Skip to content

AuthiChain MCP server

com.authichain/authichainauthichain.comstreamable-httpv1.4.0Scanned

Verification of signed records, plus an EU DPP check.

8 tools: 1 can delete or cancel things, 5 change things and 2 only read.

Tools: 1 delete, 0 irreversible, 5 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 5
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • 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 AuthiChain MCP server can do

The AuthiChain MCP server is published by authichain.com, a domain the MCP Registry verified. It has 8 tools. It can delete or cancel things (1 tool: verify) and create or change data (5 tools: verify_attestation, verify_record, dpp_readiness_check, scan_living_qr and 1 more). 2 tools only read.

5 tools bring in text other people can write (verify, query_provenance, verify_attestation and 2 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

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

Last scanned Nov 20, 2026, version 1.4.0.

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.

8 tools

Deletes or cancels 1Claude Code: deny
  • verifyx402 paid seal-registry verification; use only after separate payment authorization, not for free lookup.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
    x402 paid seal-registry verification; use only after separate payment authorization, not for free lookup. Arguments that cannot be a seal UUID are HTTP 400 before payment. Empty arguments are unpaid HTTP 402. Paid calls are answered from the seal registry at $0.05 USDC on Base. For free verification use verify_record.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
Changes things 5Claude Code: ask
  • dpp_readiness_checkFree informational EU Digital Product Passport readiness questionnaire; this cannot issue a passport or certify compliance.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
    Free informational EU Digital Product Passport readiness questionnaire; this cannot issue a passport or certify compliance. Returns a 0-100 score, gaps, and the dated obligation for the product category (battery passport is law from 18 Feb 2027; other categories are ESPR targets). Not legal advice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • negotiateFree, read-only, non-binding agent-to-agent capability/price-class quote.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
    Free, read-only, non-binding agent-to-agent capability/price-class quote. Returns available service, free vs separately authorized paid rail, and next step; never accepts terms, creates a commitment, transfers money, or calls an external service. This is NOT MCP initialize version negotiation.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • scan_living_qrFree.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 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.
    Description, as the server wrote it
    Free. Read an existing Living QR presentation, not a QR generator or x402 purchase. Scan a stored Living QR. GET https://authichain.com/qron/r/{object_id} returns AuthiChain Verification Decision v1. This host verifies the signature. A missing id is presentation_not_found. Not an x402 payment endpoint, and it does not inspect a physical product.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • verify_attestationFree.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 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.
    Description, as the server wrote it
    Free. Use when verifying a registry-published attestation, not a supplied offline protocol record. Fetch the exact published AuthiChain v0.1 JWS from the signed-record registry and pass it to the canonical edge-router verifier. Checks signature, issuer trust, durable revocation/status, expiry, and signed decision. Supply expectedObjectId to bind the record to a scanned object identifier. A valid signed claim alone does not prove physical authenticity.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • verify_recordFree.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 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.
    Description, as the server wrote it
    Free. Use for a supplied signed protocol record or demonstration record, not published JWS issuer-status checks. Verify an AuthiChain signed provenance record with the open reference verifier. Pass id "polygon-anchor-1" for the published demonstration record, or pass your own record and anchor JSON. Returns verified, valid-unanchored, or invalid, plus whether the transaction carries the record hash. It does not inspect a physical product.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
Only reads 2Show 2 read-only tools
  • get_pricingFree.No findings

    Why it is in this group

    • The name "get_pricing" says "get": a word for reading.
    Description, as the server wrote it
    Free. Quotes without charging or authorizing payment the live x402 agent rail ($0.05 USDC on Base) and live human Stripe checkouts: $29 Starter Pack (100 generations, paid once) at https://authichain.com/checkout/starter and $299 EU DPP Readiness at https://authichain.com/checkout/dpp_readiness. One-time pack credits (Starter and Creator) never expire.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • query_provenanceFree registry and published-pack lookup for an assetId / seal / QR token; use for discovery, not proof of authenticity.Reads text others writeNo findings

    Why it is in this group

    • The name "query_provenance" says "query": a word for reading.

    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
    Free registry and published-pack lookup for an assetId / seal / QR token; use for discovery, not proof of authenticity. Reads matching rows from the canonical auth_seals registry when public Supabase configuration is available, and also resolves published packs. A registry match means registered only; it does not verify a signature or prove a physical item is genuine. Use verify_attestation for a published v0.1 JWS; verify_record is the separate reference-protocol verifier.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true

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 write5
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 15, 2026, 13:22 UTC, unchanged since Nov 15, 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
6
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 6 tools that change things (1 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://authichain.com/mcp: tools/list returned 8 tools to an anonymous client, including verify (destructive), verify_attestation (write), verify_record (write), dpp_readiness_check (write), scan_living_qr (write) and 1 more

    What this check looks for

Posture changes

  1. Nov 15, 2026
    • Tools that change things, listed without credentials: 5 to 6
  2. Oct 31, 2026
    • Tools that change things, listed without credentials: 4 to 5

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

  1. Tools1 added, 7 changed.+1 added~7 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 6.View diff
    • Tools that change things, listed without credentials: 5 to 6
  3. Tools1 added, 3 changed.+1 added~3 changedView diff
  4. PostureRemote posture changed. Tools that change things, listed without credentials: 4 -> 5.View diff
    • Tools that change things, listed without credentials: 4 to 5

Install

Pinned to version 1.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http authichain https://authichain.com/mcp
claude mcp add --transport http authichain https://authichain.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__authichain__get_pricing",
      "mcp__authichain__query_provenance"
    ],
    "ask": [
      "mcp__authichain__verify_attestation",
      "mcp__authichain__verify_record",
      "mcp__authichain__dpp_readiness_check",
      "mcp__authichain__scan_living_qr",
      "mcp__authichain__negotiate"
    ],
    "deny": [
      "mcp__authichain__verify"
    ]
  }
}

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 authichain. Review it before you use it.

Capability tags behind 5 rules
  • mcp__authichain__verify untrusted-input
  • mcp__authichain__query_provenance untrusted-input
  • mcp__authichain__verify_attestation untrusted-input
  • mcp__authichain__verify_record untrusted-input
  • mcp__authichain__scan_living_qr 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/com.authichain/authichain/verify?hash=4fe8e44bed28a8d08f31ec848c3189d953556a89cf2bebfc4e15f87f859d2d45" | jq -e '.changed == false'

Pinned hash 4fe8e44bed28, from Nov 20, 2026, 05:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.authichain/authichain/changes.xml

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

Badge

Anlyon Radar badge for com.authichain/authichain
[![Anlyon Radar](https://radar.anlyon.com/badge/com.authichain/authichain.svg)](https://radar.anlyon.com/servers/com.authichain/authichain)

Source: MCP Registry · repository. Synced Nov 6, 2026, 05:17 UTC.

AuthiChain MCP server: questions and answers

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

Is the AuthiChain MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 6 of which can change, send or delete something, and 0 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 AuthiChain MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: verify.

Can the AuthiChain MCP server 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 AuthiChain MCP server have?

8 tools: 1 destructive, 5 write, 2 read. verify, verify_attestation, verify_record, dpp_readiness_check, scan_living_qr, negotiate, get_pricing and query_provenance.

Does the AuthiChain MCP server need sign-in or OAuth?

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

Does the AuthiChain MCP server send data to outside services?

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

Has the AuthiChain MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.