MCP Gateway · Claude Code
Connect Linear to Claude Code
Developers in Claude Code can read, file and update Linear issues without leaving the terminal. Through the Speakeasy MCP Gateway, each person signs in through your identity provider, reaches only the Linear tools their role allows, and every issue Claude Code creates or edits is logged against their name.
- Category
- Project management
- Tools
- 31
- Authentication
- OAuth
- Claude Code
- CLI
Behind the MCP Gateway
Run Linear MCP behind the MCP Gateway
One URL for every agent, sign-in through your IdP, RBAC down to the tool, and every Linear call inspected and logged.
Set up
Add Linear to Claude Code in 4 steps
- 01
Add Linear from the catalog
An admin finds Linear in the MCP Catalog (MCP Gateway > MCP > Catalog) and clicks Add. Speakeasy registers the vendor's server as a remote MCP server and proxies sessions to it. Nothing is copied or re-hosted.
Linear uses OAuth. Servers that support dynamic client registration get their OAuth configuration applied automatically.
Where MCP-scoped policies are enabled, the install offers a recommended risk policy for the new server that detects secrets and PII and inspects tool requests and responses.
- 02
Choose who can use Linear
Give teams the
mcp:connectscope on the Linear server through team access or a role. The organization gateway works out each person's servers from their live access, so granting access adds Linear to their gateway on the next call, and removing it takes it away. - 03
Connect Claude Code
Add the organization gateway as an HTTP MCP server, then authenticate from /mcp.
Run the command below with your organization gateway URL.
Open
/mcpin Claude Code and choose Authenticate to sign in.claude mcp add --transport http --scope user \ 'speakeasy' \ 'https://<organization host>/mcp/gateway/<organization slug>' - 04
Sign in and use Linear from Claude Code
The first time Claude Code connects, it opens a browser so the person can sign in to Speakeasy through your identity provider.
Linear needs its own OAuth grant, so each person connects it once. Until they do, Linear calls fail while the rest of the gateway keeps working.
From then on, Linear's tools appear in Claude Code, limited to what the person's access allows, and every call lands in the gateway's tool logs.
To roll it out to a whole team, publish the server in a plugin and register the plugin marketplace in Claude Code's managed settings, so every member gets it without running the command. The device agent can also write and reapply these settings on each laptop.
Use cases
What Claude Code users do with Linear
Start work from an assigned issue
Ask Claude Code for your open issues, pull the one you are picking up, and get its description, attachments and git branch name before writing the first line.
File a bug from the code
When Claude Code finds a defect it can't fix in the current change, it opens a Linear issue with the file, the failing case and the right team, then carries on.
Close the loop on review
After a change lands, Claude Code moves the issue to the team's done status and leaves a comment that summarizes what changed and why.
Tools
31 tools
Each Linear tool can be allowed or denied per team and role at the MCP Gateway before Claude Code sees it.
get_attachment
Retrieve an attachment's content by ID.
create_attachment
Create a new attachment on a specific Linear issue by uploading base64-encoded content.
delete_attachment
Delete an attachment by ID
list_comments
List comments for a specific Linear issue
save_comment
Create or update a comment on a Linear issue. If id is provided, updates the existing comment; otherwise creates a new one. When creating, issueId and body are required.
delete_comment
Delete a comment from a Linear issue
Control
What Speakeasy can see and stop in Claude Code
The gateway covers every client the same way. The rest depends on what Claude Code exposes to Speakeasy.
Tool logs
Gateway
Every Linear call is logged with the person and the client that made it.
Access by role
Gateway
People reach only the Linear tools their team or role allows.
Request and response blocking
Gateway
A risk policy scoped to Linear can reject a tool request before it reaches the server, or withhold a result from Claude Code. MCP-scoped policies are enabled per organization.
Prompt and tool-call blocking
Claude Code
Agent hooks send each prompt and tool call to Speakeasy, which allows or denies it before Claude Code runs it.
User attribution
Claude Code
Claude Code's OpenTelemetry exporter ties each session to a named person. Without it, activity can't be attributed.
Budgets
Claude Code
Spend limits can block Claude Code traffic once a budget is reached.
Device agent and MDM
Claude Code
The device agent installs the marketplace, plugin and telemetry settings and reapplies them every minute. It deploys through MDM.
Anthropic inference hooks
Claude Code
On Claude Enterprise, prompts can be checked before inference with nothing installed on the device (beta).
- Claude Code on the web doesn't use the laptop setup. It needs the device agent in a shared Anthropic-hosted environment.
- Plugin marketplace URLs for Claude Code carry an access token, so share install snippets only through a private channel.
Questions
Frequently asked questions
Can I limit which Linear actions Claude Code can take?
Do developers need their own Linear API keys in Claude Code?
How do Claude Code users get Linear?
Are Linear calls from Claude Code logged?
Connect more