
Gecko MCP server
Which MCP servers are Gecko'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 2026-10-21
- Registry nametech.geckovision/surfverified in the MCP registry
The registry name sits under geckovision.tech. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools1
- Server calls itselfgecko
- Server version0.12.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 253 ms.
- Its tools do none of the product's use cases we checked: check whether suppliers are still active; size up suppliers by headcount; identify decision makers at each company.
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 score69 of 100answers 100 · does the job 0 · definitions 100 · context 100 · use 39 · connects 100
- What an agent can do with it0 of 3 use cases
- Use86 PyPI downloads a week21 GitHub stars
- Answered100% of days8 of 8 daily checks
- Median first answer245 ms
- Space in an agent's context≈ 80 tokensthe definitions of all its tools (1), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 1 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · check whether suppliers are still active
- cannot · size up suppliers by headcount
- cannot · identify decision makers at each company
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
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 →
list_surfacesEvery API surface served on this host, with the MCP URL to reconnect to. Use it when you landed on the host root and need a specific API. Free, instant, and it lists only what the public index lists.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"surf": {
"type": "http",
"url": "https://mcp.geckovision.tech/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http geckovision https://mcp.geckovision.tech/mcpclaude.ai, ChatGPT and other clients: add https://mcp.geckovision.tech/mcp as a custom connector in the settings.
Also shipped through: pypi
OpenAPI spec
2 paths, read 2026-10-21. Open the spec ↗
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.