How to connect Monday to OpenClaw
Connect Monday to OpenClaw with ClawLink in one click — 121 tools your AI agent can call from chat via hosted OAuth. No API keys, no manual setup.
MondayOAUTH2MCPPlan, track, and deliver team projects. Once connected, OpenClaw can read and act on Monday from chat — pairing, token refresh, and tool wiring handled for you.
The usual route to Monday access for OpenClaw is an MCP server you configure and keep running, plus your own OAuth app or API keys. ClawLink gives OpenClaw a more practical Monday setup: install one ClawHub skill, connect Monday in the browser, and OpenClaw can call real Monday actions from any chat surface with no auth, token refresh, or tool wiring to build yourself.
Copy this prompt into OpenClaw, or open the Monday skill on ClawHub.
Before installing anything, inspect the ClawHub skill metadata and setup requirements.
If the skill asks you to install a third-party package or CLI, verify its source, maintainer, and package contents before running the install command.
Install the skill "Monday" (hith3sh/monday-workflows) from ClawHub only after those checks pass.
Skill page: https://clawhub.ai/hith3sh/monday-workflows
Keep the work scoped to this skill only.
After install, help me finish setup from verified skill metadata.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.Setup
It takes three steps to connect OpenClaw to Monday.
1Install the plugin
Paste the setup prompt into OpenClaw, or install from the terminal and ask OpenClaw to pair:
openclaw plugins install clawhub:clawlink-plugin- 2
Connect Monday
One-click OAuth in the dashboard.
- 3
Use it from chat
Ask OpenClaw: "What can you do with Monday?"
Install by command
The setup prompt above does all of this in one paste. By hand, it is one install command plus a browser approval:
openclaw plugins install clawhub:clawlink-pluginThen ask OpenClaw to set up ClawLink. It starts browser pairing and prints an approval link — open it, approve the device, return to the chat, and say done. Finally, connect Monday in the ClawLink dashboard — a one-click OAuth approval, no API keys.
Verify the connection by asking OpenClaw:
Use monday_boards to list the boards I can see, then monday_get_items on the one I pick to show its items, groups, and current statuses. Do not walk every board yet.
Using a different agent?
The OpenClaw plugin is one client of ClawLink's MCP server. Claude Code, Cursor, Codex, or any agent that can run a shell command pairs with the same ClawLink account through the CLI:
npx -y @useclawlink/cli loginlogin opens the same browser approval and stores a credential locally. Once Monday is connected in the dashboard, that agent calls the same 121 Monday tools over MCP. Full setup for MCP clients and shell agents: connect apps to any AI agent.
Monday MCP for OpenClaw
Looking for a Monday MCP server for OpenClaw? ClawLink connects Monday to OpenClaw and exposes 121 Monday tools your agent can call over MCP, with hosted auth and nothing to run or maintain yourself. Using Hermes instead? The Hermes Monday integration works the same way.
The walkthrough the answer engines hand out for this query starts at monday's Developers page: create a personal access token, save it somewhere secure, then wire it into an agent skill. The token step is the whole reason this page exists, and the hosted route removes it: you install one skill, connect Monday in the dashboard, and approve what monday shows on its own consent screen. The same split applies to monday's own answer to "no API keys": its native agents and Agent Factory genuinely need no token, but they live inside monday, managed by monday. This page is the other route: your OpenClaw agent acts on your monday account through a hosted OAuth connection, with 121 tools callable from chat and no token anywhere on your machine.
What the OpenClaw Monday integration can do
121 Monday tools are ready for OpenClaw once the account is connected. The 30 below are the ones people reach for most; your agent can call all 121.
30 of 121 Monday tools for OpenClaw
| Tool | What it does |
|---|---|
Add users to board monday_add_users_to_board | Add users to a Monday board with a specified role |
Add users to team monday_add_users_to_team | Add users to a Monday team |
Archive board monday_archive_board | Archive a Monday board |
Archive item monday_archive_item | Archive a Monday item |
Create board monday_create_board | Create a new Monday board |
Create item monday_create_item | Create a new item on a Monday board |
Create update monday_create_update | Create an update on a Monday item |
Account trigger statistics monday_account_trigger_statistics | Retrieve statistics about account-level triggers and automations |
Aggregate data monday_aggregate_data | Aggregate data across Monday.com boards using groupings and aggregation functions like COUNT |
App subscription monday_app_subscription | Retrieve current app subscription data for the account |
Audit logs monday_audit_logs | Retrieve detailed security-related activity records for a Monday.com account |
Blocks monday_blocks | Retrieve document block data from workdocs via the API |
Boards monday_boards | Retrieve board data via the Monday.com API |
Columns monday_columns | Retrieve column metadata from boards via the GraphQL API |
Connection board IDS monday_connection_board_ids | Retrieve board IDs associated with connection columns |
Connections monday_connections | Retrieve connection data for integrations with external services |
Custom activity monday_custom_activity | Retrieve custom activity data from the Emails & Activities app |
Docs monday_docs | Retrieve Monday.com document data via the API |
Get account info monday_get_account_info | Retrieve account metadata and settings for the authenticated Monday.com account |
Get activity logs monday_get_activity_logs | Retrieve activity logs from a specific Monday.com board |
Get API version monday_get_api_version | Retrieve the Monday.com API version in use |
Get assets monday_get_assets | Retrieve file/asset metadata from monday.com by asset IDs |
Get board views monday_get_board_views | Retrieve board view data via GraphQL API |
Get favorites monday_get_favorites | Retrieve all favorited items for the authenticated user |
Get folders monday_get_folders | Retrieve folder data from workspaces with filtering and pagination options |
Get form monday_get_form | Retrieve form metadata via the API using the form's unique token from the URL |
Get items monday_get_items | Retrieve specific items by their IDs from Monday.com, returning metadata including name |
Get me monday_get_me | Fetch the current authenticated user's profile and permissions |
Get mutation complexity monday_get_mutation_complexity | Get complexity data of mutations in Monday.com |
Get query complexity monday_get_query_complexity | Retrieve complexity data and cost metrics for Monday.com API operations |
Try it: find the Monday tool you need
Browse the 30 Monday tools
Click any tool to see exactly what OpenClaw can do and copy a ready-to-use prompt.
Example prompts
Use monday_boards to list the boards I can see, then monday_get_items on the one I pick to show its items, groups, and current statuses. Do not walk every board yet.
Create an item on the board <board id> with monday_create_item, name it "Q3 review", and set its group and status. Show me the arguments before you send them, since this lands in a board other people see.
Post an update on the item <item id> with monday_create_update summarizing the status below. Keep it under 200 words and show me the text before sending.
Add the user <email> to board <board id> with monday_add_users_to_board. Confirm the board id with monday_boards first, and tell me what access the user will get.
How the Monday tools behave
Details that decide whether a Monday prompt is a fast answer or a slow crawl through a big workspace.
- Boards are the root object. Most reads start with
monday_boardsto get board ids, and every board-level call takes the id, never the name. An id from documentation fails like a typo. - Items live inside boards and groups.
monday_get_itemsreturns items with their group, column values, and statuses; the item id is the key for updates and item-level tools. - Writes are visible to a team. Creating an item, posting an update, and adding users land in a workspace other people are working in. A confirmation step in the prompt is the habit that keeps a board clean.
- Account-level tools exist. Audit logs, app subscription, and account statistics are readable, so access questions can be answered from the tool catalog rather than the monday UI.
- Users and teams are first-class objects. Adding users to boards and teams changes real access, and the tools take email addresses or user ids, so confirm which one you are passing.
ClawLink vs. building it yourself
The alternative to ClawLink is usually manual OAuth app setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Monday working from chat.
| Manual | ClawLink | |
|---|---|---|
| Connection flow | Register a Monday app, configure redirect URLs, manage consent details, and reconnect users when auth settings drift. | Users connect Monday through the hosted browser flow and ClawLink keeps the token lifecycle out of your app code. |
| Ongoing maintenance | You own refresh logic, permission debugging, environment config, and every provider-specific edge case for Monday. | ClawLink handles the repetitive integration plumbing so your team can focus on the workflow instead of the infrastructure. |
| Agent usability | You still need to expose the right Monday actions to the runtime in a format your agent can reliably use. | 121 tools for Monday are already exposed through ClawLink, so the agent can read and act from chat immediately. |
ClawLink vs. Composio
Composio also exposes Monday to AI agents. It is developer infrastructure: Python and TypeScript SDKs, an MCP server, and a catalog past 1,000 apps, aimed at teams shipping agent products. ClawLink is built for OpenClaw users instead. You install the plugin once, connect Monday in the browser, and the 121 tools above work from chat. There is no SDK, no config file, and no API key handling. Choosing between them? Read the full Composio alternatives comparison.
Troubleshooting
OpenClaw installed the Monday skill but can't call the tools
The ClawHub skill teaches OpenClaw about Monday, but the calls run through the ClawLink plugin and your connected account. Make sure Monday is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register.
Connection succeeds but no tools appear
Reconnect Monday from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded.
"Tool schema not loaded yet" error when calling Monday tools
Monday tool schemas load on demand the first time a tool runs and are cached after that, so this error usually clears on its own: wait a few seconds and retry the same request. If every Monday call keeps failing with it in a fresh chat, reconnect from the dashboard, and contact support if it still persists — that pattern points to a configuration problem on our side, not something you can fix by reconnecting again.
Monday returns 403 or "permission denied" on one action while others work
Two usual causes. The connected account may not have access to the specific workspace, inbox, store, or project in the request — check that first. If access looks right, the agent may have sent a placeholder value (like "YOUR_ID" or an example id from documentation) instead of a real one: ask it to run a list or search tool first, then retry the action with a real id from those results. Most failures at this stage are one of these two, not ClawLink bugs.
Monday returns 403 or "insufficient permissions" although the account shows as connected
The causes the search engines teach for this error are the ones to check in order: the board is private and the connected account is not a member, the OAuth grant lacks a scope the action needs, or the user's role in the workspace does not permit the operation. A personal token mirrors its user's permissions, and so does a hosted connection, so the connected account's membership and role decide everything. Start by asking the agent to list what it can see: clawlink_list_tools --integration monday, then read the board structure with a get tool and confirm the failing id is a real one rather than a placeholder from documentation. If access genuinely changed, reconnecting from the dashboard re-runs the consent flow and refreshes the grant.
Ask the agent to diagnose it:
Run clawlink_list_tools --integration monday, then list the boards the connected account can see. Quote the exact 403 error text and tell me which board or item id it names. Do not retry the failing call until I confirm the id is real.Monday tools fail with an auth error after a scope or account change, while the dashboard still says connected
This is the stale-grant case: the connection is intact, but monday's side has changed what it is allowed to do, for example a workspace admin removed a permission, the account was reorganized, or the grant was revoked on monday's side. The dashboard showing "connected" describes the session, not the grant's current reach, so the fix is to refresh the grant: disconnect and reconnect Monday from the ClawLink dashboard, which re-runs monday's consent screen, then start a fresh chat so OpenClaw reloads the tool catalog. If the error persists after a fresh reconnect, the limit is on monday's side of the account, not the connection.
Ask the agent to diagnose it:
Do not retry yet. First run clawlink_list_integrations and confirm Monday's status, then quote the exact error from the last call. If the error is an auth or token error, I will reconnect from the dashboard and you will retry in a fresh chat.Monday returns a rate-limit error while the agent enumerates a workspace
monday moved to complexity-based rate limits: the cost of a call is measured by the work it asks for, and plan limits are documented per plan rather than a flat per-minute number. An agent walking a large workspace, board by board and item by item, is exactly the traffic shape that meets the limit. The response is not to retry faster, which counts against the same bucket, but to change the shape of the work: one board at a time, a single aggregate call instead of a loop, and a pause between calls. If a bulk audit is genuinely needed, running it in stages across a few turns beats one sweep.
Ask the agent to diagnose it:
Tell me what you were enumerating when the rate-limit error hit and quote the error text. Switch to one board at a time with a short pause between calls and tell me how many calls remain.Monday tools are missing, or a single tool name is not found
Two different failures. If no monday tools appear at all, the connection or pairing is incomplete: confirm the skill is installed and Monday shows as connected, run clawlink_list_integrations, then start a fresh chat. If most tools work and one name fails, the name is wrong rather than missing: the error lists the closest real tools, and clawlink_list_tools --integration monday shows the exact catalog. There is also a first-call timing case unique to this setup: schemas load on demand, so the opening Monday call in a fresh session can arrive before the catalog and needs one retry. What does not apply is the advice for this symptom that assumes a local MCP server declared in a client config, which is what the search results teach.
Ask the agent to diagnose it:
List the Monday tools you actually have access to. If there are none, run clawlink_list_integrations and tell me what it returns. If there are, tell me which one reads a board and use that exact name.OAuth finished in the browser but the account is still missing
Try reconnecting Monday and complete the consent flow in the same browser session. Partial OAuth approvals or switching accounts mid-flow can leave the connection incomplete.
FAQ
Is there a OpenClaw Monday integration?
Yes. ClawLink is the fastest way to connect OpenClaw to Monday: link your Monday account once in the browser and OpenClaw can call the Monday API through 121 ready-made tools — no custom code or token handling.
How do I add Monday to OpenClaw with ClawLink?
Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Monday skill from ClawHub, then you click Connect in the dashboard to authorize Monday. OpenClaw calls the tools from the next message — no config files or API keys to manage.
How long does it take to connect Monday to OpenClaw?
About two minutes. Sign in, click Connect next to Monday in the dashboard, authenticate, and OpenClaw can use it from the next chat message.
Why use ClawLink instead of wiring Monday up myself?
The alternative to ClawLink is usually manual OAuth app setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Monday working from chat.
Does this need a monday personal access token?
No. The flow most search results teach starts at monday.com/developers, where you generate a personal access token and paste it into an environment file or a skill config. Here the authorization happens in the browser: monday shows its consent screen, you approve, and the connection is stored server-side. A token you generate yourself mirrors your user's permissions, and so does the connected account, but the token itself never exists on your machine and can be revoked in one place from the ClawLink dashboard.
How is this different from monday's own AI agents or Agent Factory?
monday's native agents and Agent Factory are monday's product: they work inside monday, built and managed on monday's side, and they are the no-token answer monday's own pages give. This page is about OpenClaw acting on your monday data instead. The connection is the monday account you already have, exposed to OpenClaw through hosted OAuth, so your agent can read and write boards, items, updates, and users from any chat surface without monday-native agents being involved at all.
How do I check which monday tools OpenClaw can actually call?
Ask OpenClaw to run clawlink_list_integrations to confirm Monday shows as connected, then clawlink_list_tools --integration monday to see the live tool catalog with each tool's input schema. This is the diagnostic script ChatGPT already teaches for permission errors on this provider, and it is the first thing to run when a tool name you expected is missing or an argument fails.
What can the agent do in Monday, and what should I gate?
The 121 tools cover the board surface end to end: boards and their views, items, updates, groups, users, teams, and account-level reads like audit logs and aggregate data. Creating items and updates are the writes to be deliberate about, because they land in a board other people are working in; adding or removing users changes access for real people. Reads come first, and a confirmation step before writes is the habit that keeps a board clean.
OpenClaw installed the Monday skill but can't call the tools
The ClawHub skill teaches OpenClaw about Monday, but the calls run through the ClawLink plugin and your connected account. Make sure Monday is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register.
