bitHuman docs is an MCP server published by ai.bithuman, hosted at docs.bithuman.ai. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 2 tools, including search, fetch.
The bitHuman docs over MCP: two read-only tools, search and fetch; it needs no account and no key.
37 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Search docs.bithuman.ai (bitHuman real-time avatar SDKs, the REST API, deployment options, models, pricing). Returns JSON {results: [{id, title, url, section, text}]}, most relevant first (default 8, at most 20); `text` is a short snippet, so pass the `id` to `fetch` for the whole page. Example: {"query": "create an agent and poll status", "section": "API reference"}. An empty query is an error; no match returns an empty list (try fewer or other words, or drop `section`). The REST contract as OpenAPI 3.1 JSON: https://docs.bithuman.ai/openapi.json.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many results, 1 to 20 (default 8). |
| query * | string | What to look for, e.g. "Android first frame" or "LiveKit secret". |
| section | string | Limit to one section. |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "search",
"title": "Search the bitHuman docs",
"description": "Search docs.bithuman.ai (bitHuman real-time avatar SDKs, the REST API, deployment options, models, pricing). Returns JSON {results: [{id, title, url, section, text}]}, most relevant first (default 8, at most 20); `text` is a short snippet, so pass the `id` to `fetch` for the whole page. Example: {\"query\": \"create an agent and poll status\", \"section\": \"API reference\"}. An empty query is an error; no match returns an empty list (try fewer or other words, or drop `section`). The REST contract as OpenAPI 3.1 JSON: https://docs.bithuman.ai/openapi.json.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "How many results, 1 to 20 (default 8)."
},
"query": {
"type": "string",
"description": "What to look for, e.g. \"Android first frame\" or \"LiveKit secret\"."
},
"section": {
"enum": [
"Overview",
"Platforms",
"Models",
"Guides",
"Deploy",
"Performance",
"API reference",
"Get started",
"Resources",
"Build",
"API"
],
"type": "string",
"description": "Limit to one section."
}
}
},
"annotations": {
"title": "Search the bitHuman docs",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fetch one docs page as markdown by the id `search` returned (a path such as /platforms/python), or by its full docs.bithuman.ai URL. Returns JSON {id, title, text (the whole page as markdown), url, metadata}. Example: {"id": "/api/agents"}. Errors: an unknown path (run `search` for the id) and a URL outside docs.bithuman.ai are refused. Read-only, no sign-in.
| Parameter | Type | Description |
|---|---|---|
| id * | string | A page path (/platforms/python) or URL (https://docs.bithuman.ai/platforms/python). |
{
"name": "fetch",
"title": "Fetch a bitHuman docs page",
"description": "Fetch one docs page as markdown by the id `search` returned (a path such as /platforms/python), or by its full docs.bithuman.ai URL. Returns JSON {id, title, text (the whole page as markdown), url, metadata}. Example: {\"id\": \"/api/agents\"}. Errors: an unknown path (run `search` for the id) and a URL outside docs.bithuman.ai are refused. Read-only, no sign-in.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "A page path (/platforms/python) or URL (https://docs.bithuman.ai/platforms/python)."
}
}
},
"annotations": {
"title": "Fetch a bitHuman docs page",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}bitHuman documentation (https://docs.bithuman.ai). Use `search` to find pages and `fetch` to read one as markdown; the index is https://docs.bithuman.ai/llms.txt.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.