Log an activity (call, email, meeting, note, task, sms) against a CRM contact.
AI agents use log_activity to create or update resources in Inkwell MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Inkwell MCP Server environment.
This tool creates new activity records associated with CRM contacts. It is a write operation (creating data) that is reversible in principle (records can be deleted). The blast radius is medium because misuse could pollute CRM contact histories with false or misleading activity logs, affecting sales/support workflows.
From the tool's definition 'Log an activity' against a CRM contact — creates a new activity record (call, email, meeting, note, task, sms)
Attacks that exploit this kind of access
Log an activity (call, email, meeting, note, task, sms) against a CRM contact. It is categorised as a Write tool in the Inkwell MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Inkwell MCP Server MCP server in PolicyLayer and add a rule for log_activity: 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 Inkwell MCP Server. Nothing to install.
log_activity 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 log_activity 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 log_activity. 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.
log_activity is provided by the Inkwell MCP Server MCP server (mumega-com/inkwell). 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 →