don’t pass any RBAC or scoping fields in the request. What a caller can query (their own data, their team’s data, or tenant-wide data) depends entirely on the rules an admin has set up. See Configure Data Access for how these rules are defined and evaluated.

Authentication

Get your API key

Authenticate with your TrueFoundry API key. You can use either a Personal Access Token (PAT) or Virtual Account Token (VAT).

Personal Access Token (PAT): Go to Access → Personal Access Tokens in your TrueFoundry dashboard
Virtual Account Token (VAT): Go to Access → Virtual Account Tokens (requires admin permissions)

For detailed authentication setup, see our Authentication guide.

Quick start

By default, the API returns metrics across all MCP methods including non-tool calls (initialize, tools/list, prompts/list, etc.). To analyse tool-call usage specifically, filter with {"fieldName": "method", "operator": "IN", "value": ["tools/call"]} and optionally group by toolName.

Token, cost, and time-to-first-token aggregations (inputTokens, outputTokens, costInUSD, timeToFirstTokenMs, interTokenLatencyMs, timePerOutputTokenLatencyMs) do not apply to MCP metrics; they are model-only signals. Use the Model Metrics datasource if you need them.

Distribution query
Timeseries query

Top MCP servers by request count and p99 latency:

import requests

response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2026-04-21T00:00:00.000Z",
        "endTs": "2026-04-22T00:00:00.000Z",
        "datasource": "mcpMetrics",
        "type": "distribution",
        "aggregations": [
            {"type": "count", "column": "mcpServerName"},
            {"type": "avg", "column": "latencyMs"},
            {"type": "p99", "column": "latencyMs"}
        ],
        "groupBy": ["mcpServerName"]
    }
)

print(response.json())

Hourly tool-call counts and p99 latency by tool:

import requests

response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2026-04-21T00:00:00.000Z",
        "endTs": "2026-04-22T00:00:00.000Z",
        "datasource": "mcpMetrics",
        "type": "timeseries",
        "interval": "1 hour",
        "aggregations": [
            {"type": "count", "column": "toolName"},
            {"type": "p99", "column": "latencyMs"}
        ],
        "groupBy": ["toolName"],
        "filters": [
            {"fieldName": "method", "operator": "IN", "value": ["tools/call"]}
        ]
    }
)

print(response.json())

API reference

Post JSON to the endpoint above with Authorization: Bearer <your_api_key> and Content-Type: application/json.

Request parameters

string

required

ISO 8601 timestamp marking the inclusive lower bound of the query window (e.g. "2026-04-21T00:00:00.000Z").

string

required

ISO 8601 timestamp marking the exclusive upper bound of the query window (e.g. "2026-04-22T00:00:00.000Z").

string

required

The data source to query. Use "mcpMetrics" for Gateway MCP metrics.

string

required

The type of query to execute:

"distribution": returns aggregated rows (one row per groupBy combination).
"timeseries": returns time-bucketed rows (one row per bucket per groupBy combination). Requires interval.

array

Array of { type, column } objects describing the aggregations to compute. When omitted, only the implicit total = COUNT(*) is returned.

"aggregations": [
    {"type": "count", "column": "mcpServerName"},
    {"type": "avg", "column": "latencyMs"},
    {"type": "p99", "column": "latencyMs"}
]

Supported aggregation types

Type	Description
`sum`	Sum of values
`count`	Non-null count of the column
`countDistinct`	Distinct count
`min`	Minimum value
`max`	Maximum value
`avg`	Average
`p5`, `p10`, `p25`, `p50`, `p75`, `p90`, `p95`, `p99`, `p999`	Percentiles (approximate)
`rateSum`	`sum` normalised by the interval in seconds (timeseries only)
`rateAvg`	`avg` normalised by the interval in seconds (timeseries only)
`rateMin`	`min` normalised by the interval in seconds (timeseries only)
`rateMax`	`max` normalised by the interval in seconds (timeseries only)
`ratePerMinute`	Value divided by the interval in minutes (timeseries only)

Supported aggregation columns

Column	Supported aggregation types	Notes
`latencyMs`	all scalar and all percentiles	Total MCP request latency in ms
`mcpServerName`	`count`, `countDistinct`	Useful for “how many servers were called?”
`method`	`count`, `countDistinct`	Useful for traffic-mix breakdowns
`toolName`	`count`, `countDistinct`	Useful when filtered to `method = "tools/call"`

array

Array of field names to group results by. Custom metadata keys are supported with a metadata. prefix (e.g. "metadata.environment").

"groupBy": ["mcpServerName", "toolName", "metadata.environment"]

Available group-by fields

Field	Notes
`mcpServerName`	The MCP server name
`method`	JSON-RPC method invoked (e.g. `tools/call`, `tools/list`, `initialize`)
`toolName`	Tool invoked (populated only for `tools/call`)
`userEmail`	Group by user (response key: `createdBySubjectSlug`)
`virtualaccount`	Group by virtual account (response key: `createdBySubjectSlug`)
`team`	Unnests the `Teams` array
`createdBySubjectType`	Distinguishes `user` vs `virtualaccount`
`metadata.<key>`	Group by a custom metadata key

When groupBy contains userEmail (without virtualaccount), the server auto-injects WHERE CreatedBySubjectType = 'user'. virtualaccount alone auto-injects 'virtualaccount'. When both appear, scope it yourself with createdBySubjectType if needed.

array

Array of filter objects, AND-combined. See Filtering below for the full operator reference and the per-field allow-list.

string

Required for timeseries queries. Bucket size as <positive integer> <unit>, where <unit> is one of second, minute, hour, day, week, month, year (with or without a trailing s). Examples: "30 second", "5 minute", "1 hour", "1 day". Compound expressions like "1 hour 30 minute" are rejected.

number

deprecated

Deprecated alias for interval. Accepts a positive integer number of seconds (e.g. 3600 for hourly). Prefer interval in new code. If both are provided, interval wins.

Filtering

Filters narrow down the rows that go into each aggregation and group. They are AND-combined; there is no OR-group support. The server enforces a per-field operator allow-list, so the exact subset of operators you can use depends on the field.

Field filters
Metadata filters

For standard datasource fields, use fieldName:

{
    "fieldName": "method",
    "operator": "IN",
    "value": ["tools/call"]
}

For custom request-metadata keys, use metadataKey. Works on every datasource:

{
    "metadataKey": "environment",
    "operator": "IN",
    "value": ["production"]
}

Filterable fields and allowed operators

The MCP-specific string fields (mcpServerName, method, toolName) accept only a narrow set of string operators (IN, NOT_IN, STRING_CONTAINS, STRING_STARTS_WITH, STRING_ENDS_WITH). EQUAL and NOT_EQUAL are only supported on userEmail, virtualAccount, and conversationID.

Field	Type	Allowed operators
`mcpServerName`	string	`IN`, `NOT_IN`, `STRING_CONTAINS`, `STRING_STARTS_WITH`, `STRING_ENDS_WITH`
`method`	string	`IN`, `NOT_IN`, `STRING_CONTAINS`, `STRING_STARTS_WITH`, `STRING_ENDS_WITH`
`toolName`	string	`IN`, `NOT_IN`, `STRING_CONTAINS`, `STRING_STARTS_WITH`, `STRING_ENDS_WITH`
`userEmail`	string	full string operator set
`virtualAccount`	string	full string operator set
`team`	array	`ARRAY_HAS_ANY`, `ARRAY_HAS_NONE`
`latencyMs`	number	`GREATER_THAN`, `LESS_THAN`, `GREATER_THAN_EQUAL`, `LESS_THAN_EQUAL`, `BETWEEN`
`conversationID`	string	full string operator set
`metadataKey` / `metadata.<key>`	string	full string operator set

Filter operators reference

String field operators

Operator	Description	Example value
`EQUAL`	Exact match	`"alice@example.com"`
`NOT_EQUAL`	Not equal to value	`"bot@example.com"`
`IN`	Match any value in the list	`["tools/call", "tools/list"]`
`NOT_IN`	Exclude values in the list	`["initialize"]`
`STRING_CONTAINS`	Contains substring	`"github"`
`STRING_NOT_CONTAINS`	Does not contain substring	`"internal"`
`STRING_STARTS_WITH`	Starts with prefix	`"github-"`
`STRING_NOT_STARTS_WITH`	Does not start with prefix	`"internal-"`
`STRING_ENDS_WITH`	Ends with suffix	`"-mcp"`
`STRING_NOT_ENDS_WITH`	Does not end with suffix	`"-deprecated"`
`IS_NULL`	`true` matches rows where the field is unset; `false` matches rows where it is set	`true`

Numeric field operators

Operator	Description	Example value
`EQUAL`	Exact match	`1000`
`NOT_EQUAL`	Not equal to value	`0`
`IN`	Match any value in the list	`[100, 200, 300]`
`NOT_IN`	Exclude values in the list	`[0]`
`GREATER_THAN`	Strictly greater than	`1000`
`LESS_THAN`	Strictly less than	`5000`
`GREATER_THAN_EQUAL`	Greater than or equal to	`100`
`LESS_THAN_EQUAL`	Less than or equal to	`1000`
`BETWEEN`	Between two values (inclusive)	`[500, 5000]`
`IS_NULL`	`true` matches rows where the field is unset; `false` matches rows where it is set	`true`

Array field operators (used by team)

Operator	Description	Example value
`ARRAY_HAS_ANY`	Match if the array contains any of the values	`["team-alpha", "team-beta"]`
`ARRAY_HAS_NONE`	Match if the array contains none of the values	`["excluded-team"]`

Custom metadata, team unnesting, and combining filters

Custom metadata filtering and grouping. Every datasource supports filtering and grouping by custom request-metadata keys:

Filter: { "metadataKey": "environment", "operator": "EQUAL", "value": "prod" }
Group: include "metadata.environment" in the groupBy array (string literal, prefix is metadata.).

Metadata fields are treated as strings; use the string field operators above.Implicit team unnesting. When team is in groupBy (or used as the column of an aggregation), the server transparently UNNESTs the Teams array CTE before applying RBAC. Callers don’t need to do anything extra. Rows whose Teams array is NULL or empty drop out naturally.Combining multiple filters. Filters are AND-combined:

{
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]},
        {"fieldName": "mcpServerName", "operator": "IN", "value": ["github-mcp", "atlassian-mcp"]},
        {"fieldName": "latencyMs", "operator": "BETWEEN", "value": [100, 10000]},
        {"fieldName": "team", "operator": "ARRAY_HAS_ANY", "value": ["team-alpha"]}
    ],
    "groupBy": ["mcpServerName", "toolName"]
}

Query examples

Every example posts a JSON body to the endpoint above. To keep the snippets short, only the json body is shown; the request wrapper is identical to the Quick start.

MCP metrics include all JSON-RPC methods by default. Many of the examples below pin the tool-call subset with {"fieldName": "method", "operator": "IN", "value": ["tools/call"]} so toolName is populated.

Distribution examples

Top servers by request count

Count requests per server, alongside p99 latency:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "count", "column": "mcpServerName"},
        {"type": "p99", "column": "latencyMs"}
    ],
    "groupBy": ["mcpServerName"]
}

Tool calls grouped by tool name

Restrict to tools/call and group by toolName:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "count", "column": "toolName"}
    ],
    "groupBy": ["toolName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]}
    ]
}

Method distribution per server

Traffic mix per server (initialize / tools/list / tools/call / …):

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "count", "column": "method"}
    ],
    "groupBy": ["mcpServerName", "method"]
}

Latency percentiles by tool

p50, p90, and p99 latency per tool:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "p50", "column": "latencyMs"},
        {"type": "p90", "column": "latencyMs"},
        {"type": "p99", "column": "latencyMs"}
    ],
    "groupBy": ["toolName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]}
    ]
}

Distinct tools per server

How many unique tools each server exposed:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "countDistinct", "column": "toolName"}
    ],
    "groupBy": ["mcpServerName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]}
    ]
}

Exclude internal tools

Count tool calls excluding internal/debug tools using NOT_IN:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "count", "column": "toolName"}
    ],
    "groupBy": ["toolName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]},
        {"fieldName": "toolName", "operator": "NOT_IN", "value": ["internal-debug", "healthcheck", "echo"]}
    ]
}

High-latency tool calls

Find slow tool calls (above 5 seconds):

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "count", "column": "toolName"}
    ],
    "groupBy": ["mcpServerName", "toolName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]},
        {"fieldName": "latencyMs", "operator": "GREATER_THAN", "value": 5000}
    ]
}

Group by metadata

Tool-call counts per metadata key:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "count", "column": "toolName"}
    ],
    "groupBy": ["toolName", "metadata.environment"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]}
    ]
}

Filter by team

Tool-call activity scoped to a team:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "count", "column": "toolName"}
    ],
    "groupBy": ["mcpServerName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]},
        {"fieldName": "team", "operator": "ARRAY_HAS_ANY", "value": ["team-alpha"]}
    ]
}

Complex filter combination

Tool-call traffic on a known list of servers, latency window, scoped to a team:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "distribution",
    "aggregations": [
        {"type": "count", "column": "toolName"},
        {"type": "p99", "column": "latencyMs"}
    ],
    "groupBy": ["mcpServerName", "toolName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]},
        {"fieldName": "mcpServerName", "operator": "IN", "value": ["github-mcp", "atlassian-mcp"]},
        {"fieldName": "latencyMs", "operator": "BETWEEN", "value": [100, 10000]},
        {"fieldName": "team", "operator": "ARRAY_HAS_ANY", "value": ["team-alpha"]}
    ]
}

Timeseries examples

Every timeseries query must include interval (or the deprecated intervalInSeconds). Buckets are expressed as <positive integer> <unit> strings like "5 minute", "1 hour", or "1 day".

Hourly request volume

Total MCP requests per hour:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "timeseries",
    "interval": "1 hour",
    "aggregations": [
        {"type": "count", "column": "mcpServerName"}
    ]
}

Hourly tool-call counts

Hourly tool calls grouped by tool:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "timeseries",
    "interval": "1 hour",
    "aggregations": [
        {"type": "count", "column": "toolName"}
    ],
    "groupBy": ["toolName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]}
    ]
}

Hourly p99 latency by server

Track regressions per server, bucket-by-bucket:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "timeseries",
    "interval": "1 hour",
    "aggregations": [
        {"type": "p99", "column": "latencyMs"}
    ],
    "groupBy": ["mcpServerName"]
}

Hourly method mix

Volume per JSON-RPC method over time:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "timeseries",
    "interval": "1 hour",
    "aggregations": [
        {"type": "count", "column": "method"}
    ],
    "groupBy": ["method"]
}

5-minute traffic on a specific server

Fine-grained tool-call traffic on one server:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-21T06:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "timeseries",
    "interval": "5 minute",
    "aggregations": [
        {"type": "count", "column": "toolName"},
        {"type": "p99", "column": "latencyMs"}
    ],
    "groupBy": ["toolName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]},
        {"fieldName": "mcpServerName", "operator": "IN", "value": ["github-mcp"]}
    ]
}

Daily traffic over a week

Daily tool-call volume across a 7-day window:

json={
    "startTs": "2026-04-14T00:00:00.000Z",
    "endTs": "2026-04-21T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "timeseries",
    "interval": "1 day",
    "aggregations": [
        {"type": "count", "column": "toolName"}
    ],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]}
    ]
}

Hourly counts by team

Per-team tool-call usage over time:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "timeseries",
    "interval": "1 hour",
    "aggregations": [
        {"type": "count", "column": "toolName"}
    ],
    "groupBy": ["team"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]},
        {"fieldName": "team", "operator": "ARRAY_HAS_ANY", "value": ["team-alpha", "team-beta"]}
    ]
}

Complex timeseries query

Multiple filters and grouping together:

json={
    "startTs": "2026-04-21T00:00:00.000Z",
    "endTs": "2026-04-22T00:00:00.000Z",
    "datasource": "mcpMetrics",
    "type": "timeseries",
    "interval": "1 hour",
    "aggregations": [
        {"type": "count", "column": "toolName"},
        {"type": "p99", "column": "latencyMs"}
    ],
    "groupBy": ["mcpServerName", "toolName"],
    "filters": [
        {"fieldName": "method", "operator": "IN", "value": ["tools/call"]},
        {"fieldName": "mcpServerName", "operator": "IN", "value": ["github-mcp", "atlassian-mcp"]},
        {"metadataKey": "environment", "operator": "IN", "value": ["production"]}
    ]
}

Response format

Every successful response has the same outer shape:

{
  "data": {
    "dataPoints": [
      {
        "startTimestamp": "2026-04-29T12:00:00.000Z",
        "endTimestamp": "2026-04-29T13:00:00.000Z",
        "total": 1234,
        "<aggregationKey>": 0,
        "<groupByKey>": "value-or-null"
      }
    ]
  }
}

total: implicit COUNT(*) for the row. Always present.
<aggregationKey>: one key per requested aggregation. The key is <type><Column> in camelCase (e.g. countToolName, p99LatencyMs, countDistinctMcpServerName).
<groupByKey>: one key per groupBy entry. The key is the lowerCamelCase form of the underlying column. Two special mappings:
- userEmail and virtualaccount both map to createdBySubjectSlug in the response.
- team maps to team (the value is a single unnested scalar, not an array). All other groupBy keys preserve their lowerCamelCase name.
startTimestamp / endTimestamp: present only for timeseries responses. Bucket start and end as ISO 8601 timestamp strings; endTimestamp equals the next bucket’s startTimestamp. Distribution responses omit both.

Distribution response example

{
  "data": {
    "dataPoints": [
      {
        "mcpServerName": "github-mcp",
        "total": 4200,
        "countMcpServerName": 4200,
        "avgLatencyMs": 142.3,
        "p99LatencyMs": 612.0
      },
      {
        "mcpServerName": "atlassian-mcp",
        "total": 1850,
        "countMcpServerName": 1850,
        "avgLatencyMs": 98.7,
        "p99LatencyMs": 411.5
      }
    ]
  }
}

Timeseries response example

{
  "data": {
    "dataPoints": [
      {
        "startTimestamp": "2026-04-21T00:00:00.000Z",
        "endTimestamp": "2026-04-21T01:00:00.000Z",
        "toolName": "create_issue",
        "total": 18,
        "countToolName": 18,
        "p99LatencyMs": 380.0
      },
      {
        "startTimestamp": "2026-04-21T01:00:00.000Z",
        "endTimestamp": "2026-04-21T02:00:00.000Z",
        "toolName": "create_issue",
        "total": 22,
        "countToolName": 22,
        "p99LatencyMs": 410.0
      }
    ]
  }
}

If groupBy is empty or omitted, the response collapses to a single row (or one row per timeseries bucket) summarising every MCP request inside the window.

toolName rows are populated only for method = "tools/call"; rows for other methods will surface toolName: null in the response when grouped by it.

Error responses

A malformed query returns 400 Bad Request:

{
  "statusCode": 400,
  "message": "Invalid query",
  "details": ["..."]
}

Common causes and other status codes

Common causes of 400:

Operator not allowed on this field, for example, EQUAL on mcpServerName (it supports only IN, NOT_IN, and STRING_* operators).
Missing required value (or wrong shape, e.g. scalar where array is expected for IN / BETWEEN).
Unknown field name for the datasource (e.g. inputTokens on mcpMetrics).
Invalid interval format (compound expressions, unrecognised unit, non-positive integer).
Missing required interval for a timeseries query.

Other status codes:

401 Unauthorized: missing or invalid bearer token.
403 Forbidden: caller does not have permission for the requested scope.
500 Internal Server Error: unexpected server error while executing the query.

Get Started

LLM Gateway

MCP Registry and Gateway

Skills Registry

Prompt Registry

Guardrails and Security

Observability

Deployment

Admin Guide

Chat

Messages

Embeddings

Rerank

Responses

Image

Audio

Batch

Files

Fine-tuning

Moderations

Models

Access control

Authentication

Quick start

API reference

Request parameters

Filtering

Query examples

Distribution examples

Timeseries examples

Response format

Error responses

​Access control

​Authentication

​Quick start

​API reference

​Request parameters

​Filtering

​Query examples

​Distribution examples

​Timeseries examples

​Response format

​Error responses

Access control

Authentication

Quick start

API reference

Request parameters

Filtering

Query examples

Distribution examples

Timeseries examples

Response format

Error responses