AI agents use adr_create 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 creates new ADR documents with title and optional content. Creation of records is a Write operation—the data is newly generated but can be modified or deleted later, making it reversible. The blast radius is low since ADRs are typically documentation artifacts without direct external system impact. No financial, destructive, or execution-of-external-code implications present.
From the tool's definition Tool description states 'Create a new ADR', which is a create operation that generates new data (Architecture Decision Records) reversibly.
Attacks that exploit this kind of access
Create a new ADR with the given title and optional content. 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_create: 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_create 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_create 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_create. 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_create 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 →