Business · MCP Server

Linear MCP: setup, permissions and security risks

The Linear MCP server gives an agent issues, projects, cycles, and comments. That is useful, and it is also a set of real capabilities pointed at a real system. Here is what it exposes, why it is worth governing, and the policy to put in front of it.

Exposure grade B

3 of 7 points, default setup. Last checked October 21, 2026.

Returns text written by people outside your team	Yes, +2
Can change things outside your machine	Yes, +1
Can do something hard to undo	No
Can read local files or run code locally	No
Default credential is long-lived and broad	No
Advisory or disclosure in the 12 months before the check	No

0–1 points is A, 2–3 B, 4 C, 5–6 D, 7 F. The grade measures how much the default setup can reach, not the quality of the code. The hardening options below lower it.

Setup

Remote server hosted by Linear (Claude Code, OAuth)

claude mcp add --transport http linear-server https://mcp.linear.app/mcp
# then run /mcp inside Claude Code to sign in

Read-only endpoint

claude mcp add --transport http linear-readonly https://mcp.linear.app/mcp/readonly

How it logs in

OAuth 2.1 with dynamic client registration. You can also send an OAuth access token or a Linear API key as a Bearer header; a key created with only the Read permission is read-only.

Tools that change things

create and update issuescreate and update projectscreate comments

Built-in hardening

Point the agent at /mcp/readonly, which exposes only read tools.
Or request only the read OAuth scope on /mcp.
The SSE endpoint (/sse) is deprecated; use /mcp.

Known advisories and incidents

None published as of the check date.

What the server hands your agent

Issue and project read and write, comment creation, and status changes.

Why it is worth governing

Issue descriptions and comments are free text written by teammates and, through intake integrations, sometimes by customers.
Status and assignment changes are real signals that other people act on.
Linked customer feedback pulls verbatim user text into the agent context.

Tag what the tools actually do

Prismor tags every tool by behavior rather than by name, so rules survive a server adding tools you have never seen. A sensible starting map for Linear:

Tool pattern	Tags	Why
mcp__linear__issue	untrusted_content	issue bodies are free text from many sources
mcp__linear__create	critical_action	created issues are visible to the team
mcp__linear__update	critical_action	status and assignee changes trigger other people’s work

Patterns are illustrative globs. Run prismor tags list to see how your installed tools actually resolve.

The policy

Rules read as a sentence: a tag, then or with another tag, and what to do about it. Note the mode - start by watching, not blocking.

settings:
  tool_tags:
    enabled: true
    mode: observe            # switch to enforce once the log looks right
    tags:
      "mcp__linear__*issue*": [untrusted_content]
      "mcp__linear__*create*": [critical_action]
      "mcp__linear__*update*": [critical_action]
    rules:
      - "untrusted_content then critical_action -> block"

Putting Linear behind the gateway

You do not change the Linear server or how it is configured. Move your existing mcpServers block behind the Prismor gateway and point your agent at Prismor instead:

prismor mcp-gateway install    # moves your .mcp.json servers behind the gateway
prismor mcp-gateway uninstall  # restores the original, backup kept

Your agent sees the same Linear tools, namespaced as mcp__linear__<tool>. Every call is evaluated against policy before it is forwarded, and every result is scanned as untrusted content before the model sees it.

Frequently asked questions

Is the Linear MCP server safe to give an AI agent?

It is as safe as the credential behind it and the policy in front of it. The server itself is not the problem: the risk is that an agent can combine Linear access with everything else in the session, with no record of what it did. Front it with a gateway that evaluates each call and logs the verdict.

Does Prismor replace the Linear MCP server?

No. You keep running the same server, unchanged. Prismor aggregates it behind a single connector so your agent sees the same tools, namespaced as mcp__<server>__<tool>, with every call and every result passing through policy first.

Will this block work my team actually needs to do?

Not if you start in observe mode. Every call is recorded with the decision that would have applied, and nothing is blocked. You promote rules to enforce once the log shows the policy matches how your agents really work.

What about tool results, not just tool calls?

Results are scanned as untrusted content before the model sees them. A response carrying injected instructions or poisoned output is withheld and replaced with the reason, which matters most for servers that return text other people wrote.

One gateway for every MCP server

Linear is one connector. The same policy covers the rest of them, plus the shell commands and file access your agents already have.

Install Prismor How MCP security works

Other business servers

Salesforce

HubSpot SEServiceNow

Jira All servers

Linear is a trademark of its respective owner. Prismor is not affiliated with or endorsed by it. The Linear MCP server is third-party software; Prismor governs it the same way it governs any MCP server, without modifying it.