Mural + Claude Code
Build a Mural reader with Claude Code
Prepare a grounded workshop recap
Use Claude Code to build a separate read-only Mural assistant with Agent200. Ground the workshop recap in returned source data.
On this page
Overview
Use Claude Code to implement a read-only Mural reader in your application. Validate identifiers, schemas and access failures before presenting a workshop recap.
Start with one identified mural. Preserve returned workspace, room, mural identity and returned widget content; report missing data and keep the workflow read-only.
Provider reference: Mural API.
- Connector
- Mural
- Works with
- Claude Code · Coding agent, with the SDK
- Authentication
- Managed OAuth, per end user
- You need
- An Agent200 API key
- Tools
- 6 tools
- Model in examples
openai/gpt-5.6-sol
Before you start
- An Agent200 API key. Create one on the API keys page of the dashboard.
- Mural enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- An end user with a Mural account. They approve access once, on Mural's own page.
- Claude Code in your project. It writes the code with the Agent200 SDK; you review it.
Connect Mural to Claude Code
-
1
Step 1: Create your Agent200 API key
Create a key on the API keys page and store it securely.
.envConceptual exampleStore the Agent200 API key as an environment variable # Keep the key out of your code, prompts and chats. export AGENT200_API_KEY="paste-your-key-here" -
2
Step 2: Inspect the real tool definitions
Confirm the actual Mural read operations and input schemas in your runtime.
-
3
Step 3: Connect the user’s Mural account
Preserve the same stable user identity during authorization and later requests.
connect.jsConceptual exampleLet 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); } -
4
Step 4: Build and test the read-only answer
Prepare the workshop recap only from returned source data. The code example illustrates a sequence, not an SDK installation contract.
run.jsConceptual exampleRun 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);
Test your connection
Run one request to check everything is wired up.
Ask
Read the Mural board I identify in its workspace and room. Summarize the returned widgets into themes and open questions. Name the board and disclose any content types not returned. Do not change the mural.
What should come back
- The selected mural is identified.
- Only returned workspace, room, mural identity and returned widget content are reported.
- Access gaps and missing context are explicit; no source data is changed.
Check workspace, room and mural IDs, connected-user access, read scopes and pagination. Do not infer a blank board from an incomplete response.
Get your API key
Create a key in the Agent200 dashboard. It reaches Mural and every other connector enabled for your project.
Instructions for AI agents
Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect Mural to Claude Code.
Goal: connect Mural to Claude Code with Agent200. Guide: https://www.agent200.com/connectors/mural/framework/claude-code/ 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. Make sure Mural is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs. 3. Add the Agent200 SDK to the project and create a client with that key. 4. Give every request a stable id for the end user. Agent200 uses only that user's own connections. 5. Connect the user's Mural account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on Mural. 6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "mural" in the tools. The model decides when a Mural tool is needed; Agent200 executes the call. 7. Check it works with this request: "Read the Mural board I identify in its workspace and room. Summarize the returned widgets into themes and open questions. Name the board and disclose any content types not returned. Do not change the mural." What should come back: - The selected mural is identified. - Only returned workspace, room, mural identity and returned widget content are reported. - Access gaps and missing context are explicit; no source data is changed. 8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in Mural, then retry. The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
The whole guide is also available as Markdown, for agents and LLMs: /connectors/mural/framework/claude-code.md
Mural tools Claude Code can call
-
List workspaces
Readmural_list_workspacesFind workspaces available to the connected user.
-
List rooms
Readmural_list_roomsFind accessible rooms in a selected workspace.
-
List murals
Readmural_list_muralsFind murals in a selected room.
-
Search murals
Readmural_search_muralsFind candidate murals by title within an accessible workspace.
-
Read a mural
Readmural_get_muralRetrieve details of one identified mural.
-
List mural widgets
Readmural_list_widgetsRead supported widgets from a selected mural with pagination.
No tool matches that search.
How it works
-
01
Your app sends the request
It calls Agent200 with the model, instructions, the input, the end user's id and the Mural tools.
-
02
The model picks a tool
The model decides whether a Mural tool is needed, and with which arguments.
-
03
Agent200 runs the call
It uses that user's own Mural connection, within the endpoints and scopes your project allows, and returns the result to the model.
-
04
Your app gets the result
Agent200 returns the completed result. Your app decides when the agent runs and what happens next.
Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's Mural account.
Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and Mural enforces what its API grants.
Troubleshooting
The source cannot be read
Check workspace, room and mural IDs, connected-user access, read scopes and pagination. Do not infer a blank board from an incomplete response.
FAQ
How do I verify this result?
Compare the named mural and returned workspace, room, mural identity and returned widget content with the source. Treat missing information as missing, not as a fact.
Is this a native product integration?
This describes a separate application built with Agent200 and Claude Code; it does not install a connector into the Claude Code app.
