candidate_search

THE RISK

Low Risk

Why candidate_search needs a policy

This tool retrieves candidate information based on search criteria (email and/or name). It performs no data modification, deletion, or execution of external operations. The lack of pagination and straightforward search semantics confirm it is a read-only operation with minimal security risk if misused by an agent.

From the tool's definition Tool description states "Search for candidates by email and/or name" with no mention of modifications, deletions, or side effects. The verb "search" indicates a query/retrieval operation.

Documented attack patterns abuse exactly the kind of access candidate_search gives an agent:

POLICY

How to control candidate_search

PolicyLayer is an MCP gateway — it sits between your AI agents and Ashby MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for candidate_search:

policy.json

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

candidate_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Ashby MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Ashby MCP Server tools

Write application_change_stage Move an application to a different interview stage. Write application_create Create an application linking a candidate to a job. Write candidate_add_tag Add a tag to a candidate. This is a WRITE operation. Write candidate_create Create a new candidate in Ashby. Only Write candidate_create_note Add a note to a candidate. Supports HTML formatting in the note body. Read application_info Get full details for a single application by ID. Returns candidate, job, Read application_list List applications (candidates in a hiring pipeline). Filter by jobId to see Read candidate_full_profile Get a complete view of a candidate: their info, all applications (with job

All 21 Ashby MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about candidate_search

What does the candidate_search tool do? +

Search for candidates by email and/or name. Not paginated. It is categorised as a Read tool in the Ashby MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on candidate_search? +

Register the Ashby MCP Server MCP server in PolicyLayer and add a rule for candidate_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 Ashby MCP Server. Nothing to install.

What risk level is candidate_search? +

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

Can I rate-limit candidate_search? +

Yes. Add a rate_limit block to the candidate_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.

How do I block candidate_search completely? +

Set action: deny in the PolicyLayer policy for candidate_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.

What MCP server provides candidate_search? +

candidate_search is provided by the Ashby MCP Server MCP server (plenishai/mcp-ashby). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Ashby MCP Server tool call.

Start from Ashby MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →