AI agents use adr_deprecate to create or update resources in Mcp Adr — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Adr environment.
This tool modifies existing ADR records by changing their status to deprecated, which is a reversible write operation. It does not delete data (would be Destructive), execute external code (Execute), or retrieve data (Read). The modification is non-destructive since the ADR record itself remains and the deprecation state could theoretically be reverted.
From the tool's definition Tool name 'adr_deprecate' and description 'Deprecate an ADR with a reason' indicates modification of an ADR's status/metadata. Deprecation marks a record as obsolete while preserving it (reversible state change), contrasting with deletion.
Attacks that exploit this kind of access
Deprecate an ADR with a reason. It is categorised as a Write tool in the Mcp Adr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Adr MCP server in PolicyLayer and add a rule for adr_deprecate: 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 Mcp Adr. Nothing to install.
adr_deprecate 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 adr_deprecate 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 adr_deprecate. 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.
adr_deprecate is provided by the Mcp Adr MCP server (mauriziomocci/mcp-adr). 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 →