Medium Risk

linear_updateIssueCustomField

Set or clear a custom field value on an issue. Pass null as value to clear it.

How to control linear_updateIssueCustomField ↓

AI agents use linear_updateIssueCustomField to create or update resources in Linear — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Linear environment.

Medium Risk

This tool modifies issue metadata (custom field values) within Linear but does not delete issues or execute arbitrary code. Changes are reversible by setting a different value or clearing the field again. The blast radius is limited to the specific issue's custom field state, affecting project tracking and workflow but not causing irreversible data loss or financial impact.

From the tool's definition Tool name contains 'update' and description states 'Set or clear a custom field value on an issue', indicating modification of existing data. The ability to pass null to clear values confirms reversible write operations.

Documented attack patterns abuse exactly the kind of access linear_updateIssueCustomField gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Linear, and nothing reaches the server without passing your rules. This is the rule we recommend for linear_updateIssueCustomField:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "linear_updateIssueCustomField": {
      "limits": [
        {
          "counter": "linear_updateissuecustomfield_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

linear_updateIssueCustomField stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Linear — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the linear_updateIssueCustomField tool do? +

Set or clear a custom field value on an issue. Pass null as value to clear it. It is categorised as a Write tool in the Linear MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on linear_updateIssueCustomField? +

Register the Linear MCP server in PolicyLayer and add a rule for linear_updateIssueCustomField: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Linear. Nothing to install.

What risk level is linear_updateIssueCustomField? +

linear_updateIssueCustomField is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit linear_updateIssueCustomField? +

Yes. Add a rate_limit block to the linear_updateIssueCustomField rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block linear_updateIssueCustomField completely? +

Set action: deny in the PolicyLayer policy for linear_updateIssueCustomField. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides linear_updateIssueCustomField? +

linear_updateIssueCustomField is provided by the Linear MCP server (tacticlaunch/mcp-linear). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Linear tool call.

Deterministic rules across all 182 Linear tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

182 Linear tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.