Searches a database for real-time job listings. Function: Call this tool to find jobs based on user criteria. CRITICAL SEARCH RULES: - Use the FULL job title/role as the query. - BAD: Query "Ruby" (Too broad, finds nurses, jewelry, etc.) - GOOD: Query "Ruby Developer" or "Ruby on Rails Engineer" ...
Risk signalsAccepts freeform code/query input (query)
Part of the FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT server.
Free to start. No card required.
AI agents call jobs_search to retrieve information from FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though jobs_search only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"jobs_search": {}
}
}See the full FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT policy for all 13 tools.
These attack patterns abuse exactly the kind of access jobs_search gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Searches a database for real-time job listings. Function: Call this tool to find jobs based on user criteria. CRITICAL SEARCH RULES: - Use the FULL job title/role as the query. - BAD: Query "Ruby" (Too broad, finds nurses, jewelry, etc.) - GOOD: Query "Ruby Developer" or "Ruby on Rails Engineer" - If user says "Find ruby developer jobs", query MUST be "Ruby Developer". OUTPUT & USAGE: - The output includes a list of jobs with an id field for each job. - To get full details about a specific job (description, requirements, benefits, etc.), use the jobs.details tool with the job's id value. - Example: If a job has id: "software-engineer-123", call jobs.details(job_id: "software-engineer-123") to fetch complete details. RENDERING RULES: - After receiving results, STOP calling tools. - If an interactive widget is shown to the user, it already displays the jobs — do NOT repeat them as a Markdown table; at most add one short summary sentence. - If NO widget is shown (text-only client), render the results as a Markdown table with columns: Title, Company, Location, Salary, Apply (using the job's link). PAGINATION RULES: - Initial Search: { query: "...", location: "..." } - Next Page: Use ONLY { cursor: "..." }.. It is categorised as a Read tool in the FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT MCP Server, which means it retrieves data without modifying state.
Register the FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT MCP server in PolicyLayer and add a rule for jobs_search: 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 FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT. Nothing to install.
jobs_search 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 jobs_search 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 jobs_search. 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.
jobs_search is provided by the FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT MCP server (@foundrole/ai-job-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.