Skip to content
Manus logo

Manus MCP server

Which MCP servers are Manus'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 2026-10-08

← Back to Manus

Whose server it is
  • Addresshttps://mcp.manus.im/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on manus.im when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools7
  • Server calls itselfmanus-chatgpt-app
  • Server version1.1.0
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 113 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: research a topic and compile a report; build a website or slide deck from a request.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "research a topic and compile a report", the likely first call is initiate_research.
  • For "build a website or slide deck from a request", the likely first call is initiate_website.

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.

Measured dailydaily checks: 1, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer245 ms
  • Space in an agent's context≈ 2,880 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results7 of 7 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · research a topic and compile a report
  • can do · build a website or slide deck from a request
  • not sure · run multi-step web tasks without supervision

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 →

Tools it offers7 tools · read 2026-10-26
  • initiate_slides

    Use this when the user wants to generate a slide presentation/deck/PPT/PPTX. Starts an asynchronous slide-generation task in Manus and immediately returns a task reference (task_id, task_url). The widget refreshes progress automatically…

  • initiate_website

    Use this when the user wants to build a website (landing page, marketing site, web app, dashboard, etc.). Starts an asynchronous website task in Manus and immediately returns a task reference (task_id, task_url). The widget refreshes…

  • initiate_mobile_app

    Use this when the user wants to build a native iOS/Android mobile app. Starts an asynchronous mobile-app task in Manus and immediately returns a task reference (task_id, task_url). The widget refreshes progress automatically; do not poll…

  • initiate_video

    Use this when the user wants to generate a video. Starts an asynchronous video-generation task in Manus and immediately returns a task reference (task_id, task_url). The widget refreshes progress automatically; do not poll or call…

  • initiate_research

    Use this when the user wants to conduct comprehensive, in-depth research on a topic. Starts an asynchronous Deep Research (aka Wide Research) task in Manus and immediately returns a task reference (task_id, task_url). The widget refreshes…

  • get_status

    Widget-only status refresh for a Manus task. Returns status, progress metadata, task details, and failure information.

  • log

    Internal tool for logging errors, warnings, and informational messages from the ChatGPT client. Used by the widget to report frontend issues to the server for monitoring and debugging.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "manus": {
      "type": "http",
      "url": "https://mcp.manus.im/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http manus https://mcp.manus.im/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.manus.im/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.