AI agents use disconnect to create or update resources in Arca MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arca MCP environment.
The tool removes relationships (edges) between nodes in a semantic memory graph, which is a structural modification. This is categorized as Write rather than Destructive because: (1) it modifies relationships, not core data deletion, and (2) the operation appears reversible through re-adding edges.
From the tool's definition Tool description states 'Remove one or all directed edges between two memory nodes' — this modifies the graph structure of stored memories by deleting connections, which is reversible graph manipulation rather than deletion of data nodes themselves.
Attacks that exploit this kind of access
Remove one or all directed edges between two memory nodes. It is categorised as a Write tool in the Arca MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arca MCP server in PolicyLayer and add a rule for disconnect: 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 Arca MCP. Nothing to install.
disconnect 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 disconnect 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 disconnect. 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.
disconnect is provided by the Arca MCP server (m0nochr0me/arca-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 →