Read a watch's run history (newest first), paged. Each run includes changed, diffScore, and signed before/after/overlay image URLs. Returns { items, nextCursor }.
AI agents call watch_runs to retrieve information from Rendex Screenshot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | Yes | The watch ID (UUID). |
limit | integer | — | Page size (1–100). |
cursor | string | — | Pagination cursor from a previous nextCursor. |
Parameters from the server's own tool schema.
This tool retrieves and queries historical run data from watches with pagination support. It has no side effects—it only returns existing records (run history, diff scores, and image URLs). There is no creation, modification, deletion, or execution of external operations.
From the tool's definition Tool description explicitly states 'Read a watch's run history' and returns historical data (items, nextCursor) without modification. The verb 'read' and the passive data retrieval nature confirm this is a query operation.
Attacks that exploit this kind of access
Read a watch's run history (newest first), paged. Each run includes changed, diffScore, and signed before/after/overlay image URLs. Returns { items, nextCursor }. It is categorised as a Read tool in the Rendex Screenshot MCP Server, which means it retrieves data without modifying state.
watch_runs accepts 3 parameters: id, limit, cursor. Required: id. The full parameter table on this page comes from the server's own tool schema.
Register the Rendex Screenshot MCP server in PolicyLayer and add a rule for watch_runs: 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 Rendex Screenshot. Nothing to install.
watch_runs 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 watch_runs 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 watch_runs. 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.
watch_runs is provided by the Rendex Screenshot MCP server (copperline-labs/rendex-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 →