Update an existing ADR
AI agents use update_adr to create or update resources in Planning Game — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Planning Game environment.
Updating an ADR modifies existing data (ADRs are architectural decision records) in a reversible manner. This is a classic Write operation—it creates or modifies data without permanent deletion or irreversible effects. The medium severity reflects that corrupted or malicious ADR updates could mislead teams about architectural decisions, but the change can be undone by subsequent updates.
From the tool's definition Tool name is 'update_adr' and description states 'Update an existing ADR', indicating modification of an Architecture Decision Record.
Attacks that exploit this kind of access
Update an existing ADR. It is categorised as a Write tool in the Planning Game MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Planning Game MCP server in PolicyLayer and add a rule for update_adr: 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 Planning Game. Nothing to install.
update_adr 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_adr 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_adr. 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_adr is provided by the Planning Game MCP server (planning-game-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 →