Search products for an enrolled chat, returning ONLY the scenario
AI agents call telegram_agent_product_lookup to retrieve information from Odoo Claude MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and returns product data. The 'search' verb and 'returning' phrasing indicate data retrieval with no side effects. Severity is low because product lookups have minimal blast radius even if an AI agent queries repeatedly or with unexpected arguments. The tool appears limited to a specific enrolled chat context, further constraining potential harm.
From the tool's definition Tool description states 'Search products for an enrolled chat, returning ONLY the scenario' — a search operation that retrieves product information without modifying data.
Documented attack patterns abuse exactly the kind of access telegram_agent_product_lookup gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Odoo Claude MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for telegram_agent_product_lookup:
{
"version": "1",
"default": "deny",
"tools": {
"telegram_agent_product_lookup": {}
}
} telegram_agent_product_lookup is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search products for an enrolled chat, returning ONLY the scenario. It is categorised as a Read tool in the Odoo Claude MCP MCP Server, which means it retrieves data without modifying state.
Register the Odoo Claude MCP server in PolicyLayer and add a rule for telegram_agent_product_lookup: 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 Odoo Claude MCP. Nothing to install.
telegram_agent_product_lookup 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 telegram_agent_product_lookup 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 telegram_agent_product_lookup. 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.
telegram_agent_product_lookup is provided by the Odoo Claude MCP server (rosenvladimirov/odoo-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Odoo Claude MCP, 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.
180 Odoo Claude MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.