List connected COMMIT destinations (GitHub repos, Jira projects, Linear teams). These are where ideas become REAL. After normalizing an idea, show the user where they can commit it. USE this tool when: - After normalize_idea, to show commit options - User asks
AI agents call list_destinations to retrieve information from IdeaLift MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
list_destinations retrieves and displays configuration data (connected destinations like GitHub repos, Jira projects, Linear teams) without modifying any state. This is a read-only query operation with no side effects. Even though the destinations represent commit targets for external systems, the tool itself performs only a retrieval/listing function, making it a Read category risk.
From the tool's definition Tool description uses 'List connected' and 'show' which are retrieval operations. The purpose is to display available destinations to the user, with no modification, creation, or deletion of data occurring.
Attacks that exploit this kind of access
List connected COMMIT destinations (GitHub repos, Jira projects, Linear teams). These are where ideas become REAL. After normalizing an idea, show the user where they can commit it. USE this tool when: - After normalize_idea, to show commit options - User asks. It is categorised as a Read tool in the IdeaLift MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IdeaLift MCP Server MCP server in PolicyLayer and add a rule for list_destinations: 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 IdeaLift MCP Server. Nothing to install.
list_destinations 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 list_destinations 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 list_destinations. 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.
list_destinations is provided by the IdeaLift MCP Server MCP server (startvest-llc/idealift-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →