AI agents use session_log to create or update resources in Recap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Recap environment.
This tool creates a new session log entry in the project's markdown files. It writes data (session notes, decisions, next steps) but does not delete or overwrite existing data, execute code, or involve financial transactions. The blast radius is low — misuse could write incorrect or misleading session notes, but this is reversible and contained within local markdown files.
From the tool's definition 'Log a session entry for a project: what was worked on, decisions made, next steps'
Attacks that exploit this kind of access
Log a session entry for a project: what was worked on, decisions made, next steps. The core. It is categorised as a Write tool in the Recap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Recap MCP server in PolicyLayer and add a rule for session_log: 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 Recap. Nothing to install.
session_log 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 session_log 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 session_log. 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.
session_log is provided by the Recap MCP server (shivam-singh-git/recap-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 →