Linear MCP integration for AI agents.
Connect AI agents to Linear teams, issues, projects, comments, cycles, labels, and project updates through typed actions.
- ACTION CONTRACTS
- 34
- AUTHENTICATION
- OAuth 2.0 + API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Linear integration exposes
The Linear Agent App lets an agent turn verified findings into structured engineering work. It can resolve teams and issue defaults, retrieve existing issues, create a new issue with a known team and title, or update project context without navigating the Linear interface.
Issue creation should follow discovery. The agent should first check for an existing issue, resolve the correct team and project, and preserve links to the source evidence. Status changes, assignments, deletions, and project updates require stronger confirmation than read-only searches.
VERIFIED ACTION SAMPLE
Real Linear capabilities.
Showing 12 of 34 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_all_linear_teamsREADLists all Linear team basic information accessible with the current credentials.
create_attachmentWRITECreate or update an attachment for the specified Linear issue.
INPUTS: issue_id / title / url / subtitle
delete_linear_issueHIGH IMPACTDelete the specified Linear issue.
INPUTS: issue_id
create_comment_reactionWRITECreates an emoji reaction for the specified Linear comment.
INPUTS: comment_id / emoji
create_linear_commentWRITECreates a comment for the specified Linear issue.
INPUTS: issueId / body
create_linear_issueWRITECreate a new Linear issue in the specified team and support fields such as project, person in charge, status, label, etc.
INPUTS: title / team_id / cycle_id / due_date / estimate
create_linear_issue_relationWRITECreate a relationship between two Linear issues, such as blocks, related, or duplicate.
INPUTS: issue_id / related_issue_id / relation_type
create_linear_labelWRITECreates a new Linear issue label in the specified team.
INPUTS: team_id / name / color / description
create_linear_projectWRITECreate a new Linear project and associate one or more teams.
INPUTS: icon / name / color / lead_id / priority
create_project_milestoneWRITECreates a project milestone for the specified Linear project.
INPUTS: name / project_id / sort_order / description / target_date
create_project_updateWRITECreates a project progress update for the specified Linear project.
INPUTS: body / health / project_id / is_diff_hidden
get_attachmentREADRetrieve a Linear attachment based on the issue and attachment ID or file name.
INPUTS: issue_id / attachment_id / file_name
INPUT CONTRACTS
Know what the action needs before it runs.
create_attachment
issue_idREQUIRED- Linear resource ID.
titleREQUIRED- Attachment title.
urlREQUIRED- Attachment URL.
subtitleOPTIONAL- Attachment subtitle.
delete_linear_issue
issue_idREQUIRED- Linear resource ID.
create_comment_reaction
comment_idREQUIRED- Linear resource ID.
emojiREQUIRED- Emoji to add.
create_linear_comment
issueIdREQUIRED- Linear resource ID.
bodyREQUIRED- Comment text in Markdown.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Error-to-issue
Inspect a production error, search for an existing issue, then create or update the appropriate Linear record.
Release tracking
Read the release project, attach pull-request context, and prepare a status update after CI is verified.
Decision follow-through
Turn confirmed Slack decisions into assigned Linear work while preserving the source discussion link.
SAFETY BOUNDARY
Operate Linear with explicit limits
- Resolve team and project IDs rather than inferring them from names.
- Search for duplicates before creating an issue.
- Confirm owner, priority, status, and due date changes.
- Include source URLs so humans can verify the issue context.
CONNECTION MODEL
OAuth 2.0 + API key
Linear personal API key sent as the raw Authorization header value. Create or revoke it from Settings > Account > Security & Access.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 18
- WRITE SIGNALS
- 13
- HIGH IMPACT
- 3
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Linear.