Provider REST API

11 actions

Connect Claude to Linear

Create, update, and search issues across your teams. Toolspoke puts 11 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API key
Actions exposed: 11
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Linear
Open the marketplace in your workspace, add Linear to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api key. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Linear shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Linear asks for

API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Personal API keyRequired: Linear → Settings → Security & access → Personal API keys; lin_api_…

What Claude can do in Linear

11 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 8Reads
Writes: 3Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

search_issues
Search issues with any combination of free text, team, assignee, workflow-state type, project, and label. Free text matches issue titles and descriptions. Returns compact issue summaries ordered by most recently updated; call get_issue for the full body and comments.
get_issue
Fetch one issue in full: description, current state, assignee, labels, parent and sub-issues, and its most recent comments. Use after search_issues when you need the actual content of an issue.
list_teams
List the workspace's teams with their keys and UUIDs. Call this first when you need a team_key for create_issue or search_issues.
list_workflow_states
List the workflow states (Backlog, Todo, In Progress, Done, …) available on a team, with their category type and UUID. Call this before moving an issue with update_issue so you use a state name the team actually has.
list_users
List workspace members with their names and email addresses. Use it to find the assignee_email that create_issue and update_issue expect.
list_projects
List projects with their state, dates, progress, and lead. Use it to find the project_id that create_issue and update_issue take.
list_labels
List issue labels defined in the workspace or on a specific team, so search_issues can filter by an exact label name.
list_my_issues
List issues assigned to the owner of the API key, most recently updated first. Completed and cancelled issues are excluded unless include_completed is set. Also returns who the key belongs to.

Writes

Creates or updates something on the other side.

create_issue
Create a new issue on a team. Supply team_key (or team_id) plus a title; assignee_email and state_name are resolved for you. Returns the created issue including its identifier and URL.
update_issue
Update an existing issue: retitle it, rewrite the description, move it to another workflow state, reassign it, change priority, or set a due date. Pass at least one field besides id. Does not delete anything.
create_comment
Post a markdown comment on an issue. Use this to report progress or ask a question rather than rewriting the issue description.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 11 actions above are the whole of it. A call to any other name is refused before it reaches Linear rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
Nothing here deletes: This connector writes to Linear, but nothing in it deletes or permanently alters anything.
It reaches no further than your credential: Toolspoke holds no access to Linear of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Linear: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Linear. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Linear's own rate limits. A call that Linear refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Linear?

11 named actions: 8 that only read and 3 that write. They include search_issues, get_issue and create_issue. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Linear connector need?

API key. The connector asks for personal api key. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Linear connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 11 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Linear connector not do?

The 11 actions above are the whole of it. A call to any other name is refused before it reaches Linear rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. This connector writes to Linear, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Linear of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Linear. An agent has to ask. Toolspoke does not retry, queue or back off around Linear's own rate limits. A call that Linear refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Linear's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Linear?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More project management connectors

Browse all of them