Skip to content

bitHuman MCP server

ai.bithuman/charactersbithuman.aistreamable-httpv1.0.0Scanned

Animated AI characters in your chat: short clips of a character saying your words, or a live talk.

3 tools: 2 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 2 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the bitHuman MCP server can do

The bitHuman MCP server is published by bithuman.ai, a domain the MCP Registry verified. It has 3 tools. It can create or change data (2 tools: make_character_video and talk_to_character), but cannot delete data. 1 tool only reads.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 11, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

3 tools

Changes things 2Claude Code: ask
  • make_character_videoMake a short video of one bitHuman house character saying `text` word for word, in its own voice.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Make a short video of one bitHuman house character saying `text` word for word, in its own voice. Returns video_url (an MP4 that plays inline and expires after 7 days), duration_seconds and share_url, labelled AI character. Example: {"character": "wise-pup", "text": "Welcome back! Ready for today's lesson?"}. Limits: `text` is 3 to 200 characters and at most 19 seconds when spoken (about 15 s is typical); one video at a time per user; 10 videos per user per UTC day; the same character and text again replays the earlier clip at once. Errors come back as isError with one sentence saying what to do: an unknown character (call list_characters), text too short or too long (rewrite it), personal information such as a phone number, email or street address (remove it), busy (retry in a minute), the daily limit (try again after 00:00 UTC), resting (try later). To hold a conversation in character, write each reply yourself and call this tool once per reply.

    Annotations the server declares

    • title: Make character video
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: false
  • talk_to_characterOpen a live voice conversation with one bitHuman house character in a player in the chat.No findings

    Why it is in this group

    • The description's first verb is "open": a word for a change.
    Description, as the server wrote it
    Open a live voice conversation with one bitHuman house character in a player in the chat. The user presses Start and speaks through the microphone; the character answers out loud. A conversation lasts up to 60 seconds (max_seconds), then ends by itself; call again for another. Returns session_url: when the host shows no player, give the user that link. Example: {"character": "wise-pup"}. Needs a microphone in the user's browser. Errors come back as isError: an unknown character (call list_characters and use an id whose `talk` is true), resting (live conversations are off right now; make_character_video still works).

    Annotations the server declares

    • title: Talk to character
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: false
Only reads 1Show 1 read-only tool
  • list_charactersList the bitHuman house characters that can speak.No findings

    Why it is in this group

    • The name "list_characters" says "list": a word for reading.
    Description, as the server wrote it
    List the bitHuman house characters that can speak. Each has an id (pass it as `character` to make_character_video or talk_to_character), a name, a short description, a picture URL and `talk` (true when talk_to_character is open for it). No arguments and read-only; one call per conversation is enough. Only these characters can speak: real people, photos and custom voices are not supported.

    Annotations the server declares

    • title: List characters
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:25 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.bithuman.ai/mcp: tools/list returned 3 tools to an anonymous client, including make_character_video (write), talk_to_character (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools1 changed.~1 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http characters https://mcp.bithuman.ai/mcp
claude mcp add --transport http characters https://mcp.bithuman.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__characters__list_characters"
    ],
    "ask": [
      "mcp__characters__make_character_video",
      "mcp__characters__talk_to_character"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as characters. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.bithuman/characters/verify?hash=63e37631f536767275d009a6796f030192498475d7ed3925bd7f306f397553dd" | jq -e '.changed == false'

Pinned hash 63e37631f536, from Nov 11, 2026, 17:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.bithuman/characters/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.bithuman/characters
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.bithuman/characters.svg)](https://radar.anlyon.com/servers/ai.bithuman/characters)

Source: MCP Registry. Synced Oct 21, 2026, 17:41 UTC.

bitHuman MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the bitHuman MCP server safe?

No scan can promise that. What its definitions show: 3 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the bitHuman MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the bitHuman MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the bitHuman MCP server have?

3 tools: 2 write, 1 read. make_character_video, talk_to_character and list_characters.

Does the bitHuman MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the bitHuman MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the bitHuman MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 30, 2026. Every change is on this page and in its Atom feed.