
UGT MCP server
Which MCP servers are UGT'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 2026-11-03
- Registry namecom.usegithubthing/ugtverified in the MCP registry
The registry name sits under usegithubthing.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-03
- Tools5
- Server calls itselfugt
- Server version0.1.0
- Protocol version2025-06-18
On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 299 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.
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 answer320 ms
- Space in an agent's context≈ 762 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results5 of 5 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Install a GitHub project on a Mac, Linux or Windows computer
- not sure · Fix installation errors that stop a project from starting
- cannot · Reopen and stop a set-up project later
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 →
search_recipesFind how UGT gets a job done on the user's own computer with open-source software from GitHub, such as subtitles, CAD, video or web pages to Markdown. Search by what the user wants done or by a project's name, or omit the query to list…
get_projectGet how UGT runs one GitHub project, by owner/repo or its link: the recipes people have shared for it, each verified for one job. Call it whenever the user names a GitHub project they want to use. Every GitHub project works with UGT, so…
get_recipeGet one recipe in full: what it takes and makes, what stays usable after a run, the settings it asks for, everything it can reach and why, where it was tested, and every file it runs. Use it to tell the user exactly what a recipe will do…
read_recipe_fileRead one of a recipe's files, such as compose.yaml, its Dockerfile or recipe.json, to see exactly what it runs. get_recipe lists its files.
get_installGet the one line that installs UGT on the user's computer and connects it to their AI apps, UGT for Claude Desktop, and what each computer runs recipes in. Omit the computer to get every one.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"ugt": {
"type": "http",
"url": "https://mcp.usegithubthing.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http usegithubthing https://mcp.usegithubthing.com/mcpclaude.ai, ChatGPT and other clients: add https://mcp.usegithubthing.com/mcp as a custom connector in the settings.
Also shipped through: mcpb
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.
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.