Catalog des actions disponibles sur eyeot ERP. Sans argument : liste les modules et compteur d'actions. Avec module='rh' : liste toutes les actions RH (employes, conges, paie, formations…). Avec action='rh.employes.create' : retourne le détail (path, méthode, params, schema body). Avec search='fa...
AI agents call eyeot_help to retrieve information from Eyeot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
action | string | — | Action exacte au format `<module>.<resource>.<verb>` (ex: 'rh.employes.create'). Retourne le schéma complet. |
module | string | — | Nom du module (ex: 'rh', 'finance', 'clients'). Optionnel. |
search | string | — | Recherche textuelle dans les noms d'action et descriptions. Optionnel. |
Parameters from the server's own tool schema.
This tool is purely a discovery/catalog tool that retrieves information about available ERP actions. It queries and returns metadata (module lists, action details, search results) without creating, modifying, executing, or deleting any data. The instruction 'appeler eyeot_help AVANT eyeot_call' confirms it is a read-only preparatory step.
From the tool's definition 'Catalog des actions disponibles' — lists modules, actions, and their details; 'retourne le détail (path, méthode, params, schema body)' — returns metadata only; no data mutation described.
Attacks that exploit this kind of access
Catalog des actions disponibles sur eyeot ERP. Sans argument : liste les modules et compteur d'actions. Avec module='rh' : liste toutes les actions RH (employes, conges, paie, formations…). Avec action='rh.employes.create' : retourne le détail (path, méthode, params, schema body). Avec search='facture' : recherche les actions matchant. Toujours appeler eyeot_help AVANT eyeot_call pour découvrir l'action exacte. It is categorised as a Read tool in the Eyeot MCP Server, which means it retrieves data without modifying state.
eyeot_help accepts 3 parameters: action, module, search. The full parameter table on this page comes from the server's own tool schema.
Register the Eyeot MCP server in PolicyLayer and add a rule for eyeot_help: 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.
eyeot_help 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 eyeot_help 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 eyeot_help. 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.
eyeot_help 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →