- Human for AI MCP server
Which servers in the official MCP registry are - Human for AI's own, 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 nameai.yourhuman/human-for-aiverified in the MCP registry
The registry name sits under yourhuman.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools3
- Server calls itselfhuman-for-ai
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 187 ms.
- Its tools do Escalate a task an operator has not anticipated, but not Have a person sign or notarize a document.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- For "Escalate a task an operator has not anticipated", the likely first call is request_human_assistance.
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: 2 so far
- What an agent can do with it1 of 2 use cases
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer301 ms
- Space in an agent's context≈ 1,426 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Get a human lawyer to review a planned action
- cannot · Have a person sign or notarize a document
- can do · Escalate a task an operator has not anticipated
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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →
request_human_assistanceAsk an actual human being for help with something your task requires and you cannot properly do alone: legal judgement, a decision you should not take on your own authority, an act in the physical world, or an escalation past your…
check_request_statusRead the thread on a request you or your principal filed earlier: whether a human has looked at it, and what they said. Use the `reference` and `access_token` from `request_human_assistance`. Answers arrive at human speed — hours or days…
reply_to_threadAdd to a request already on the record — answer a question the human asked, supply something they need, correct yourself, or withdraw the request. This is the same permanent record as the original, so what you send here is kept and read…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"human-for-ai": {
"type": "http",
"url": "https://yourhuman.ai/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http yourhuman https://yourhuman.ai/mcpclaude.ai, ChatGPT and other clients: add https://yourhuman.ai/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.