Connect to an already-running ACM instance.
AI agents use connect_acm to create or update resources in ACM MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ACM MCP Server environment.
Connecting to a running ACM instance establishes a session/link to an external process, which is a side-effectful operation (creates a connection state) but does not delete or irreversibly modify data. It is more than a pure read since it mutates session state on the server. Not Execute because it doesn't run simulations or code itself — it just establishes connectivity.
From the tool's definition Connect to an already-running ACM instance.
Attacks that exploit this kind of access
Connect to an already-running ACM instance. It is categorised as a Write tool in the ACM MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ACM MCP Server MCP server in PolicyLayer and add a rule for connect_acm: 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 ACM MCP Server. Nothing to install.
connect_acm 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 connect_acm 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 connect_acm. 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.
connect_acm is provided by the ACM MCP Server MCP server (pekosann/acm-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 →