Retrieve a Linear issue by ID. Default → a minimal flattened field set; full:true → a documented richer superset (assignee, lifecycle timestamps, state type, parent, estimate, dueDate).

List issues as a {issues, hasNextPage, cursor} envelope. Lean rows by default (identifier, title, state, statusType, priority, createdAt, blockedBy, labels, project{id}, projectMilestone{id}, gitBranchName); full:true adds description, url, assignee, milestone name, updatedAt per row. query is a case-insensitive title/description text search (find an existing ticket without raw graphql). Page forward by passing the returned cursor back. Filter names (state/project/label/assignee/team) resolve server-side; an unresolved name errors loudly. Narrow server-side with team and includeCompleted:false (excludes completed/canceled/duplicate) to cut row count before it reaches you.

List projects as lean rows (id, name, status{name,type}) by default; full:true adds description, dates, lead, labels, initiatives. Optional state (lifecycle string), label (project label name), and team filters; includeCompleted:false excludes completed/canceled projects server-side.

Get one project. Default → id, name, description, labels[name]; full:true adds status{name,type}, dates, lead, initiatives.

List a project's milestones (id, name). project accepts a name or id.

Get one project milestone (id, name, description).

List an issue's comments (id, body, authorName, createdAt). issue accepts an identifier (e.g. ENG-123) or id.

Create (no id) or update (id) an issue. Returns only {id, identifier, state, url} — no full-object echo. id-or-name args (state/assignee/project/milestone/labels) resolve server-side; blockedBy takes issue identifiers; create requires title + team.

Add a comment to an issue. Returns only {id, url}. issue accepts an identifier or id.

Create (no id) or update (id) a project. Returns only {id, name, url}. Create requires name + team; addInitiatives (names or ids) are attached after create.

Create (no id) or update (id) a project milestone. Returns only {id, name}. Create requires name + project (name or id).

Get one team by id, key, or name → {id, name, key}.

List teams → [{id, name, key}]. query filters by name/key substring.

Get one user by id, "me", or name → {id, name, displayName, email, active}.

List users → [{id, name, displayName, email, active}]. query filters by name/displayName/email substring.

Get one attachment → {id, title, subtitle, url, sourceType}.

Link an external URL to an issue as an attachment → {id, title, url}. issue accepts an identifier or id.

Finalize an upload: link an already-uploaded assetUrl to an issue → {id, title, url}. Call after prepare_attachment_upload + the client-side byte PUT.

Get a presigned direct-upload URL (fileUpload) → {assetUrl, uploadUrl, headers, issue}. PUT raw bytes to uploadUrl with headers verbatim (client-side), then call create_attachment_from_upload.

Get one document → {id, title, content, slugId, updatedAt, project{id}}. id accepts a document id or slug.

List documents as lean rows → [{id, title, slugId, updatedAt}] (no content).

Create (no id) or update (id) a document → {id, title, slugId}. Create requires title; project (name or id) resolves server-side.

List issue labels → [{id, name, color, isGroup}]. Optional name filter.

List project labels → [{id, name, color, isGroup}]. Optional name filter.

Create an issue label → {id, name, color}. team (name or id) scopes it to a team; omit for a workspace label.

List workflow states → [{id, name, type, color}]. Optional team (name or id) scope.

Get one workflow state → {id, name, type, color}.

List cycles → [{id, number, name, startsAt, endsAt}]. Optional team (name or id) scope.

Get one status update by id, or list a project's/initiative's updates → [{id, body, health, createdAt, url, authorName}]. type selects project vs initiative.

Create (no id) or update (id) a project/initiative status update → {id, url, health}. Create requires the matching parent (project or initiative).

Search Linear's help-center documentation. Proxied to the hosted Linear MCP (no public GraphQL backing).

Extract and fetch images from markdown content. Proxied to the hosted Linear MCP (content helper, no GraphQL backing).

Exact lookup for a Linear diff (review URL, PR URL/ID, slug, or full identifier). Proxied to the hosted Linear MCP (no public GraphQL backing).

Exact lookup for diff review threads. Proxied to the hosted Linear MCP (no public GraphQL backing).

List Linear diff pull requests. Proxied to the hosted Linear MCP (no public GraphQL backing).

Run an arbitrary GraphQL query or mutation against Linear's API (https://api.linear.app/graphql) and return the raw result. For the rare need neither the lean default nor full:true covers. Example: linear_graphql({query: "query($id:String!){ issue(id:$id){ identifier subscribers{ nodes{ name } } } }", variables: {id: "ENG-123"}}). Bearer-gated like every tool; errors surface, never swallowed.