find_references
AI agents call find_references to retrieve information from Odoo Index MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
find_references almost certainly searches for cross-references or usages of code elements within the Odoo codebase index, returning query results without modifying any data. This is consistent with other introspection tools on the same server. Despite the empty description, the naming and context strongly indicate a read-only operation.
From the tool's definition Tool name 'find_references' and server context describe search/retrieval operations on an Odoo code index. Sibling tools (search_odoo_index, search_by_attribute, get_item_details, list_modules) are all read-only retrieval operations.
Attacks that exploit this kind of access
find_references. It is categorised as a Read tool in the Odoo Index MCP MCP Server, which means it retrieves data without modifying state.
Register the Odoo Index MCP server in PolicyLayer and add a rule for find_references: 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 Index MCP. Nothing to install.
find_references 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 find_references 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 find_references. 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.
find_references is provided by the Odoo Index MCP server (letzdoo/odoo-indexer-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 →