Connectors · Work & projects
Linear MCP server for AI agents.
actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Linear and the rest of your systems. It gives your agent 2 Linear actions (1 read and 1 write) and holds the Linear credential itself, so the agent never does. It paces Linear's limits and records every call.
100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.
claude mcp add --transport http actionlake https://connect.actionlake.com/mcpdo { action: "linear.issues.list", intent: "check which Linear account is connected"}# List Linear issues · read · 1 upstream call- 2actionspreview: growing in the store
- 1readlook, never change
- 1writecreate and update
- 0wait for a yesdestructive, confirmed first
Set up
Connect Linear in three steps.
- 01
Add actionlake to Claude.
Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.
https://connect.actionlake.com/mcp - 02
Connect Linear.
API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.
api_keyLinear API key
account { op: "connections.requirements", service: "linear" } # free: exactly what to paste, and what is found for you - 03
Make the first call. Check before a write.
Ask in plain words; Claude picks the action. Before anything changes,
checkvalidates the call and prices it, for free.do { action: "linear.issues.list" }# list linear issues · read · 1 upstream callcheck { action: "linear.issues.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent
Linear at a glance
- Sign-in
- API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
- You provide
api_key- Limits we pace to
- 2,500 calls an hour, per connection
- API covered
- Linear API 1
api.linear.app - Built from
- Linear's documentation, read 8 September 2026linear.app
- Service file
- Version 1.0.0, signed (Ed25519)
- Cached reads
- 1 of 1 reads, for up to an hour; a write clears what it affects
- Shared entities
- 1, so ask can line Linear up with your other systems
- Data
- Processed and stored in Sydney, Australia. No US region yet
Capabilities
What an AI agent can do in Linear.
2 actions in 1 area. Every one carries its effect, so a key can allow the reads and hold the rest.
- 1readlook, never change
- 1writecreate and update
- 0destructivewait for a confirmation
Issues
21 read · 1 write · 0 destructive
List Linear issues · Create a Linear issue
Top actions
The Linear API, shaped for agents.
The ids your agent types, what each does, and the one name it shares with other systems. 2 of Linear's 2 action names are shared with at least one other connector, so an agent learns them once.
| Action | What it does | Effect | Same name in |
|---|---|---|---|
linear.issues.listList Linear issues | List issues, most recently updated first. | read | work.task.list122 connectors |
linear.issues.createCreate a Linear issue | Create an issue on a team, by team id and title. | write | work.task.create127 connectors |
Try it
Prompts to paste into Claude.
Each one names the Linear actions it will call, so you know what it reads and what it changes before you send it.
- Readread
Which Linear tasks are overdue, and who owns each one?
calls
linear.issues.list - Writewrite
Create a Linear issue in Linear. Show me exactly what you will send before you save it.
calls
linear.issues.create
Governance for Linear
Every write can wait for a yes.
None of Linear's actions is destructive. A key can still be held to reads, capped, and set so a person confirms every write.
A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.
account { op: "keys.create", name: "linear-agent", allowed_actions: ["linear.*"], cap_calls: 2000, confirm_policy: "human_for_writes"}Cost
What Linear costs on actionlake.
Every Linear action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Linear refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.
- 1upstream call per actionall 2 Linear actions
- 0actions pageeach page of a long list is one call
- 1reads can be cacheda cache hit costs nothing
- 100,000calls a month, freepaid plans from US$49 a month for 250,000
Action index
Every Linear action.
2 actions by area: the id your agent calls, what it does, and its effect.
Issues2
linear.issues.createCreate a Linear issuewritelinear.issues.listList Linear issuesread
Questions
The Linear MCP server, answered.
Is there a Linear MCP server for Claude?
Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 2 Linear actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Linear.
What do I need to connect Linear?
Linear API key. The free call account { op: "connections.requirements", service: "linear" } lists exactly what to paste.
Can an AI agent change things in Linear?
Only if its key allows it. 1 Linear action write, and none is destructive. A key can be limited to reads, capped, and set so a person confirms every write.
Will an AI agent use up my Linear API limit?
actionlake paces every call to the limits in the Linear service file: 2,500 calls an hour per connection. Repeated reads are answered from cache (1 Linear actions can be), which never reaches Linear.
What does a Linear action cost?
One upstream call, the only unit actionlake bills. Cache hits, searches, dry runs and calls Linear refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.
Which Linear API does it cover?
The Linear API 1 at api.linear.app. It is built from Linear's documentation as read on 8 September 2026. 2 actions in 1 area, each one in the signed service file (version 1.0.0).
Does actionlake keep my Linear data, and where?
actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Linear credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.
Which AI clients can use it?
Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.
Give your agent Linear today.
Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.
