Get data model definitions with their read/write relationships.
AI agents call repomap_data_model to retrieve information from RepoMap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs introspection of a codebase to extract metadata about data models and their relationships. The action is purely retrievals that provide static analysis information about the code, with no side effects, state changes, or code execution. This aligns with the Read category (get, fetch, query data).
From the tool's definition Tool retrieves 'data model definitions with their read/write relationships' — a query operation that describes existing code structure without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access repomap_data_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RepoMap, and nothing reaches the server without passing your rules. This is the rule we recommend for repomap_data_model:
{
"version": "1",
"default": "deny",
"tools": {
"repomap_data_model": {}
}
}repomap_data_model 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.
Get data model definitions with their read/write relationships. It is categorised as a Read tool in the RepoMap MCP Server, which means it retrieves data without modifying state.
Register the RepoMap MCP server in PolicyLayer and add a rule for repomap_data_model: 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 RepoMap. Nothing to install.
repomap_data_model 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 repomap_data_model 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 repomap_data_model. 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.
repomap_data_model is provided by the RepoMap MCP server (tusharkarkera22/repomap-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RepoMap, 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.
6 RepoMap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.