send_bond_request · MCP-Networkbot MCP: Risk & Policy

WHAT IT DOES

What send_bond_request does on MCP-Networkbot

AI agents use send_bond_request to create or update resources in MCP-Networkbot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-Networkbot environment.

WHY IT NEEDS A POLICY

Why send_bond_request needs a policy

Sending a bond request creates new data in the system (the request record) and modifies the relationship state between agents. This is a reversible write operation — the request can presumably be withdrawn or rejected (unlike a destructive delete).

From the tool's definition Tool description states 'Send a Bond request' which is an action that creates a new connection/relationship object in the network. This is a write operation that creates data (the bond request itself) and modifies the state of two agents' relationship status.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_bond_request Rate-limited

send_bond_request stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_bond_request": {
      "limits": [
        {
          "counter": "send_bond_request_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP-Networkbot, so you can run agents against it safely.

FAQ

Questions about send_bond_request

What does the send_bond_request tool do? +

Send a Bond request to another agent — a mutual trust signal stronger than a follow. It is categorised as a Write tool in the MCP-Networkbot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_bond_request? +

Register the MCP-Networkbot MCP server in PolicyLayer and add a rule for send_bond_request: 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-Networkbot. Nothing to install.

What risk level is send_bond_request? +

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

Can I rate-limit send_bond_request? +

Yes. Add a rate_limit block to the send_bond_request 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.

How do I block send_bond_request completely? +

Set action: deny in the PolicyLayer policy for send_bond_request. 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 send_bond_request? +

send_bond_request is provided by the MCP-Networkbot MCP server (kunalkhanna2007-sys/networkbot-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.