AI agents call poll_dev_queue to retrieve information from Tickr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | — | Project slug to filter assignments (e.g. 'tickr'). Without this, returns tasks from all projects. |
Parameters from the server's own tool schema.
This tool queries state (polls a queue) and returns information (ticket details, skills, instructions) with no side effects. It is a classic Read operation analogous to fetching or checking status. The mention of 'project filter' reinforces it's a read-only parameter to control scope, not a modification. No data is created, deleted, executed, or financially committed.
From the tool's definition Tool name 'poll_dev_queue' combined with description 'Poll for next dev task in the agent queue. Returns ticket details and assigned skills/instructions' indicates a retrieval operation that reads the current state of a queue without modifying or executing…
Attacks that exploit this kind of access
Poll for next dev task in the agent queue. Returns ticket details and assigned skills/instructions. Use project filter to prevent cross-project race conditions. It is categorised as a Read tool in the Tickr MCP Server, which means it retrieves data without modifying state.
poll_dev_queue accepts 1 parameter: project. The full parameter table on this page comes from the server's own tool schema.
Register the Tickr MCP server in PolicyLayer and add a rule for poll_dev_queue: 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 Tickr. Nothing to install.
poll_dev_queue 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 poll_dev_queue 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 poll_dev_queue. 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.
poll_dev_queue is provided by the Tickr MCP server (@k-system/tickr-mcp). 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 →