Skip to content

com.midax402/mcp

by midax402.com · remote · no sign-in to list tools · v1.0.0 · published by com.midax402

Pay-per-query x402 business intelligence on Base, settled in USDC via the native 402 payment flow.

Final · 1Changes · 2

5 tools: 1 do something that can't be undone, 2 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http midax402 https://mcp.midax402.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Can't be undone 1Claude Code: ask
  • verify_before_payThe question to ask BEFORE paying any x402 service: does MIDAX have a signed conformance verdict for this URL?Can send data outNo findings

    Why it is in this group

    • The name "verify_before_pay" says "pay": a word that usually means money moves, which cannot be taken back.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    The question to ask BEFORE paying any x402 service: does MIDAX have a signed conformance verdict for this URL? FREE, ONE call. Returns the verdict with its age and freshness if one exists in MIDAX's signed registry, plus the authenticity verdict when that feature ships (always present in the payload, null with a note until then). If nothing exists yet, says so plainly and returns the exact price and route for the next paid step -- never a vague 'contact us'. Reads MIDAX's own registry only: it never probes the target live, so it adds minimal latency to your payment decision.
Changes things 2Claude Code: ask
  • get_market_verdictRuns a paid MIDAX402 analysis tier.No findings

    Why it is in this group

    • The name "get_market_verdict" says "get": a word for reading.
    • The description's first verb is "run": a word for a change.
    Description, as the server wrote it
    Runs a paid MIDAX402 analysis tier. Payment is x402-native: called WITHOUT payment_signature it returns the HTTP 402 payment requirements (decoded + raw PAYMENT-REQUIRED header) for your x402-capable wallet to sign; call again WITH payment_signature (the signed payment proof, as sent in the PAYMENT-SIGNATURE header) to receive the full analysis. This server NEVER holds keys and never signs — your wallet does.
  • verifyChecks x402 protocol conformance for a target service URL: a live 402 probe (well-formed challenge, non-empty accepts, atomic-unit amounts) plus price coherence against the target'…Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Checks x402 protocol conformance for a target service URL: a live 402 probe (well-formed challenge, non-empty accepts, atomic-unit amounts) plus price coherence against the target's own well-known. PAID ($0.10 USDC via x402). This MCP server holds no wallet, so calling this tool returns the upstream payment requirements rather than a result — pay them with your own x402 client, or call the endpoint directly. A signed, permanently published attestation of the same check is available at /midas-ops/attest ($0.50). Does NOT measure output quality, uptime history, or on-chain transaction volume — see the returned scope_note.
Only reads 2Claude Code: allow
  • get_sampleFree sample of MIDAX402's analysis: returns ONLY the calibrated verdict and confidence score for an x402-ecosystem question, plus pointers to the paid tiers that serve the full ana…No findings

    Why it is in this group

    • The name "get_sample" says "get": a word for reading.
    Description, as the server wrote it
    Free sample of MIDAX402's analysis: returns ONLY the calibrated verdict and confidence score for an x402-ecosystem question, plus pointers to the paid tiers that serve the full analysis. Rate-limited; the full analysis is the paid product.
  • list_tiersLists the paid analysis tiers with their CANONICAL prices, fetched live from https://midax402.com/.well-known/x402 (resource_details) — the same first-party source directories craw…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_tiers" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "directory": it reads files.
    • untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Lists the paid analysis tiers with their CANONICAL prices, fetched live from https://midax402.com/.well-known/x402 (resource_details) — the same first-party source directories crawl, so it can never drift.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

2 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 untrusted-input tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__midax402__list_tiers"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 14:36 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
none
Authorization servers
none
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.midax402.com/mcp: tools/list returned 5 tools to an anonymous client, including verify_before_pay (irreversible), get_market_verdict (write), verify (write)

    What this check looks for

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http midax402 https://mcp.midax402.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__midax402__list_tiers",
      "mcp__midax402__get_sample"
    ],
    "ask": [
      "mcp__midax402__get_market_verdict",
      "mcp__midax402__verify",
      "mcp__midax402__verify_before_pay"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as midax402. Review it before you use it.

Capability tags behind 3 rules
  • mcp__midax402__list_tiers private-data, untrusted-input
  • mcp__midax402__verify outbound
  • mcp__midax402__verify_before_pay outbound