
Usero MCP server
Which MCP servers are Usero'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 2026-10-20
- Registry nameio.usero/useroverified in the MCP registry
The registry name sits under usero.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools2
- Server calls itselfusero
- Server version1.28.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 156 ms.
- Its tools do none of the product's use cases we checked: Watch session replays of users before they send feedback; Send feedback items to Linear, Jira or GitHub issues; Request draft pull requests from individual feedback items.
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 score64 of 100answers 96 · does the job 0 · definitions 100 · context 100 · use 0 · connects 100
- What an agent can do with it0 of 3 use cases
- Answered100% of days16 of 16 daily checks
- Median first answer1379 ms
- Space in an agent's context≈ 490 tokensthe definitions of all its tools (2), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · Watch session replays of users before they send feedback
- cannot · Send feedback items to Linear, Jira or GitHub issues
- cannot · Request draft pull requests from individual feedback items
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 →
start_signupStart signup without leaving the agent. Ask for the user's email, do not invent one. Sends an email with a Review connection button; the user presses that button, then types the userCode this tool returns and presses "Yes, connect" on the…
check_signupPoll after start_signup. Returns { status: "pending" } until the user presses the button in the email, then { status: "ready", apiKey, setup } exactly once; the pollToken is dead after that. The setup field holds the exact config or…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"usero": {
"type": "http",
"url": "https://usero.io/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http usero https://usero.io/mcpclaude.ai, ChatGPT and other clients: add https://usero.io/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.
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.