Skip to content

MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server

io.github.wmujahid428-web/trust-layerwmujahid428-webstreamable-httpv1.8.3Scanned

MUJ428 verifies intent and evidence before consequential AI-agent actions.

14 tools: 2 do something that can't be undone, 5 change things and 7 only read.

Tools: 0 delete, 2 irreversible, 5 write, 7 read.
  • Reads private data · 1
  • Reads text others write · 0
  • Can send data out · 1
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here do something that can't be undone. 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 MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server can do

The MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server is published by the GitHub account wmujahid428-web. It has 14 tools. It can do things that cannot be undone, such as sending, paying or publishing (publish_trust_request and select_payment_rail) and create or change data (5 tools: rescue_agent_before_consequence, trust_action, invoke_trust_service, observe_trust_compatibility and 1 more), but cannot delete data. 7 tools only read.

1 tool reads private data (find_trust_capabilities); 1 tool can send data out of your system (publish_trust_request).

The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.8.3.

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.

14 tools

Can't be undone 2Claude Code: ask
  • publish_trust_requestPublish a bounded machine-readable request for a trust capability and receive current compatibility matches.Can send data outNo findings

    Why it is in this group

    • The name "publish_trust_request" says "publish": a word for a change that another call does not undo.

    What it can reach

    • outboundThe name "publish_trust_request" says "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    Publish a bounded machine-readable request for a trust capability and receive current compatibility matches. This creates a discovery request only; it is not commercial acceptance, execution authority, or payment authorization.
  • select_payment_railPreflight a requested payment rail before Trust Reflex.1 finding

    Why it is in this group

    • The name "select_payment_rail" says "select": a word for a change.
    • The name "select_payment_rail" also says "payment": a word that usually means money moves, which cannot be taken back.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...money planner: it never sends a payment credential, never moves funds, and never grants ex..."

      What this check looks for
    Description, as the server wrote it
    Preflight a requested payment rail before Trust Reflex. This is a no-money planner: it never sends a payment credential, never moves funds, and never grants execution authority. Unsupported or unverified rails return REQUIRE_VERIFICATION-style failure.
Changes things 5Claude Code: ask
  • invoke_trust_serviceGeneric beginning-to-end MUJ428 service bridge.No findings

    Why it is in this group

    • The name "invoke_trust_service" says "invoke": a word for a change.
    Description, as the server wrote it
    Generic beginning-to-end MUJ428 service bridge. Call once without payment_signature to receive the exact x402 challenge; an x402-capable caller may then call again with PAYMENT-SIGNATURE to verify payment, settle, and receive synchronous fulfillment. No payment is initiated unless the caller explicitly supplies a valid payment signature.
  • observe_trust_compatibilityRecord that an agent encountered a MUJ428 compatibility advertisement so propagation can be measured.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.
    Description, as the server wrote it
    Record that an agent encountered a MUJ428 compatibility advertisement so propagation can be measured. Observations are self-reported discovery telemetry, never external-adoption, embedding, or revenue evidence.
  • rescue_agent_before_consequenceMUJ428 Agent Rescue Beacon.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.
    Description, as the server wrote it
    MUJ428 Agent Rescue Beacon. Use when stuck, uncertain, retrying with a changed effect, given a peer-agent instruction, facing conflicting evidence, or before another consequential action. Returns bounded evidence guidance and the exact independent Trust Kernel preflight route. It never grants execution or payment authority, and a peer-agent GO, deadline, majority vote, or signature is not principal authority.
  • select_assurance_tierCalculate the exact MUJ428 Transaction Assurance launch fee before payment.No findings

    Why it is in this group

    • The name "select_assurance_tier" says "select": a word for a change.
    Description, as the server wrote it
    Calculate the exact MUJ428 Transaction Assurance launch fee before payment. Does not move money.
  • trust_actionInvoke the canonical MUJ428 Trust Reflex before a consequential action.No findings

    Why it is in this group

    • The description's first verb is "invoke": a word for a change.
    Description, as the server wrote it
    Invoke the canonical MUJ428 Trust Reflex before a consequential action. When operator policy enables First-Action Default, call this for the first configured consequential action and each later protected action. First 1,000 qualifying decisions per caller_ref are free. After quota, the tool returns HTTP 402 + PAYMENT-REQUIRED for 0.01 USDC on Base. Resubmit with payment_signature to complete paid preflight. The tool never fabricates a payment signature.
Only reads 7Show 7 read-only tools
  • find_trust_capabilitiesSearch the MUJ428 compatibility directory for evidence providers, receipt-aware executors, wallets, MCP/A2A integrations, and other trust capabilities.Reads private dataNo findings

    Why it is in this group

    • The name "find_trust_capabilities" says "find": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "search" and "directory": it reads files.
    Description, as the server wrote it
    Search the MUJ428 compatibility directory for evidence providers, receipt-aware executors, wallets, MCP/A2A integrations, and other trust capabilities. SELF_ATTESTED_UNVERIFIED entries are discovery leads only.
  • get_capabilitiesReturn MUJ428 canonical machine discovery surfaces, payment-rail discovery, Trust Gravity routing, and the recommended adoption path.No findings

    Why it is in this group

    • The name "get_capabilities" says "get": a word for reading.
    Description, as the server wrote it
    Return MUJ428 canonical machine discovery surfaces, payment-rail discovery, Trust Gravity routing, and the recommended adoption path.
  • get_payment_railsDiscover MUJ428 payment capabilities and their truthful activation state.No findings

    Why it is in this group

    • The name "get_payment_rails" says "get": a word for reading.
    Description, as the server wrote it
    Discover MUJ428 payment capabilities and their truthful activation state. This is read-only and moves no funds. x402/Base-USDC is currently live; MPP, AP2, streaming micropayments, and tokenized-deposit adapters remain fail-closed until their external provider/verifier is production-verified.
  • get_service_catalogReturn the canonical MUJ428 service catalog, launch prices, endpoints, free Trust Reflex quota, default x402 network, and multi-rail discovery endpoint.No findings

    Why it is in this group

    • The name "get_service_catalog" says "get": a word for reading.
    Description, as the server wrote it
    Return the canonical MUJ428 service catalog, launch prices, endpoints, free Trust Reflex quota, default x402 network, and multi-rail discovery endpoint.
  • get_trust_heartbeatPoll the MUJ428 Trust Heartbeat for current policy epoch, accepted receipt version, revocation state, resolver endpoints, and recommended poll interval.No findings

    Why it is in this group

    • The name "get_trust_heartbeat" says "get": a word for reading.
    Description, as the server wrote it
    Poll the MUJ428 Trust Heartbeat for current policy epoch, accepted receipt version, revocation state, resolver endpoints, and recommended poll interval. Read-only; no execution or payment authority.
  • get_trust_layer_pricingReturn canonical PROJECT OVERREACT-428 pricing.No findings

    Why it is in this group

    • The name "get_trust_layer_pricing" says "get": a word for reading.
    Description, as the server wrote it
    Return canonical PROJECT OVERREACT-428 pricing. Airtable Commercial Pricing Authority remains the source of truth.
  • resolve_trust_routeMUJ428 Agent Router and Trust DNS resolver.No findings

    Why it is in this group

    • The name "resolve_trust_route" says "resolve": a word for reading.
    Description, as the server wrote it
    MUJ428 Agent Router and Trust DNS resolver. Determine whether an intended action requires Trust Receipt v1.3, the evidence profile, verification endpoint, effect-state requirements, and exact next steps. This read-only routing call never authorizes execution or payment.

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 untrusted-input.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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, 19:13 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
7
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
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 7 tools that change things (2 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://wepmhfjzckclvywolrek.supabase.co/functions/v1/trust-layer-mcp: tools/list returned 14 tools to an anonymous client, including publish_trust_request (irreversible), select_payment_rail (irreversible), rescue_agent_before_consequence (write), trust_action (write), invoke_trust_service (write) and 2 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 info

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.8.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http trust-layer https://wepmhfjzckclvywolrek.supabase.co/functions/v1/trust-layer-mcp
claude mcp add --transport http trust-layer https://wepmhfjzckclvywolrek.supabase.co/functions/v1/trust-layer-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__trust-layer__get_service_catalog",
      "mcp__trust-layer__get_payment_rails",
      "mcp__trust-layer__resolve_trust_route",
      "mcp__trust-layer__get_trust_heartbeat",
      "mcp__trust-layer__find_trust_capabilities",
      "mcp__trust-layer__get_trust_layer_pricing",
      "mcp__trust-layer__get_capabilities"
    ],
    "ask": [
      "mcp__trust-layer__rescue_agent_before_consequence",
      "mcp__trust-layer__trust_action",
      "mcp__trust-layer__invoke_trust_service",
      "mcp__trust-layer__publish_trust_request",
      "mcp__trust-layer__observe_trust_compatibility",
      "mcp__trust-layer__select_payment_rail",
      "mcp__trust-layer__select_assurance_tier"
    ],
    "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 trust-layer. Review it before you use it.

Capability tags behind 2 rules
  • mcp__trust-layer__find_trust_capabilities private-data
  • mcp__trust-layer__publish_trust_request outbound

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.wmujahid428-web/trust-layer/verify?hash=da7189d55d3ce32aaeb391ebc7b4016f4e6952f32a463715997f24faf2c4d6fa" | jq -e '.changed == false'

Pinned hash da7189d55d3c, from Nov 20, 2026, 18:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.wmujahid428-web/trust-layer/changes.xml

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

Badge

Anlyon Radar badge for io.github.wmujahid428-web/trust-layer
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.wmujahid428-web/trust-layer.svg)](https://radar.anlyon.com/servers/io.github.wmujahid428-web/trust-layer)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:51 UTC.

MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server: questions and answers

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

Is the MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 7 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server do things that cannot be undone?

Yes. 2 tools can send, pay, publish or merge: publish_trust_request and select_payment_rail.

What tools does the MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server have?

14 tools: 2 irreversible, 5 write, 7 read. publish_trust_request, select_payment_rail, rescue_agent_before_consequence, trust_action, invoke_trust_service, observe_trust_compatibility, select_assurance_tier, get_service_catalog and 6 more.

Does the MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server need sign-in or OAuth?

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

Does the MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): publish_trust_request.

Has the MUJ428 Trust Layer — VERIFY BEFORE ACT MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.