Medium Risk

connect_remote

Connect to a remote ACDP coordination server on another machine. Use this when you need to coordinate with agents running on a different computer. You will need the server IP/hostname and the secret token (found in acdp-socket-server/config.json on the remote machine). ASK THE USER for these valu...

Accepts URL/endpoint input (url); Handles credentials or secrets (token)

Part of the Acdp MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents use connect_remote to create or modify resources in Acdp. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call connect_remote repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Acdp.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

acdp.yaml
tools:
  connect_remote:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full Acdp policy for all 9 tools.

Tool Name connect_remote
Category Write
MCP Server Acdp MCP Server
Risk Level Medium

View all 9 tools →

Agents calling write-class tools like connect_remote have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

What does the connect_remote tool do? +

Connect to a remote ACDP coordination server on another machine. Use this when you need to coordinate with agents running on a different computer. You will need the server IP/hostname and the secret token (found in acdp-socket-server/config.json on the remote machine). ASK THE USER for these values if you do not have them.. It is categorised as a Write tool in the Acdp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on connect_remote? +

Add a rule in your Intercept YAML policy under the tools section for connect_remote. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Acdp MCP server.

What risk level is connect_remote? +

connect_remote is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit connect_remote? +

Yes. Add a rate_limit block to the connect_remote rule in your Intercept 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.

How do I block connect_remote completely? +

Set action: deny in the Intercept policy for connect_remote. 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.

What MCP server provides connect_remote? +

connect_remote is provided by the Acdp MCP server (acdp-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

Currently onboarding teams running MCP in production.
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.

// REQUEST EARLY ACCESS

We're letting people in as fast as we can.

You're in the queue.

We'll be in touch as soon as we can let you in.