Fetch a bounded slice of records and build a local BM25 knowledge index
AI agents call index_knowledge to retrieve information from Odoo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves records from Odoo and builds a local search index (BM25). The primary action is reading/fetching data. Building a local index is a side effect confined to local storage, not modifying remote Odoo data. Severity is medium because it could expose sensitive ERP records depending on what data is fetched.
From the tool's definition Fetch a bounded slice of records and build a local BM25 knowledge index
Attacks that exploit this kind of access
Fetch a bounded slice of records and build a local BM25 knowledge index. It is categorised as a Read tool in the Odoo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Odoo MCP Server MCP server in PolicyLayer and add a rule for index_knowledge: 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 MCP Server. Nothing to install.
index_knowledge 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 index_knowledge 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 index_knowledge. 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.
index_knowledge is provided by the Odoo MCP Server MCP server (pypi:odoo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.