Mural

Files and knowledge

Mural for AI agents. Turn a board into a clear recap.

Find murals in a user’s workspaces and read selected board content. Prepare a workshop recap grounded in the widgets returned.

About Mural

With the Mural connector, your agent reads boards in each user’s own Mural account. It can list workspaces, rooms and murals, search for a mural by name, and read the widgets on it, using only the tools your project allows.

Mural is a digital whiteboard for visual collaboration and workshops.

Tools

What your agent can do in Mural.

Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Mural connection.

  • List workspaces

    Read
    mural_list_workspaces

    Find workspaces available to the connected user.

  • List rooms

    Read
    mural_list_rooms

    Find accessible rooms in a selected workspace.

  • List murals

    Read
    mural_list_murals

    Find murals in a selected room.

  • Search murals

    Read
    mural_search_murals

    Find candidate murals by title within an accessible workspace.

  • Read a mural

    Read
    mural_get_mural

    Retrieve details of one identified mural.

  • List mural widgets

    Read
    mural_list_widgets

    Read supported widgets from a selected mural with pagination.

Control

Limits you can set.

You decide what your agent may do in Mural, and Agent200 runs every call within those limits.

  • Turn single tools on or off

    Let the agent find and read murals, and switch off mural_list_widgets if it should not read what is on a board.

  • Restrict what the agent reaches

    Choose the endpoints and scopes a project may use, for example murals but not widgets. A call outside them is refused.

Get started

Connect Mural
in three steps.

  1. 1

    Set up the SDK

    Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

    agent.js
    Conceptual example
    Set up the SDK with the Agent200 API key
    // One Agent200 API key covers every connector enabled for the project.
    const agent200 = new Agent200({
      apiKey: process.env.AGENT200_API_KEY,
    });
  2. 2

    Let your user connect Mural

    Each end user authorizes their own Mural account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

    connect.js
    Conceptual example
    Let an end user connect their account (managed OAuth)
    // Each end user authorizes their own Mural account, once.
    const connection = await agent200
      .user("user_123")
      .connect("mural");
    
    if (connection.authorizationUrl) {
      // Show this link to your user; Agent200 handles the rest.
      console.log(connection.authorizationUrl);
    }
  3. 3

    Run with the Mural tools

    Name the user, the model and the tools. The model decides which Mural tools to call, and Agent200 executes them with that user's connection.

    run.js
    Conceptual example
    Run a request with the connector's tools
    const result = await agent200
      .user("user_123")
      .run({
        model: "openai/gpt-5.6-sol",
        input: "Find the mural for our Q1 planning workshop",
        tools: ["mural"],
      });
    
    console.log(result.output);

Access

Sign-in and permissions.

  • Connect the intended Mural account

    Have the end user authorize Mural through managed OAuth. Select the workspace and room relevant to the requested board.

  • Use the needed read scopes

    Mural documents separate read scopes for workspaces, rooms and murals. The connected user must also have access to the selected resource.

  • Preserve the application user

    Use a stable authenticated application identity for connection and subsequent requests. Store the Agent200 key outside prompts and source files.

For agents

Instructions for AI agents.

Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Mural connector and how to use it.

Agent brief
Connector: Mural, through Agent200. In code: "mural".
What it does: Find murals in a user’s workspaces and read selected board content. Prepare a workshop recap grounded in the widgets returned.
Page: https://www.agent200.com/connectors/mural/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Mural's own page, through the authorization link Agent200 returns. Never ask a user for a Mural password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: mural_list_workspaces, mural_list_rooms, mural_list_murals, mural_search_murals, mural_get_mural, mural_list_widgets. Name "mural" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/mural/framework/claude/
   https://www.agent200.com/connectors/mural/framework/chatgpt/
   https://www.agent200.com/connectors/mural/framework/claude-code/
   https://www.agent200.com/connectors/mural/framework/muse/
   https://www.agent200.com/connectors/mural/framework/grok-bot/
   https://www.agent200.com/connectors/mural/framework/openai-dots/
   https://www.agent200.com/connectors/mural/framework/claude-duet/
   https://www.agent200.com/connectors/mural/framework/hermes-agent/
   https://www.agent200.com/connectors/mural/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

This page is also available as Markdown, for agents and LLMs: /connectors/mural.md

Guides

Use Mural with the AI you build on.

Step-by-step setup for Mural with a specific model, assistant or agent framework.

FAQ

Mural and Agent200, answered.

How should an agent find the right mural?

Resolve the workspace and room first, then select the returned mural ID. Similar board titles can refer to different workspaces. Mural room murals.

Does listing widgets capture the entire board?

Mural’s widget endpoint does not include drawings. Follow pagination and report which widget types and board were read. Do not describe unseen visual elements as facts. Widget reference.

Can the agent change the workshop board?

The tools listed here are read operations. A proposed next step in the recap does not create or edit a mural, room or widget.

Which scopes are needed?

Mural documents workspaces:read, rooms:read and murals:read for this discovery path. Use the permissions actually granted to the connected user. Mural scopes.

What makes a useful recap?

Identify the board, summarize only returned widget text and labels, and separate observations from suggested follow-up. Note when drawings or other unreturned content may affect the interpretation.

  • Google Drive

    Google Drive

    Find, read and organize the files in each user's Drive.

    Managed OAuth Files and knowledge
  • OneDrive

    OneDrive

    Search, read, upload and share OneDrive files, including Word, Excel and PowerPoint documents, on behalf of each of your users.

    Managed OAuth Files and knowledge
  • Dropbox

    Dropbox

    Search, read, upload and organize Dropbox files, and create shared links, on behalf of each of your users.

    Managed OAuth Files and knowledge
  • Notion

    Notion

    Search, read and write Notion pages and databases on behalf of each of your users.

    Managed OAuth Files and knowledge
200 OK

Start with Mural.
Your agent does the rest.

Your users connect their own Mural accounts. Agent200 handles the OAuth, the tokens and every tool call.

Book a demo.
See it in action.

Tell us who you are, then pick a time for a 1:1 session with an expert from our team.

We use your details only to email you about Agent200. See the Privacy Policy.

Pick a time. We'll take it from there.

A 1:1 session with an expert from our team, about what you are building.

Open in Calendly (opens in a new tab)