Skip to content

mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments

io.github.Timwal78/mcp-x402Timwal78streamable-httpv2.3.0Scanned

85+ pay-per-call MCP tools: trading, federal grants/contracts, SEC, FTD. x402 USDC/RLUSD. No keys.

15 tools: 5 can delete or cancel things, 6 change things and 4 only read.

Tools: 5 delete, 0 irreversible, 6 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 9
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

5 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments can do

The mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments is published by the GitHub account Timwal78. It has 15 tools. It can delete or cancel things (5 tools: interfere, leviathan_interfere, spend_gate_check, omnilist_run and 1 more) and create or change data (6 tools: precross_analyze, regime_scan_board, regime_scan_ticker, sml_xray_bars and 2 more). 4 tools only read.

9 tools bring in text other people can write (interfere, leviathan_interfere, spend_gate_check and 6 more).

The fixed checks matched 2 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 16, 2026, version 2.3.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Deletes or cancels 5Claude Code: deny
  • interfereCoherent Gate (PAID, x402/USDC).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Coherent Gate (PAID, x402/USDC). Scores whether your trading-signal paths agree: confidence-weighted long/short/flat consensus, coherence 0-1, and a pass/block gate (pass needs a non-flat consensus and coherence at or above the threshold, default 0.6). Tiers by path count: scout ≤4 $0.01, standard ≤8 $0.05, beast ≤32 $0.25 (defaults). The $0.25 max tier is charged upfront; on the x402 rail the unused difference is recorded as owed (not yet auto-refunded); on the Arc escrow rail (arc_auth_id) only the used tier is captured. Optional ticker pulls extra paths from registered sources before charging. Max 32 paths. Not financial advice.

    Annotations the server declares

    • title: Score Signal Coherence — Coherent Gate
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • leviathan_interfereCoherent Gate + Leviathan (PAID, x402/USDC).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Coherent Gate + Leviathan (PAID, x402/USDC). Fetches the SML Leviathan signal (squeeze, momentum, or all) for a ticker, adds it as one path with your optional paths and registered sources, then runs the same coherence check as interfere: consensus, coherence 0-1, pass/block gate. Same tiers and billing as interfere ($0.25 max tier charged upfront; x402 difference recorded as owed, Arc rail captures only the used tier). If Leviathan is unavailable it continues on the other paths; with no paths it errors before charging. Max 32 paths. Not financial advice.

    Annotations the server declares

    • title: Score Coherence with Leviathan Signal
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • omnigate_runtime_executeOMNIGATE Runtime (PAID, USDC).Reads text others writeNo findings

    Why it is in this group

    • The name "omnigate_runtime_execute" says "execute": a word for a change.
    • The input takes a statement or command to run (input.script), which can change anything it can reach.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    OMNIGATE Runtime (PAID, USDC). Run ONE JavaScript script that calls many SML tools, in one round trip, instead of one model turn per tool call. The script is the body of an async function: `const r = await sml.call("<route-id>", { query: {...} }); return r.data;`. Available inside: sml.call, sml.tools.search, sml.tools.get, sml.budget, sml.sleep, sml.log, sml.input. Every call is metered at its live registry price against budget_usdc, charged only on upstream 2xx, and tagged with source + response sha256; a failed upstream throws TruthError (nothing charged, nothing substituted). Unused budget is returned as credit. Returns result, per-call provenance, billing and an Ed25519-signed receipt id. Without payment it returns the x402 challenge (amount = budget). Pay with payment_header (Base USDC, x402 v2), credit_token (smlrt_…), or arc_auth_id (Arc escrow, when enabled). Sandbox: no network except sml.call, no fs, 32MB, 20s CPU, 120s wall (sync).

    Annotations the server declares

    • title: Run a paid multi-tool script — OMNIGATE Runtime
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • omnilist_runOmniList (PAID $1.00 USDC on Base via x402).Reads text others writeNo findings

    Why it is in this group

    • The name "omnilist_run" says "run": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    OmniList (PAID $1.00 USDC on Base via x402). File-once listing run for an x402 server or MCP server: give ONE server record and OmniList presence-checks it, files it where it is missing, and reads back a receipt at x402-list, 402index, x402dash, nohumans.directory and the MCP Registry (PREPARED artifact there — publishing needs the namespace owner's own key). Every venue is free to file; the $1.00 pays for the run, the venue know-how, and the verified per-venue report (states: FILED with receipt id, PENDING_REVIEW, ALREADY_PRESENT by read-back, PREPARED, BLOCKED with the exact reason). Runs execute live against third-party venues, so this tool starts the run and returns a run_id; fetch the finished report with omnilist_report or GET /x402/omnilist/runs/<run_id>. Use for: getting a new x402/MCP server into the directories agents actually browse. Don't use when: you expect a guaranteed listing (venue review decisions belong to the venues) or a free run (there is none — unpaid calls return the payment challenge). Settlement to the canonical SML payTo on Base.

    Annotations the server declares

    • title: File Once, List to All — OmniList
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • spend_gate_checkSpend Gate (PAID $0.005 USDC on Base via x402).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Spend Gate (PAID $0.005 USDC on Base via x402). Advisory payment assessment — no wallet signing or spending by the buyer: a real Provider Trust approval and price cap are mandatory; explicit package/history rejections block. Four distinct decision inputs vote pay-side/reject-side — provider_trust (Provider Trust verify_provider) and payload_safety (ScriptDocs vulnerability check, only when manifest_url names an npm/PyPI/crates package) — both vote with real verdicts via the fleet operator lane at $0 upstream toll, price_sanity (quote vs caller policy_cap_usdc or the v1 default cap table; cap-only in v1, no historical median), delivery_history (this host's OmniGate settlement/delivery ledger). Coherence = |Σ w·d| / Σ w with d=+1 pay-side, −1 reject-side, w=confidence; gate_pass requires a positive Provider Trust decision, a real within-cap quote, no explicit safety or delivery-history rejection, coherence ≥ 0.6, and a pay-side consensus. The verdict is advisory, not payment authorization. Paths with no data abstain (no_signal) and contribute nothing. Only on a gate pass does Jev review run (noul act probability + pay/reject/quarantine choice, model + token usage returned). Use for: vetting a payee/invoice immediately before an agent wallet pays it. Don't use when: you need an actual payment executed (this is a check, it moves no funds), a trading signal (use interfere), or a free lookup (there is none — unpaid calls return the payment challenge). Settlement to the canonical SML payTo on Base.

    Annotations the server declares

    • title: Check Before an Agent Wallet Pays — Spend Gate
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
Changes things 6Claude Code: ask
  • omnigate_runtime_receiptOMNIGATE Runtime receipt (FREE).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    OMNIGATE Runtime receipt (FREE). Returns a run receipt — script sha256, payer, rail, payment tx, every upstream call with request/response hashes and charges, outcome — signed with Ed25519 and hash-chained to the previous receipt, plus a verification of signature, body hash and chain link. Use it to prove what an agent ran and paid for.

    Annotations the server declares

    • title: Get and verify an OMNIGATE Runtime receipt
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • omnilist_reportOmniList run report (free read-back).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    OmniList run report (free read-back). Fetch the per-venue report of an omnilist_run by its run_id: states (FILED / PENDING_REVIEW / ALREADY_PRESENT / PREPARED / BLOCKED), receipt ids, live URLs and any PREPARED artifacts with publish instructions.

    Annotations the server declares

    • title: OmniList Run Report
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • precross_analyzeSML PRECROSS (PAID $0.02 USDC on Base via x402).Reads text others write1 finding

    Why it is in this group

    • The name "precross_analyze" says "analyze": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "precross_analyze" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "precross_analyze" says "analyze": a word for reading.

      What this check looks for
    Description, as the server wrote it
    SML PRECROSS (PAID $0.02 USDC on Base via x402). 11/64 EMA cross intelligence for US stocks and ETFs on 1H or 4H (regular session) or 1D bars — derived analysis, not raw bars. Returns the exact price at which the 11 and 64 EMA cross on the next bar (closed-form, plus a zero-lag variant), the move needed to reach it in % and ATR, whether the EMAs are converging and an estimated bars-to-cross, and a walk-forward self-backtest of anticipating that cross (in-sample config selection, out-of-sample verdict, costs both sides, confirmed-cross baseline for comparison) with a six-check proof gate per side; on 1H/4H the grid also tests a "daily agrees" filter (daily 11/64 trend, no lookahead). Also returns a 75-ticker basket proof (pooled out-of-sample trades across US stocks and funds incl. gold, silver, Bitcoin and Ethereum funds, with breadth check and standout ranking) and a plain-English summary. A long/short setup is returned ONLY for a side whose out-of-sample results pass the gate (this ticker's own gate, or the basket gate when the ticker is in the basket); otherwise the direction is withheld and the reason is given. Use for: knowing where an 11/64 EMA cross will trigger before it prints, and whether anticipating it has actually worked on this ticker and timeframe. Don't use when: you need raw OHLC bars, timeframes below 1H, spot crypto, or order execution (this tool places no orders). Research output, not financial advice.

    Annotations the server declares

    • title: Where Will the 11/64 EMA Cross? — SML PRECROSS
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • regime_scan_boardSML REGIME SCAN board (PAID $0.05 USDC on Base via x402).Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    SML REGIME SCAN board (PAID $0.05 USDC on Base via x402). Dynamic scan of the most liquid US stocks and ETFs (no hard-coded watchlist: every US listing from the last completed session, filtered by price ≥ $5, volume ≥ 500k and dollar volume ≥ $25M, top ~400 by dollar volume). Reads the regime first (ADX + Choppiness → TREND / RANGE / TRANSITION), then one indicator per family — EMA21/50, SuperTrend+DMI, RSI+MACD, ATR/BB-width/squeeze, OBV+CMF+RVOL, Donchian/52w, CHOP/ER/Z/RS-vs-SPY, universe breadth — and returns the 15–25 tickers where the families agree. Each ticker: setup (TREND_CONTINUATION, TREND_PULLBACK, BREAKOUT, SQUEEZE_COIL, RANGE_STRETCH), bias, score 0–100, tier, trigger, invalidation, next level, reward-to-risk, RVOL, ATR%, a one-line why, the setup type's measured history on the scanned tickers (5/10-day forward move, +1R-before-invalidation rate, sample count), and a live price vs levels during market hours. Starts with a one-sentence `answer`. Completed daily bars only; nothing repaints. Use for: a ranked, ready-to-reason shortlist of US equities with aligned technicals today. Don't use when: you need raw bars or quotes, intraday timeframes, crypto spot, or order execution. Describes conditions; not buy/sell instructions or financial advice.

    Annotations the server declares

    • title: Which US Stocks Have Aligned Technicals Today? — SML REGIME SCAN
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • regime_scan_tickerSML REGIME SCAN single ticker (PAID $0.02 USDC on Base via x402).Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    SML REGIME SCAN single ticker (PAID $0.02 USDC on Base via x402). Same engine as regime_scan_board for any one US stock or ETF, on the board or not: regime, all 8 family readings with their vote, setup (or why there is none), score, the checks that passed and the ones missing, trigger / invalidation / next level, the setup type's measured history and the live price vs levels. Starts with a one-sentence `answer`. Use for: checking one ticker against the regime-first, one-per-family stack. Don't use when: you need raw OHLC, intraday bars, crypto spot, or execution. Not financial advice.

    Annotations the server declares

    • title: Regime + One-Per-Family Read for One Ticker — SML REGIME SCAN
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • sml_xray_barsOWNER-ONLY private feed for the Script Master Labs First Candle X-RAY app.Reads text others write1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The input schema at properties.access_key.description mentions "credential".

      Matched text

      inputSchema.properties.access_key.description: "Owner credential."

      What this check looks for
    Description, as the server wrote it
    OWNER-ONLY private feed for the Script Master Labs First Candle X-RAY app. Requires the owner access key; returns nothing without it. Not a public data product and not for agents: public agents should use regime_scan_ticker or precross_analyze for derived analysis.

    Annotations the server declares

    • title: SML X-RAY owner history feed
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 4Show 4 read-only tools
  • sml_discoverFind the x402 Gateway contract and where to inspect fresh payment requirements.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    Find the x402 Gateway contract and where to inspect fresh payment requirements. FREE.

    Annotations the server declares

    • title: Discover SML x402 Gateway
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • sml_statusCheck the public x402 Gateway identity and canonical payment rail.No findings

    Why it is in this group

    • The name "sml_status" says "status": a word for reading.
    Description, as the server wrote it
    Check the public x402 Gateway identity and canonical payment rail. FREE.

    Annotations the server declares

    • title: Inspect SML Gateway Status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • x402_contractInspect the canonical x402 payment contract.No findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.
    Description, as the server wrote it
    Inspect the canonical x402 payment contract. Returns network, USDC asset, payTo, headers, and the rule for resolving fresh target requirements. FREE.

    Annotations the server declares

    • title: Inspect x402 Contract
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write9
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:00 UTC, unchanged since Nov 20, 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
12
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
yes
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 12 tools that change things (5 destructive, 7 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp-x402.onrender.com/mcp: tools/list returned 15 tools to an anonymous client, including interfere (destructive), leviathan_interfere (destructive), spend_gate_check (destructive), omnilist_run (destructive), omnigate_runtime_execute (destructive) and 7 more

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 11 to 12
  2. Nov 13, 2026
    • Tools that change things, listed without credentials: 8 to 11
  3. Nov 6, 2026
    • Tools that change things, listed without credentials: 5 to 8
  4. Oct 29, 2026
    • Tools that change things, listed without credentials: 0 to 5

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info
  • The server marks "precross_analyze" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "precross_analyze" says "analyze": a word for reading.

    What this check looks for
  • The input schema at properties.access_key.description mentions "credential".

    Matched text

    inputSchema.properties.access_key.description: "Owner credential."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 11 -> 12.View diff
    • Tools that change things, listed without credentials: 11 to 12
  2. Tools6 added.+6 addedView diff
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 8 -> 11.View diff
    • Tools that change things, listed without credentials: 8 to 11
  4. PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 8.View diff
    • Tools that change things, listed without credentials: 5 to 8
  5. Tools6 added.+6 addedView diff
  6. PostureRemote posture changed. Tools that change things, listed without credentials: 0 -> 5.View diff
    • Tools that change things, listed without credentials: 0 to 5

Install

Pinned to version 2.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http x402 https://mcp-x402.onrender.com/mcp
claude mcp add --transport http x402 https://mcp-x402.onrender.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__x402__sml_discover",
      "mcp__x402__sml_status",
      "mcp__x402__x402_contract",
      "mcp__x402__omnigate_runtime_search"
    ],
    "ask": [
      "mcp__x402__precross_analyze",
      "mcp__x402__regime_scan_board",
      "mcp__x402__regime_scan_ticker",
      "mcp__x402__sml_xray_bars",
      "mcp__x402__omnilist_report",
      "mcp__x402__omnigate_runtime_receipt"
    ],
    "deny": [
      "mcp__x402__interfere",
      "mcp__x402__leviathan_interfere",
      "mcp__x402__spend_gate_check",
      "mcp__x402__omnilist_run",
      "mcp__x402__omnigate_runtime_execute"
    ]
  }
}

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 x402. Review it before you use it.

Capability tags behind 9 rules
  • mcp__x402__interfere untrusted-input
  • mcp__x402__leviathan_interfere untrusted-input
  • mcp__x402__spend_gate_check untrusted-input
  • mcp__x402__precross_analyze untrusted-input
  • mcp__x402__regime_scan_board untrusted-input
  • mcp__x402__regime_scan_ticker untrusted-input
  • mcp__x402__sml_xray_bars untrusted-input
  • mcp__x402__omnilist_run untrusted-input
  • mcp__x402__omnigate_runtime_execute untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Timwal78/mcp-x402/verify?hash=a759ea9ff3acfc1baf162a6c64d58852472413dd08cada142f5cc44f22a224be" | jq -e '.changed == false'

Pinned hash a759ea9ff3ac, from Nov 16, 2026, 06:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.Timwal78/mcp-x402/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.Timwal78/mcp-x402
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Timwal78/mcp-x402.svg)](https://radar.anlyon.com/servers/io.github.Timwal78/mcp-x402)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:21 UTC.

mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments: questions and answers

Answered from the scan above, not from the publisher's description.

Is the mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments safe?

No scan can promise that. What its definitions show: 15 tools, 11 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments delete data?

Yes. 5 tools can delete, cancel or revoke something: interfere, leviathan_interfere, spend_gate_check, omnilist_run and omnigate_runtime_execute.

Can the mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments have?

15 tools: 5 destructive, 6 write, 4 read. interfere, leviathan_interfere, spend_gate_check, omnilist_run, omnigate_runtime_execute, precross_analyze, regime_scan_board, regime_scan_ticker and 7 more.

Does the mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.