Get data structs, enums, Firestore collections, and Supabase tables from local cache. No API calls. Run sync_project first if not cached.
AI agents call get_data_models to retrieve information from Community Ff without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs read-only queries against cached project metadata. It retrieves structural information (data models, enums, collections) without creating, modifying, deleting, or executing anything. The instruction to 'Run sync_project first if not cached' indicates it depends on prior synchronization but performs no mutations itself.
From the tool's definition Tool description explicitly states it 'Get[s] data structs, enums, Firestore collections, and Supabase tables from local cache' with 'No API calls.' This is retrieval of schema/metadata information without modification or side effects.
Documented attack patterns abuse exactly the kind of access get_data_models gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Community Ff, and nothing reaches the server without passing your rules. This is the rule we recommend for get_data_models:
{
"version": "1",
"default": "deny",
"tools": {
"get_data_models": {}
}
}get_data_models 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 structs, enums, Firestore collections, and Supabase tables from local cache. No API calls. Run sync_project first if not cached. It is categorised as a Read tool in the Community Ff MCP Server, which means it retrieves data without modifying state.
Register the Community Ff MCP server in PolicyLayer and add a rule for get_data_models: 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 Community Ff. Nothing to install.
get_data_models 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 get_data_models 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 get_data_models. 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.
get_data_models is provided by the Community Ff MCP server (mohn93/ff-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Community Ff, 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.
25 Community Ff tools catalogued and risk-classified — across an index of 43,000+ MCP servers.