Search Linear issues
AI agents call linear_search_issues to retrieve information from Curri MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search operation, which is a read-only action that retrieves and returns matching issues from Linear. No data is created, modified, deleted, or executed. The blast radius is minimal since the action is non-destructive and returns only accessible information.
From the tool's definition Tool name 'linear_search_issues' and description 'Search Linear issues' indicate a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
Search Linear issues. It is categorised as a Read tool in the Curri MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Curri MCP Server MCP server in PolicyLayer and add a rule for linear_search_issues: 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 Curri MCP Server. Nothing to install.
linear_search_issues is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the linear_search_issues 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.
Set action: deny in the PolicyLayer policy for linear_search_issues. 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.
linear_search_issues is provided by the Curri MCP Server MCP server (teamcurri/mcp-linear). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
linear_search_issues is one line of Curri MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →