AI agents call associations_of to retrieve information from Graphdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves metadata about Rails model associations. It performs a read-only inspection of code structure without modifying files, executing code, or triggering side effects. The broader server context (indexing Rails codebases into a queryable graph) confirms this is a navigation and analysis tool, not an action tool. The risk is minimal as it only surfaces existing code relationships.
From the tool's definition Tool name is 'associations_of' and description states it retrieves 'all ActiveRecord associations on a model' - a pure data retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Rails-specific: all ActiveRecord associations on a model. It is categorised as a Read tool in the Graphdb MCP Server, which means it retrieves data without modifying state.
Register the Graphdb MCP server in PolicyLayer and add a rule for associations_of: 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 Graphdb. Nothing to install.
associations_of 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 associations_of 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 associations_of. 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.
associations_of is provided by the Graphdb MCP server (samagra001/claude-code-graphdb). 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 →