order_by, filter, limit, depth, starting_after or ending_before can be provided to request your favorites
AI agents call findManyFavorites to retrieve information from Twenty MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/retrieval operation that fetches favorite records from the CRM database. It only reads data with no side effects—no data is created, modified, deleted, or executed. The parameters are all read-related filtering and pagination options. The blast radius is low as misuse would only expose data the user should have access to within their CRM.
From the tool's definition Tool name 'findManyFavorites' and description indicating it retrieves favorites with optional filtering, ordering, limiting, and pagination parameters (order_by, filter, limit, depth, starting_after, ending_before).
Documented attack patterns abuse exactly the kind of access findManyFavorites gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Twenty MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for findManyFavorites:
{
"version": "1",
"default": "deny",
"tools": {
"findManyFavorites": {}
}
}findManyFavorites 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.
order_by, filter, limit, depth, starting_after or ending_before can be provided to request your favorites. It is categorised as a Read tool in the Twenty MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Twenty MCP Server MCP server in PolicyLayer and add a rule for findManyFavorites: 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 Twenty MCP Server. Nothing to install.
findManyFavorites 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 findManyFavorites 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 findManyFavorites. 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.
findManyFavorites is provided by the Twenty MCP Server MCP server (jdu278/twenty-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Twenty MCP Server, 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.
219 Twenty MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.