AI agents use create_time_entry to create or update resources in Timecamp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Timecamp environment.
This tool creates new time entry records in TimeCamp, which is a reversible operation (entries can be edited or deleted later). It does not execute external code, delete data permanently, or move money. The blast radius is medium because misuse could create false time records affecting billing, payroll, or project tracking, but the impact is containable through audit logs and correction mechanisms.
From the tool's definition Tool name 'create_time_entry' and description 'Manually create a time entry for past work' indicate data creation without deletion or modification of existing records.
Attacks that exploit this kind of access
Manually create a time entry for past work. It is categorised as a Write tool in the Timecamp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Timecamp MCP server in PolicyLayer and add a rule for create_time_entry: 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 Timecamp. Nothing to install.
create_time_entry 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 create_time_entry 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 create_time_entry. 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.
create_time_entry is provided by the Timecamp MCP server (kkeeling/timecamp-mcp-server). 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 →