backchannel_start

THE RISK

High Risk

Why backchannel_start needs a policy

This tool triggers external operations — sending a push notification to the Nubank app or dispatching an OTP SMS — which are real-world side effects that depend on arguments. It initiates an authorization flow that will be completed later, making it an Execute-class action. While it touches financial authorization, it does not itself move money or commit a financial obligation; it only starts a pre-auth handshake.

From the tool's definition 'Start a CIBA / OTP pre-authorization for a shopper. Sends a push to Nubank app (CIBA) or triggers an OTP SMS.'

Documented attack patterns abuse exactly the kind of access backchannel_start gives an agent:

POLICY

How to control backchannel_start

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for backchannel_start:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "backchannel_start": {
      "limits": [
        {
          "counter": "backchannel_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

backchannel_start stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Mcp Ap2 — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Mcp Ap2 tools

Financial authorize_transaction Authorize a transaction (reserve funds without capturing) via Braintree GraphQL authorizeP Financial block_card Block a card temporarily (reversible). Use for lost-card or fraud-suspected flows. Card st Financial cancel_bill Cancel a pending bill Financial cancel_collection Cancel a scheduled collection request Financial cancel_credit Cancel an authorized-but-uncaptured credit payment. Financial cancel_debit Cancel a debit-card payment by Getnet payment_id. Financial cancel_invoice Cancel/void an authorized invoice (FECancel — limited to certain types/conditions) Financial cancel_order Cancel an order, optionally restocking and refunding

All 1300 Mcp Ap2 tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Mcp Ap2 → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about backchannel_start

What does the backchannel_start tool do? +

Start a CIBA / OTP pre-authorization for a shopper. Sends a push to Nubank app (CIBA) or triggers an OTP SMS. Returns an auth_req_id/ticket to complete later. It is categorised as a Execute tool in the Mcp Ap2 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on backchannel_start? +

Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for backchannel_start: 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 Ap2. Nothing to install.

What risk level is backchannel_start? +

backchannel_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit backchannel_start? +

Yes. Add a rate_limit block to the backchannel_start 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 backchannel_start completely? +

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

backchannel_start is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Ap2 tool call.

Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →