Linear MCP. Control your issues, sprints, and projects via chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Linear lets your AI client read, write, and manage issues directly inside Linear—no tab switching needed. You can list all teams, search for specific bugs, create new tasks with defined priorities, or add comments right from your IDE.
It gives your agent full control over project metadata, allowing you to check sprint progress, view project scope, and audit issue status using natural conversation.
What your AI agents can do
Create comment
Adds a formatted comment, including mentions and strikethrough text, to an existing Linear issue.
Create issue
Creates a brand new Linear task, requiring a team ID and title, with optional fields like priority and assignee.
Get issue
Retrieves the full details of any specific issue using its unique UUID or readable identifier (e.g., TEAM-123).
You can search for existing bugs or features using search_issues, get full details on a single issue ID with get_issue, or create new ones entirely with create_issue.
Modify an issue's state, assignee, or priority using the dedicated update_issue tool. You must provide the specific issue ID for this to work.
List all active sprint cycles (list_cycles) and get their current completion percentage, giving you a clear view of team velocity.
Find out what teams exist (list_teams), which projects group issues across multiple departments (list_projects), or check the user credentials linked to your API key using get_viewer.
Use create_comment to add formatted notes directly to an issue, keeping team context without leaving your current chat window.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Linear: 12 Tools for Issue Tracking
Use these tools to list, read, write, and manage all data points in Linear—from individual issue statuses to entire project cycles.
019d8453create comment
Adds a formatted comment, including mentions and strikethrough text, to an existing Linear issue.
019d8453create issue
Creates a brand new Linear task, requiring a team ID and title, with optional fields like priority and assignee.
019d8453get issue
Retrieves the full details of any specific issue using its unique UUID or readable identifier (e.g., TEAM-123).
019d8453get project
Fetches all data for a single, defined Linear project by ID.
019d8453get viewer
Checks and returns the user profile details associated with your current API access token.
019d8453list cycles
Lists all sprint cycles for a team, providing the start date, end date, and completion percentage.
019d8453list issues
Retrieves a list of issues, optionally filtering results to show only tasks belonging to one specific team.
019d8453list labels
Lists all issue labels available across your workspace, including their name and color.
019d8453list projects
Fetches a list of all projects in the Linear workspace. You can limit the number of results returned.
019d8453list teams
Lists every team in your organization, providing their unique ID and name for later use when querying issues or cycles.
019d8453search issues
Searches all Linear issues by text query. You can optionally limit the search to a specific team and get priority/assignee info.
019d8453update issue
Modifies an existing issue using its ID, allowing you to change only the fields you specify (e.g., status or assignee).
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Linear, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're talking to your agent, not logging into Linear. This server gives your AI client full control over project metadata—you can check sprint progress, view project scope, and audit issue status just by chatting with it. You don't have to switch tabs or open the app; your agent handles all the heavy lifting.
Project Discovery & Context
Need to know what teams you even got? Use list_teams to pull a list of every team in the organization, grabbing their unique ID and name. Want to see what projects are running across departments? Run list_projects for all available project containers; it'll let you limit how many results come back.
If you need the deep details on one specific project, use get_project with a project ID.
Your agent knows who you are when you connect; run get_viewer to check and return your current user profile data associated with the API key. This gives you immediate context about the credentials running the show.
Finding Issues & Scope
Need to find a bug or feature? You can search all Linear issues using search_issues. You'll get results back that include priority and assignee info, and you can even narrow that down by team. If you know the exact issue ID—like TEAM-123—you use get_issue to retrieve every single detail on it.
Want a quick overview of all open tickets for a specific group? Run list_issues, which lets you filter results to show only tasks belonging to one particular team.
Before creating anything, check out the available tags by running list_labels. This gives you a list of every label used in your workspace and their corresponding color codes. For full visibility into project structure, you can use list_teams to get all teams, and then follow up with get_issue or search_issues for specific work.
Making Changes & Tracking Progress
When it's time to act, your agent takes over. To start a new task, you use create_issue, providing the necessary team ID and title; you can even assign priority or set an assignee right out of the gate. If something changes on an existing bug—say, the status shifts or someone else gets assigned—you just hit up update_issue with the issue's ID to change whatever fields are needed.
Need to leave a note? Use create_comment. You can drop a formatted comment directly onto any issue, including mentions and strikethrough text, keeping all the team context right where you are. For tracking velocity, run list_cycles to get a list of every sprint cycle for a team, which provides the start date, end date, and its current completion percentage.
The Bottom Line
You just tell your agent what you need—whether it's listing all teams with list_teams, checking on progress using list_cycles, or making an update with update_issue—and it handles the API calls. It keeps you in the chat window, letting you manage everything without ever leaving your current IDE.
How Linear MCP Works
- 1 Subscribe to this server and provide your Linear Personal API Key.
- 2 Tell your AI client what you need—for example: 'What's the progress on the Mobile team sprint?'
- 3 The agent executes
list_cyclesorsearch_issues, retrieves the data, and gives you a clean summary.
The bottom line is: your AI client talks to Linear using structured tools, so you get answers without clicking through dashboards.
Who Is Linear MCP For?
Engineering Managers who are tired of opening the Linear app just to audit sprint health. Product Owners needing a quick way to understand feature scope across multiple projects. Developers who want to create, update, and comment on bugs without leaving their IDE.
Checks cycle progress using list_cycles or audits sprint health by running a search across all teams.
Adds comments to issues via create_comment and updates task statuses directly from their coding environment.
Searches across multiple teams using search_issues to understand the full scope of a feature or identify blockers.
What Changes When You Connect
- Check sprint health instantly. Instead of opening Linear to review a team's progress, just ask for it using
list_cycles. You get the start/end dates and current completion percentage in one prompt. - Audit entire feature scopes. To see all related bugs across multiple departments, use
search_issuescombined withlist_teams, giving you visibility without navigating through project folders. - Keep context within your IDE. When reviewing a bug, running
create_commentlets you add notes or ask questions directly to the issue thread via chat, skipping the tab switch. - Know who owns what. Need to find an assignee? Run
search_issues, and the output shows the current assignee right away. No manual lookup required. - Manage tasks with precision. When a bug is fixed, use
update_issueto change its status or assign it to QA—all in one go. You only provide the ID and what needs changing.
Real-World Use Cases
The PM needs an immediate scope audit.
A Product Manager needs to understand if a new feature is blocked. They run list_projects to get all active projects, then use search_issues across those project IDs with keywords like 'Auth' or 'V2'. The agent returns a list of relevant issues and their current priority, showing exactly where the roadblocks are.
The Dev needs to update status mid-flow.
A developer finishes a bug fix. Instead of navigating back to Linear, they use update_issue with the issue's ID and specify 'Status: Ready for Review'. They then run create_comment saying 'Fix pushed to staging; ready for QA review', closing the loop without leaving their coding window.
The Manager needs a quick cycle check.
It's Monday morning, and the Engineering Manager needs to know if the Mobile team is falling behind. They run list_cycles for that team. The agent immediately reports the active sprint number, the date range, and the current completion percentage (e.g., 62%), allowing them to call a meeting before issues pile up.
The Planner needs to structure new work.
A Product Owner has gathered requirements for next quarter's goals. They run create_issue, providing the required team ID, title, and setting the priority to 'High', ensuring the issue is logged correctly from day one with proper metadata.
The Tradeoffs
Searching without context
Asking, 'Show me all issues about payments.' The agent might return too many irrelevant results because it doesn't know which team the issue belongs to.
→
Always narrow your scope. Use search_issues and provide a specific Team ID or Project ID filter in the prompt. Or, first run list_teams to find the exact key you need.
Trying to change everything at once
Prompting: 'Make this issue high priority and assign it to Bob.' If you don't provide the UUID for the issue, the agent can't tell what you mean.
→
You must first use get_issue or search_issues to get the precise Issue ID (UUID). Then pass that specific ID into update_issue, listing only the fields you want to change.
Assuming all data is visible
Asking for a 'report on Q3 performance' without specifying which teams or projects are included. The tool can’t guess your company structure.
→
Start by calling list_teams and/or list_projects. Then, build your query step-by-step: 'Filter the issues from Project X in Team Y.'
When It Fits, When It Doesn't
Use this server if you are managing structured work within Linear—specifically tasks, sprints, or projects. If your goal is to get general company knowledge, pull meeting minutes, or write code that doesn't reference a specific bug ID, don't use it. For example, if you just need to know who the current user is, run get_viewer. But if you want to find out how many issues are open, running list_issues will give you that data structure. Never assume all tools are needed; for simple status checks, stick to search_issues; only use update_issue when you know the exact UUID and the specific field you must change.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Linear. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Checking issue status shouldn't require jumping between five different tabs.
Today, checking on a single bug requires juggling multiple browser windows. You open Linear to check the main dashboard, switch tabs to verify the assignee, then open another tab just for that project to see if it's in scope. If you need cycle data, you have to navigate to the team view, risking losing context or getting lost in nested menus.
With this MCP server, your AI client handles the navigation. You tell it what you need—like 'What is the status of the Auth bug?'—and it runs `get_issue` and any necessary checks behind the scenes. It gives you a single, clean answer, instantly.
Linear MCP Server: Manage issues and sprints from your IDE.
Manual process steps that vanish include switching between Linear's web app and your coding environment. You don't have to copy an issue ID, paste it into a separate window, then switch back to write a comment. The whole loop stays in the chat.
This means your context never breaks. Your AI acts as a true extension of your workflow, allowing you to manage complex tasks and collaborate without ever leaving your primary workspace.
Common Questions About Linear MCP
How do I find all open issues assigned to the 'Platform' team using list_issues? +
You must run list_teams first to get the unique Team ID for 'Platform'. Then, pass that ID into search_issues. This gives you a filtered list of only those issues.
What is the best way to check sprint health using list_cycles? +
Run list_cycles and specify the Team ID. The output provides the cycle's progress percentage, start date, and end date in one data block, letting you spot delays immediately.
Can I change an issue's priority using update_issue? +
Yes. You must first get the specific Issue UUID using get_issue. Then, use update_issue and specify both the UUID and the new desired priority level (e.g., 'High').
How do I find all available projects to scope a feature? +
Call list_projects. This function returns every active project in your workspace, allowing you to gather context and understand which teams are contributing to that scope.
How do I use `get_viewer` to verify which account my agent is operating under? +
Run get_viewer first. This confirms the authenticated user details, so you know exactly which Linear workspace your AI client is accessing before making any changes.
When should I use `list_labels` before creating a new issue with `create_issue`? +
You must run list_labels to pull the exact label ID. This prevents errors and ensures your agent assigns categorization tags correctly when generating a new task.
How do I use `get_issue` to verify details before running `update_issue`? +
Get_issue pulls all current fields and metadata for an issue ID. Always run this first; it lets you confirm the assignee or priority level before committing a change with update_issue.
When should I use `create_comment` instead of creating a new task via `create_issue`? +
Use create_comment when you just need to provide immediate, contextual discussion or an update. It keeps the conversation attached directly to the existing thread without generating new tasks.
How do I find my Linear Personal API Key? +
Go to Linear Settings > API and click Create API Key. Give it a descriptive name like 'Vinkius MCP' and copy the generated key immediately — it won't be shown again.
Can I create new issues with assignees and labels? +
Yes! Use the create_issue tool with the required team_id and title parameters. Optionally provide assignee_id, priority (0-4), description in Markdown and label_ids as a comma-separated list. The agent will return the created issue's identifier and URL.
Does the agent have access to delete issues or modify team settings? +
No. This server focuses on read operations and safe mutations — creating issues, updating fields and adding comments. Destructive actions like deletion or team configuration changes are not exposed, keeping your workspace secure.
Multi-server workflows that include Linear MCP
Find API Vulnerabilities First Using MCP
Your OpenAPI spec has 14 security findings and 3 match active HackerOne reports , your agent creates the tickets before the bounty payout
Find Codebase Duplications Using MCP Servers
Your codebase has 4 different implementations of date formatting, 3 versions of the retry logic, and 2 competing validation libraries , but nobody knows because grep only finds exact matches and these duplicates are semantic
How MCP Servers Auto-Triage Bug Reports
New bugs detected, severity classified, sprint tickets created, team notified , triage your backlog without a standup
MCP Recipe to Fix Production Crashes Faster
Your app crashed 847 times yesterday and the error report sits in Honeybadger while your Linear board has no idea , the engineer who wrote the broken code merged a different PR today
MCP Recipe to Kill Codebase Bloat
Codebase audited, bloat identified, requirements questioned, lean tickets created , kill architectural complexity before it ships
MCP Servers for Multi-Client Sprint Management
Your dev team tracks their work in Linear but the PM reports to clients in ClickUp , which means every sprint update is manually transcribed between two tools, and by the time the client sees it in ClickUp the data is already outdated
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
LanceDB (Serverless Vector DB)
Manage vectorized data via LanceDB — perform similarity searches, create tables, and manage multi-modal embeddings.
Fly.io Alternative
Manage edge compute infrastructure via Fly.io — list apps, control machines (VMs), manage volumes and certificates from any AI agent.
Cypress Cloud
Audit E2E testing via Cypress — monitor test runs, inspect spec instances, track flaky tests, and generate enterprise reports directly from any AI agent.
You might also like
NetEase BUFF
Automate digital skin trading via BUFF — monitor virtual item prices, snag global market trends, and fetch dynamic inventory values from any AI agent.
SparkPost
Bring your SparkPost email delivery platform into your AI. Manage templates, send campaigns, and audit deliverability directly from your editor.
Tencent Yuanqi
Orchestrate Tencent Yuanqi AI Agents — manage assistants, trigger conversations, and handle RAG documents directly from any AI agent.