poll_events
AI agents call poll_events to retrieve information from Filesystem Watcher MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves event data from filesystem watches—a read operation with no side effects. It does not create, modify, delete, or execute operations; it simply polls and returns events that have occurred. The low severity reflects that polling events cannot damage or alter the filesystem; it only reads state information.
From the tool's definition Tool name 'poll_events' indicates retrieval of filesystem events. Server description emphasizes 'event-driven access' and watching for changes.
Attacks that exploit this kind of access
poll_events. It is categorised as a Read tool in the Filesystem Watcher MCP MCP Server, which means it retrieves data without modifying state.
Register the Filesystem Watcher MCP server in PolicyLayer and add a rule for poll_events: 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 Filesystem Watcher MCP. Nothing to install.
poll_events 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 poll_events 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 poll_events. 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.
poll_events is provided by the Filesystem Watcher MCP server (trycatchkamal/filesystemwatcher-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 →