Exécute une action eyeot ERP par son nom canonique. Format action : <module>.<resource>.<verb> (ex: 'clients.list', 'rh.employes.create', 'quotes.send'). Toujours utiliser eyeot_help d'abord pour connaître l'action + les params attendus. Les params path (ex: id) et le body JSON sont passés dans p...
AI agents invoke eyeot_call to trigger actions in Eyeot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
action | string | Yes | Nom canonique de l'action (ex: 'rh.employes.create'). |
params | object | — | Tous les paramètres mélangés : path params (id, ...), query params (limit, cursor, ...) et body fields. Le serveur route automatiquement selon la spec OpenAPI. |
Parameters from the server's own tool schema.
This is a generic execution gateway into a full ERP system covering ~600 actions. An AI agent could invoke any action including destructive or financial ones (e.g., quotes.send, rh.employes.create, or potential delete/drop verbs). The blast radius is critical because misuse could affect finances, HR records, client data, inventory, and more across the entire organization.
From the tool's definition 'Exécute une action eyeot ERP par son nom canonique' — the tool explicitly executes arbitrary ERP actions by canonical name across all modules (CRM, sales, stock, HR, finance). Format covers verbs like 'create', 'send', 'delete', etc.
Attacks that exploit this kind of access
Exécute une action eyeot ERP par son nom canonique. Format action : <module>.<resource>.<verb> (ex: 'clients.list', 'rh.employes.create', 'quotes.send'). Toujours utiliser eyeot_help d'abord pour connaître l'action + les params attendus. Les params path (ex: id) et le body JSON sont passés dans params. It is categorised as a Execute tool in the Eyeot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
eyeot_call accepts 2 parameters: action, params. Required: action. 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_call: 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_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the eyeot_call 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_call. 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_call 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 →