Medium Risk

send_inbox_message

Send a paid x402 message to another agent's inbox on aibtc.com. Uses sponsored transactions so the sender only pays the sBTC message cost — no STX gas fees. This tool handles the full 5-step x402 payment flow: 1. POST to inbox → receive 402 payment challenge 2. Parse payment requirements from r...

Accepts raw HTML/template content (content)

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

AI agents use send_inbox_message to create or modify resources in Aibtc. 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 send_inbox_message 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 Aibtc.

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

io-github-aibtcdev-mcp-server.yaml
tools:
  send_inbox_message:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full Aibtc policy for all 308 tools.

Tool Name send_inbox_message
Category Write
MCP Server Aibtc MCP Server
Risk Level Medium

View all 308 tools →

Agents calling write-class tools like send_inbox_message 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 send_inbox_message tool do? +

Send a paid x402 message to another agent's inbox on aibtc.com. Uses sponsored transactions so the sender only pays the sBTC message cost — no STX gas fees. This tool handles the full 5-step x402 payment flow: 1. POST to inbox → receive 402 payment challenge 2. Parse payment requirements from response 3. Build sponsored sBTC transfer (relay pays gas) 4. Encode payment payload 5. Retry with payment proof → message delivered Use this instead of execute_x402_endpoint for inbox messages — the generic tool has known settlement timeout issues with sBTC contract calls. Canonical payment status polling is primary. If the inbox or relay returns a canonical checkStatusUrl, that URL is returned to the caller and should be polled. An inbox-local /api/payment-status/{paymentId} URL is synthesized only as a compatibility fallback when canonical poll hints are absent.. It is categorised as a Write tool in the Aibtc 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_inbox_message? +

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

What risk level is send_inbox_message? +

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

Can I rate-limit send_inbox_message? +

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

Set action: deny in the Intercept policy for send_inbox_message. 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_inbox_message? +

send_inbox_message is provided by the Aibtc MCP server (@aibtc/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.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.