request_leave · Eyeot MCP: Risk & Policy

WHAT IT DOES

What request_leave does on Eyeot

AI agents use request_leave to create or update resources in Eyeot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Eyeot environment.

PARAMETERS

Parameter	Type	Required	Description
`body`	object	Yes	Request body

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why request_leave needs a policy

The tool submits a leave request, which is a reversible write operation (creating a record in the HR module). It does not delete data, execute code, or move money. Misuse could cause HR scheduling disruptions, hence medium severity.

From the tool's definition 'Demander un congé' means 'Request a leave' in French — this creates a new leave request record in the HR system

Risk signalsAccepts raw HTML/template content (body)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

request_leave Rate-limited

request_leave 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "request_leave": {
      "limits": [
        {
          "counter": "request_leave_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Eyeot, so you can run agents against it safely.

FAQ

Questions about request_leave

What does the request_leave tool do? +

Demander un congé. It is categorised as a Write tool in the Eyeot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does request_leave accept? +

request_leave accepts 1 parameter: body. Required: body. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on request_leave? +

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

What risk level is request_leave? +

request_leave is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit request_leave? +

Yes. Add a rate_limit block to the request_leave 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 request_leave completely? +

Set action: deny in the PolicyLayer policy for request_leave. 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 request_leave? +

request_leave is provided by the Eyeot MCP server (https://erp.eyeot.fr/api/v1/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.