appflowy_search
AI agents call appflowy_search to retrieve information from AppFlowy MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search tools are retrieval operations that query data without modifying, deleting, or executing side effects. Based on the name and the context of the AppFlowy MCP server (which provides workspace and content management), this tool likely searches existing content. The empty description reduces confidence slightly, but the semantic meaning of 'search' clearly aligns with Read category operations.
From the tool's definition Tool name 'appflowy_search' indicates a search operation, which is a query/retrieval function typical of Read category operations. The tool description is empty, preventing definitive confirmation of its exact functionality.
Attacks that exploit this kind of access
appflowy_search. It is categorised as a Read tool in the AppFlowy MCP MCP Server, which means it retrieves data without modifying state.
Register the AppFlowy MCP server in PolicyLayer and add a rule for appflowy_search: 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 AppFlowy MCP. Nothing to install.
appflowy_search 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 appflowy_search 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 appflowy_search. 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.
appflowy_search is provided by the AppFlowy MCP server (weironz/appflowy_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 →