Gaitkit MCP server
Which MCP servers are Gaitkit's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-28
- Registry namecom.gaitkit/mcpverified in the MCP registry
The registry name sits under gaitkit.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools5
- Server calls itselfgaitkit
- Server version0.4.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 115 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 4 of 5 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer121 ms
- Space in an agent's context≈ 443 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsB · 87 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 4 of 5
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_assetsSearch remixable low-poly 3D assets: creatures and mechs that walk with procedural IK, vehicles, buildings, nature and props. Returns coverage none|poor|ok; on none/poor say so honestly. Each result has tier free|pro (pro GLB downloads…
get_assetFull metadata for one asset: real size in metres, palette, knob schema, rigged parts, gait for walkers, file URLs and ready-to-paste three.js code.
get_variantTurn plain words into a createAsset({...}) call: colours ("red", "dark green"), sizes ("big claws", "tall", "8 eyes"), features ("no horn", "with porch"), option and preset names. English or Turkish. Check confidence; on none it returns…
who_am_iWhich Gaitkit account is calling (from the API key in the Authorization header), its plan, and the CDN token to put in shipped code. Anonymous callers get the free catalogue.
report_needRegister an asset the catalogue does not have yet. Use when search coverage is none or poor.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"gaitkit": {
"type": "http",
"url": "https://gaitkit.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http gaitkit https://gaitkit.com/mcpclaude.ai, ChatGPT and other clients: add https://gaitkit.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.