Record an architectural or interface decision for other sessions.
AI agents use coord_record_decision to create or update resources in Session Coord — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Session Coord environment.
This tool creates/writes a decision record that persists and is shared across sessions. It modifies the coordination state by adding new decision data. This is reversible in principle (a record can be updated or deleted), placing it in the Write category. Misuse could mislead other AI coding sessions into making incorrect implementation choices, hence medium severity.
From the tool's definition Record an architectural or interface decision for other sessions
Attacks that exploit this kind of access
Record an architectural or interface decision for other sessions. It is categorised as a Write tool in the Session Coord MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Session Coord MCP server in PolicyLayer and add a rule for coord_record_decision: 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 Session Coord. Nothing to install.
coord_record_decision 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 coord_record_decision 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 coord_record_decision. 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.
coord_record_decision is provided by the Session Coord MCP server (lingfeng-vels/session-coord-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 →