Skip to main content
Glama
Sign In
OpenF1 MCP Server

OpenF1 MCP Server

by ragulhari
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Car location

get_location
Read-onlyIdempotent

Fetches approximate car position (x, y, z) at ~3.7 Hz for one driver, given session_key, driver_number, and a lap_number or date range (max 10 min).

Instructions

Approximate car position on track (x, y, z) at about 3.7 Hz. VERY large data: you must give session_key, ONE driver_number and a lap_number or a date range (max 10 minutes).

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of records to return (default 200, max 1000). A summary is added when the result is larger.
fieldsNoReturn only these attributes. Use this to make large results smaller.
date_toNoEnd of the time range (UTC, ISO 8601). Filters on "date" <= value.
filtersNoExtra comparison filters, e.g. [{"field":"lap_duration","op":"<","value":90}]. Allowed fields: date, driver_number, meeting_key, session_key, x, y, z. Array fields cannot be filtered.
date_fromNoStart of the time range (UTC, ISO 8601), e.g. "2025-11-09T17:05:00Z". Filters on "date" >= value.
lap_numberNoLap number. The server finds the start and end time of this lap and returns only its telemetry.
session_keyNoSession identifier. Use "latest" for the current or most recent session.
driver_numberNoDriver number(s) for the season, e.g. 1, 44, 81. Give a list to get more than one driver.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is the sampling rate (~3.7 Hz) and the 'VERY large data' warning plus the 10-minute range cap, which genuinely shapes invocation strategy. It doesn't describe accuracy or response shape, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences, front-loaded with the resource and sample rate, then the invocation constraints. No filler; every clause carries actionable information.

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?

No output schema exists, and the description covers volume, frequency, and required scoping well enough to call the tool safely. It leaves out what fields come back beyond x/y/z and any accuracy caveat, which would round out completeness.

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 coverage is 100%, so the baseline is 3; the description reinforces the session_key/lap_number/date-range usage model and adds the 10-minute cap that the schema doesn't state. However, 'ONE driver_number' conflicts with the schema's allowed integer array (maxItems 30), creating ambiguity rather than adding meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (car position on track) and even the payload shape (x, y, z) and sampling rate (3.7 Hz), which goes well beyond the title 'Car location'. It does not explicitly name how it differs from siblings like get_position or get_car_data, which prevents a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete preconditions: session_key, exactly one driver_number, and either lap_number or a date range capped at 10 minutes, framed by a data-volume warning. What's missing is an explicit statement of when to prefer this over get_car_data or get_position.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools