AI agents use pulse_update_task to create or update resources in Pulse — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pulse environment.
This tool creates or modifies data reversibly by allowing updates to task attributes (title, description, status, tags). Changes can be undone by subsequent updates. It does not execute code, delete data irreversibly, or move money. Severity is medium because an agent could spam task updates or corrupt task metadata, but the impact is limited to task records and reversible.
From the tool's definition Tool name 'pulse_update_task' and description 'Update a task or subtask (title/status; description is task-only)' clearly indicate modification of existing data.
Attacks that exploit this kind of access
Update a task or subtask (title/status; description is task-only). At least one update field (title, description, status, or tag) must be provided. It is categorised as a Write tool in the Pulse MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pulse MCP server in PolicyLayer and add a rule for pulse_update_task: 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 Pulse. Nothing to install.
pulse_update_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pulse_update_task 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 pulse_update_task. 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.
pulse_update_task is provided by the Pulse MCP server (nemesiscodex/pulse-tm). 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 →