Skip to content
MCP server

Manyagi

Discover Manyagi story worlds and prepare briefs and licensing steps, read-only

Install
Platforms
API, Web
Runs
Remotely
Version
0.2.0
Listing updated
5 days ago

Similar MCP servers

About Manyagi

Manyagi is an MCP server for design and media. It runs as a hosted remote server, so there is nothing to install locally.

Manyagi is a rights-aware storytelling platform, and the registry entry describes this server as covering discovery, summaries and licensing preparation with no writes or charges. A recurring theme in the developer pages is that discovery is not a licence: public catalogue responses always carry license_granted set to false, and a visible world gives no right to adapt it.

The public discovery API needs no account and returns title, slug, logline, genre, book type and status, with paging by offset. Turning an idea into a reviewable story-development brief is a separate call that requires a Manyagi product-session token; it returns review copy only, does not generate prose or chapters, does not save a draft and does not publish or charge. SDKs exist for TypeScript and Python.

Access for outside agents is limited. The developer page says external OAuth for Cursor, ChatGPT and other agents is closed, and the authorize route returns not enabled, so a correct mcp.json cannot complete a customer connection today. The page lists the scopes planned for that flow: public discovery, brief preparation and licensing preparation.

Install

Run in a terminal

claude mcp add --transport http manyagi https://manyagi.com/mcp

Add to Settings → Connectors → Add custom connector

https://manyagi.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "manyagi": {
      "url": "https://manyagi.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "manyagi": {
      "type": "http",
      "url": "https://manyagi.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "manyagi": {
      "serverUrl": "https://manyagi.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "manyagi": {
      "type": "http",
      "url": "https://manyagi.com/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

What it does

Public world discovery
Searches the public catalogue of story worlds without an account.
Licence flag
Every discovery result reports license_granted as false.
Idea to brief
Turns an idea into a reviewable development brief using a product session.
No writes or charges
The brief step saves nothing, publishes nothing and charges nothing.
SDKs
TypeScript and Python clients wrap the HTTP endpoints.
Paged results
Responses include a next_offset for reading further pages.

Good for

  • Search a catalogue of picture-book and story worlds by keyword
  • Draft a story-development brief from a one-line idea
  • Check what licensing steps are needed before adapting a world
  • Build an app that lists public story worlds
  • Review brief copy before moving to the studio product

Pricing

Pricing unknown

Public discovery needs no account; pricing for paid jobs not published

Prices change. Check manyagi.com before you buy.

Manyagi FAQ

Can I connect Cursor or ChatGPT today?

Not yet. The developer page says external OAuth grants are closed.

Does discovery give me rights to a story?

No. The responses always return license_granted false.

Do I need an account for public discovery?

No account or key is needed for the public read.

Does the brief step write a story?

No. It returns review copy only and does not generate chapters or save a draft.

How do I add Manyagi to Claude Code?

Run this command in your terminal: claude mcp add --transport http manyagi https://manyagi.com/mcp

What are the best alternatives to Manyagi?

The closest alternatives to Manyagi are HyperFrames by HeyGen, next-ai-draw-io, mcp-for-blender, ffmpeg-skill and cursor-talk-to-figma-mcp.

Where this comes from

  • Description: written from the project's README and the project's website.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers