How to connect Linear to OpenClaw

The ClawHub skill teaches OpenClaw about Linear, but the calls run through the ClawLink plugin and your connected account. Make sure Linear 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.

Reconnect Linear from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded.

Linear 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 Linear 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.

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.

Start with what the connection can see rather than with scopes. Run linear_get_current_user and linear_list_linear_teams: if the account is not a member of the team that owns the issue, reads of public data can succeed while writes fail, and the fix is team membership in Linear rather than anything in ClawLink. The second cause is a partial approval on the consent screen, which leaves a connection that reads but cannot write — reconnect from the dashboard and accept the full set. The third, which no search result covers, is a placeholder identifier: Linear ids are UUIDs, and an agent that passes an example id from documentation, or an issue key it invented rather than looked up, gets a permission-shaped error rather than a clean not-found.

Ask the agent to diagnose it:

Call linear_get_current_user and linear_list_linear_teams, and tell me exactly which account is connected and which teams it belongs to. Do not retry the failed call yet.

Two causes. First, team scope: linear_list_issues_by_team_id needs a real team id, and linear_search_issues only reaches what the connected account can see, so an issue in a private team the account is not in is genuinely invisible. Second, identifier confusion: humans refer to issues as ENG-123, but the tools address them by id, so an agent that passes the human key where an id belongs finds nothing. Ask it to search by text first with linear_search_issues and use the id from the result for anything that follows.

Ask the agent to diagnose it:

Use linear_search_issues for a distinctive word from the title and show me the full result including ids. Then tell me which team each match belongs to.

Linear workflow states are defined per team, so "Done" on one team may be "Shipped" or "Completed" on another, and an update that names a state the team does not have fails rather than being mapped to the nearest thing. Have the agent list the real states with linear_list_linear_states for that team before it updates anything, and use the state id from that list. The same applies to labels: linear_list_linear_labels returns what actually exists, and linear_create_linear_label is what you want only if you genuinely intend to add a new one to the workspace.

Ask the agent to diagnose it:

Run linear_list_linear_states for the team that owns this issue and show me every available state with its id. Then tell me which one you were trying to set.

Try reconnecting Linear and complete the consent flow in the same browser session. Partial OAuth approvals or switching accounts mid-flow can leave the connection incomplete.

Yes. ClawLink is the fastest way to connect OpenClaw to Linear: link your Linear account once in the browser and OpenClaw can call the Linear API through 32 ready-made tools — no custom code or token handling.

Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Linear skill from ClawHub, then you click Connect in the dashboard to authorize Linear. OpenClaw calls the tools from the next message — no config files or API keys to manage.

About two minutes. Sign in, click Connect next to Linear in the dashboard, authenticate, and OpenClaw can use it from the next chat message.

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 Linear working from chat.

Linear's remote MCP server is a good product and it is the right answer if Linear is the only thing your agent needs to touch. The difference is scope. It exposes Linear to a client that speaks MCP; this connection puts Linear alongside every other integration you have connected in the same dashboard, with one pairing step for the agent and one place to revoke access. The workflows that benefit are the cross-product ones — turning a Slack thread into an issue, or attaching a deployment to the ticket that caused it — because the agent already holds all of those connections rather than one server per tool.

Neither. You approve the connection on Linear's own consent screen and the credential lives on the ClawLink server, so there is no personal API key to generate in Linear's settings and no OAuth application to register. Your Linear permissions are unchanged: the agent sees the teams and projects your account can see, and Linear's own workspace rules apply on every call.

Both. It can create issues, comments, labels, projects, project milestones, project updates, attachments, and issue relations, and it can update issues, comments, and projects. The read side covers issues, projects, cycles, teams, users, states, labels, and search. The practical caution is on the write side: Linear issues are visible to your team immediately, so ask the agent to show you what it intends to create before it creates it, particularly for anything that notifies people.

Name the team, and have the agent resolve it rather than guess. Linear scopes issues to teams, and almost everything else — cycles, states, labels — is scoped by team too, so an agent that picks a team implicitly will also pick that team's workflow states. Ask it to run linear_list_linear_teams first and confirm the team id it is going to use. linear_get_issue_defaults is the other useful step, because it reports what a new issue on that team will default to before anything is created.

The ClawHub skill teaches OpenClaw about Linear, but the calls run through the ClawLink plugin and your connected account. Make sure Linear 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.