job_scan

Scan multiple job sources at once for MCP, AI, TypeScript, and Discord jobs. Returns results from Upwork, RemoteOK, and HN. Use this for a daily job check.

SERVERJobs SOURCE0xcybin/jobs-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade A, identity unverified Pull the record →

This record as markdown: /tools/0xcybin-jobs-mcp/job-scan.md

WHAT IT DOES

What job_scan does on Jobs

AI agents call job_scan to retrieve information from Jobs without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why job_scan is rated Low

job_scan performs read-only queries across multiple job platforms and aggregates the results. The tool searches and retrieves job listing data without creating, modifying, deleting, or executing anything. It is analogous to a search or list operation. The blast radius of misuse is minimal—an agent could at worst retrieve job listings repeatedly or return irrelevant results, but cannot harm systems or data.

From the tool's definition Tool description states it 'Scan multiple job sources at once' and 'Returns results from Upwork, RemoteOK, and HN' — purely retrieval operations with no modification, deletion, execution, or financial side effects.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs job_scan safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Jobs, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For job_scan, this is the rule to start with:

job_scan Allowed

job_scan is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "job_scan": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Jobs, apply this rule, and every job_scan call is checked against it from then on.

FAQ

Questions about job_scan

What does the job_scan tool do? +

Scan multiple job sources at once for MCP, AI, TypeScript, and Discord jobs. Returns results from Upwork, RemoteOK, and HN. Use this for a daily job check. It is categorised as a Read tool in the Jobs MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on job_scan? +

Register the Jobs MCP server in PolicyLayer and add a rule for job_scan: 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 Jobs. Nothing to install.

What risk level is job_scan? +

job_scan is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit job_scan? +

Yes. Add a rate_limit block to the job_scan 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.

How do I block job_scan completely? +

Set action: deny in the PolicyLayer policy for job_scan. 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.

What MCP server provides job_scan? +

job_scan is provided by the Jobs MCP server (0xcybin/jobs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Jobs, and thousands of servers like it.

This server

All 8 Jobs tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →