Black_Wall remote MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Black_Wall remote MCPCheck payment risk for 0.05 USDC on base to 0x1234"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Black_Wall remote MCP
A hosted remote MCP (Model Context Protocol over HTTP) that gives any MCP-capable agent a pre-signature payment-risk verdict — with no install and no signup. Add one URL and your agent can ask, before it signs an x402 payment, "should I pay this?" and get GO / HOLD / STOP — from counterparty settlement reputation, price-anomaly (quoted vs the payee's own median), and OFAC sanctions — plus a third-party-verifiable Ed25519 signed receipt.
Add it
Point your MCP client at:
https://mcp.blackwalltier.comTransport: Streamable HTTP. No API key. Verdicts for amounts under $10 at
risk are free; at or above that, the tool returns an x402 payment challenge
your agent settles from its own wallet (pass the settled payment back as an
X-PAYMENT header, then retry).
Related MCP server: crest-verify
The tool: forecast_payment
field | ||
| string, required | recipient wallet from the 402 |
| string, required | decimal string, e.g. |
| string, required | e.g. |
| string, required | e.g. |
| optional | binds settlement / context |
Returns a verdict (GO/HOLD/STOP) + reasons + signals, and a
signed_receipt anyone can verify against the published key at
https://agent-egress-proxy.onrender.com/.well-known/blackwall-receipt-key.json
(any RFC 8032 Ed25519 library) — Black_Wall never has to be in the loop.
How it works
This Worker is a thin transport + proxy: it speaks minimal MCP JSON-RPC
(initialize / tools/list / tools/call / ping) and forwards
forecast_payment calls to the Black_Wall x402 oracle. All decision logic and
the receipt come from the oracle unchanged.
Fail-closed by design: if the oracle errors, is unreachable, or returns a
non-verdict, the tool returns an error — never a phantom GO. A payment
guardrail that can't reach its backend must not imply "safe to pay."
Registry
Published to the official MCP Registry as
com.blackwalltier/blackwall-x402-guardrail.
Develop
node test.mjs # unit tests (mocked oracle)
npx wrangler dev # run locally
npx wrangler deploy # deploy (Cloudflare Workers)By BlueTier. Verdict only — never takes custody, never in the settlement path. No evidence is not trust.
This server cannot be deployed
Maintenance
Related MCP Connectors
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
Preflight x402 payment compatibility with structured risk evidence and remediation guidance.
Pre-trade token risk scoring API for Base tokens, paid via x402.
Pre-transaction token risk checks for autonomous agents on six chains. Read-only; paid via x402.
Related MCP Servers
- AlicenseAqualityFmaintenanceCounterparty risk scoring for agentic commerce. Scores wallets, domains, IPs, and companies 0-100 before AI agents transact via x402 micropayments on Base147 PyPI3MIT
- AlicenseNot gradedqualityDmaintenanceVerify x402 endpoints before your agent spends. Three tools: verify (SPEND/CAUTION/INVESTIGATE/DO NOT SPEND backed by 50K+ services), passport (full trust identity), risk_check (deep assessment). No API keys, no signup.12 npmMIT
- FlicenseNot gradedqualityCmaintenanceProvides counterparty risk checks for any EVM address, returning malicious-history flags, tiered risk scoring, and plain-language summaries via x402 payment.-
- AlicenseAqualityCmaintenanceMCP server for assessing counterparty risk in x402 payments using on-chain data, providing risk scores, decisions, and wallet spending policies to prevent fraud and unauthorized payments.1026 npm1MIT