monday + Claude Code
Build a monday reader with Claude Code
Prepare a grounded board progress briefing
Use Claude Code to build a separate read-only monday assistant with Agent200. Ground the board progress briefing in returned source data.
On this page
Overview
Use Claude Code to implement a read-only monday reader in your application. Validate identifiers, schemas and access failures before presenting a board progress briefing.
Start with one identified board item. Preserve returned board, item, status and date fields; report missing data and keep the workflow read-only.
Provider reference: monday API.
- Connector
- monday
- Works with
- Claude Code · Coding agent, with the SDK
- Authentication
- Managed OAuth, per end user
- You need
- An Agent200 API key
- Tools
- 5 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.
- monday enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- An end user with a monday account. They approve access once, on monday's own page.
- Claude Code in your project. It writes the code with the Agent200 SDK; you review it.
Connect monday 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 monday read operations and input schemas in your runtime.
-
3
Step 3: Connect the user’s monday 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 monday account, once. const connection = await agent200 .user("user_123") .connect("monday"); 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 board progress briefing 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: "List the boards in my monday account", tools: ["monday"], }); console.log(result.output);
Test your connection
Run one request to check everything is wired up.
Ask
Read the monday board item I identify and prepare a board progress briefing. Name the source and use only board, item, status and date fields. State access gaps; do not change records.
What should come back
- The selected board item is identified.
- Only the returned board, item, status and date fields are reported.
- Access gaps and missing context are explicit; no source data is changed.
Check the selected board item ID, account scope, read permission and pagination. Column meanings are board-specific. Resolve status labels and pagination from the selected board; search is result-limited.
Get your API key
Create a key in the Agent200 dashboard. It reaches monday 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 monday to Claude Code.
Goal: connect monday to Claude Code with Agent200. Guide: https://www.agent200.com/connectors/monday/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 monday 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 monday account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on monday. 6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "monday" in the tools. The model decides when a monday tool is needed; Agent200 executes the call. 7. Check it works with this request: "Read the monday board item I identify and prepare a board progress briefing. Name the source and use only board, item, status and date fields. State access gaps; do not change records." What should come back: - The selected board item is identified. - Only the returned board, item, status and date fields 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 monday, 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/monday/framework/claude-code.md
monday tools Claude Code can call
-
List boards
Readmonday_list_boardsFind boards visible to the connected user.
-
Read a board
Readmonday_get_boardRetrieve one identified board and its fields.
-
List items
Readmonday_list_itemsFind items on an accessible board.
-
Read an item
Readmonday_get_itemRetrieve one identified item and column values.
-
Search items
Readmonday_search_itemsSearch accessible items with a scoped query.
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 monday tools.
-
02
The model picks a tool
The model decides whether a monday tool is needed, and with which arguments.
-
03
Agent200 runs the call
It uses that user's own monday 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 monday account.
Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and monday enforces what its API grants.
Troubleshooting
The source cannot be read
Check the selected board item ID, account scope, read permission and pagination. Column meanings are board-specific. Resolve status labels and pagination from the selected board; search is result-limited.
FAQ
How do I verify this result?
Compare the named board item and returned board, item, status and date fields 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.
