Gymmy

Search gyms and studios

search_gyms

Read-onlyIdempotent

Find gyms and studios (CrossFit, HYROX, fitness, yoga, pilates, boxing, martial arts, dance, climbing) in France and Europe, near a point or by name, city or postcode. Activity words in the query filter ('CrossFit Nice', 'yoga Lyon'); the rest is the place or the gym name. Gymmy gyms (onGymmy: true) can be booked; others are listed from OpenStreetMap and other public sources (each with its source page and date), not bookable on Gymmy, with their address, opening hours, the gym's own booking link and prices when read on its website (each with its source and date, not verified by Gymmy), and a claim link. Use the gym value with get_gym, get_schedule, get_prices or start_trial.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_gyms"
  }
}

Input Schema

Name	Required	Description
`lat`	No	Latitude to search around.
`lng`	No	Longitude to search around.
`limit`	No	Max results. Default 10.
`query`	No	Gym name, address, district, city or postcode, optionally with an activity, e.g. 'Lyon', 'CrossFit Nice', 'yoga Lyon', '12 rue Oberkampf Paris' or 'The Wolf Pack'. Places are geocoded when no lat/lng is given.
`locale`	No	Answer language: fr (default), en, pt, es or de. Pass en when the person writes in English.
`activity`	No	Only this activity (studios not on Gymmy). Read from the query when it names one.
`radius_km`	No	Radius in km, 1 to 50. Default: 10, or fitted to the geocoded place (3 for an address).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 9, 2026

changedInput schema / properties / locale / description

Previous value: -"Answer language: fr (default) or en. Pass en when the person writes in English."New value: +"Answer language: fr (default), en, pt, es or de. Pass en when the person writes in English."

changedInput schema / properties / locale / enum

Previous value: -[
-  "fr",
-  "en"
-]New value: +[
+  "fr",
+  "en",
+  "pt",
+  "es",
+  "de"
+]

Changed3 schema fields changedNov 9, 2026

changedInput schema / properties / activity / description

Previous value: -"Only this activity (studios not on Gymmy)."New value: +"Only this activity (studios not on Gymmy). Read from the query when it names one."

changedInput schema / properties / locale / description

Previous value: -"Answer language. Default fr."New value: +"Answer language: fr (default) or en. Pass en when the person writes in English."

changedInput schema / properties / query / description

Previous value: -"Gym name, address, district, city or postcode, e.g. 'Lyon', '12 rue Oberkampf Paris' or 'CrossFit Nantes'. Places are geocoded when no lat/lng is given."New value: +"Gym name, address, district, city or postcode, optionally with an activity, e.g. 'Lyon', 'CrossFit Nice', 'yoga Lyon', '12 rue Oberkampf Paris' or 'The Wolf Pack'. Places are geocoded when no lat/lng is given."

First observedOct 20, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already mark the tool read-only, idempotent, and non-destructive, but the description adds important behavior beyond that: Gymmy gyms are bookable, external OSM/public-source gyms are not, and external data includes source/date context plus unverified website-derived prices. This is exactly the kind of source and bookability distinction an agent needs before presenting results.

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

Conciseness4/5

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

The purpose is front-loaded and nearly every clause adds useful information about scope, sourcing, bookability, or follow-up tools. However, it is a dense, semicolon-heavy paragraph, and the source/bookability distinctions would be easier to scan if split into shorter sentences or bullets.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite there being no output schema, the description explains the key return distinctions and fields: bookable Gymmy gyms versus externally listed gyms, source page/date, address, opening hours, booking link, prices with source/date and verification caveat, and a claim link. That is sufficient context for an agent to use and present results correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema handles most parameter meaning. The description still adds non-obvious query semantics: activity words inside `query` filter results, while the remaining text is treated as the place or gym name, which clarifies how `query` interacts with the explicit `activity` enum.

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

Purpose5/5

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

The description uses a specific verb and resource ('Find gyms and studios'), defines geographic and query scope, and enumerates supported activities. It also distinguishes Gymmy-bookable gyms from externally listed, non-bookable gyms, so the agent can tell what the tool returns.

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?

It gives clear usage context: search near a point, by name, city, postcode, or activity, and use the returned `gym` value with get_gym, get_schedule, get_prices, or start_trial. It does not explicitly contrast this tool with search_classes or state a when-not condition, so guidance is strong but not fully exhaustive.

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

All Gymmy tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.