List un-notified jobs sorted by score. Optional domain and min_score filters.
AI agents call list_new_jobs to retrieve information from Local Tech Digest without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries job listing data with optional filters (domain, min_score). There are no side effects, no data modification, no code execution, and no destructive or financial operations. It is a pure read operation that returns filtered job information to the user.
From the tool's definition Tool name is 'list_new_jobs' and description states 'List un-notified jobs sorted by score' with optional filtering parameters. The verb 'list' and the action of retrieving/querying job data without modification indicates a retrieval operation.
Attacks that exploit this kind of access
List un-notified jobs sorted by score. Optional domain and min_score filters. It is categorised as a Read tool in the Local Tech Digest MCP Server, which means it retrieves data without modifying state.
Register the Local Tech Digest MCP server in PolicyLayer and add a rule for list_new_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 Local Tech Digest. Nothing to install.
list_new_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_new_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_new_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_new_jobs is provided by the Local Tech Digest MCP server (nk1947-sudo/local-tech-digest-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 →