Sends an email to the candidate (requires Mailgun configuration)
AI agents use contact_candidate to create or update resources in Candidate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Candidate environment.
This tool sends an email to a real person (the candidate), which is an externally visible write action with real-world consequences. Misuse could result in harassment, spam, or reputational damage. It is not Destructive or Financial, but it is a high-severity Write because it triggers outbound communication to a third party that cannot be easily recalled.
From the tool's definition Sends an email to the candidate
Documented attack patterns abuse exactly the kind of access contact_candidate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Candidate, and nothing reaches the server without passing your rules. This is the rule we recommend for contact_candidate:
{
"version": "1",
"default": "deny",
"tools": {
"contact_candidate": {
"limits": [
{
"counter": "contact_candidate_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}contact_candidate stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Sends an email to the candidate (requires Mailgun configuration). It is categorised as a Write tool in the Candidate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Candidate MCP server in PolicyLayer and add a rule for contact_candidate: 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 Candidate. Nothing to install.
contact_candidate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the contact_candidate 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 contact_candidate. 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.
contact_candidate is provided by the Candidate MCP server (jhgaylor/node-candidate-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Candidate, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Candidate tools catalogued and risk-classified — across an index of 43,000+ MCP servers.