List jobs submitted from this machine (local SQLite cache).
AI agents call list_recent_jobs to retrieve information from Whipscribe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a local SQLite cache to retrieve job history. It performs a read-only operation that returns information about previously submitted transcription jobs. There is no data modification, deletion, code execution, or financial impact. The scope is limited to the user's own local machine cache, minimizing blast radius if misused.
From the tool's definition Tool name 'list_recent_jobs' and description 'List jobs submitted from this machine (local SQLite cache)' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List jobs submitted from this machine (local SQLite cache). It is categorised as a Read tool in the Whipscribe MCP Server, which means it retrieves data without modifying state.
Register the Whipscribe MCP server in PolicyLayer and add a rule for list_recent_jobs: 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 Whipscribe. Nothing to install.
list_recent_jobs 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_recent_jobs 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_recent_jobs. 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_recent_jobs is provided by the Whipscribe MCP server (neugence/whipscribe-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 →