Save the current session state after completing a task.
AI agents use update_session_context to create or update resources in Calendar Pa — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Calendar Pa environment.
This tool creates or modifies session state data reversibly. It does not delete data (would be Destructive), does not execute external operations with unpredictable side effects (would be Execute), and does not involve financial transactions (would be Financial).
From the tool's definition Tool is named 'update_session_context' and described as 'Save the current session state after completing a task.' The verb 'Save' indicates a write/modification operation on session state data.
Attacks that exploit this kind of access
Save the current session state after completing a task. It is categorised as a Write tool in the Calendar Pa MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Calendar Pa MCP server in PolicyLayer and add a rule for update_session_context: 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 Calendar Pa. Nothing to install.
update_session_context 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 update_session_context 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 update_session_context. 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.
update_session_context is provided by the Calendar Pa MCP server (richardilemon/calendar-pa). 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 →