Skip to content

ruthven MCP server

ai.ruthven/ruthvenruthven.aistreamable-httpv1.1.0Scanned

Artwork provenance and works for sale: Origin Passports, Ethereum proofs, listings with proof

10 tools: 4 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 4 write, 6 read.
  • Reads private data · 2
  • Reads text others write · 1
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

4 tools here change 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 ruthven MCP server can do

The ruthven MCP server is published by ruthven.ai, a domain the MCP Registry verified. It has 10 tools. It can create or change data (4 tools: ruthven_verify_claim, ruthven_ask, ruthven_agent_stage_records and ruthven_for_sale), but cannot delete data. 6 tools only read.

2 tools read private data (ruthven_get_asset and ruthven_list_evidence); 1 tool brings in text other people can write (ruthven_list_evidence).

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 once since Anlyon Radar first saw them.

Last scanned Nov 8, 2026, version 1.1.0.

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.

10 tools

Changes things 4Claude Code: ask
  • ruthven_agent_stage_recordsThe acquisition records of a collection's AI Agents stage (ADR-010): every application as the stage's signer recorded it — the operator's signed declaration, the wallet, the ERC-80…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
    The acquisition records of a collection's AI Agents stage (ADR-010): every application as the stage's signer recorded it — the operator's signed declaration, the wallet, the ERC-8004 identity and its on-chain check, the quantity, the permission's salt and signer, the time — each hashed and a leaf of a Merkle root the collection's owner commits to the RuthvenAnchor registry on Ethereum. With record_id, one record with its proof and the steps to check it against the chain without trusting RUTHVEN. Records are operator-declared; the root proves a record is the one recorded, not that a statement in it is true. No model is involved.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ruthven_askAsk a question about one asset.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
    Ask a question about one asset. Returns structured JSON only: an answer, claims (each with a verification state and the evidence ids it rests on), unknowns, the full cited evidence records, and follow-up questions. Never a valuation; never a recommendation to act.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ruthven_for_saleWhich works of a collection can be bought right now on the open market (the artist's own listings and collectors' resales), as the marketplace reports them: token, ask, expiry, the…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
    Which works of a collection can be bought right now on the open market (the artist's own listings and collectors' resales), as the marketplace reports them: token, ask, expiry, the listing's order hash and protocol address, and for each work its Origin Passport, its record and its proof — plus the exact steps to check the work and fill the listing from your own wallet, and what holding a work earns (a free RUTHVEN Origin Passport for an artwork you own). Without a collection, lists the collections that have a market answer. RUTHVEN values nothing, recommends nothing and is not a party to any sale.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ruthven_verify_claimGiven the evidence ids a claim rests on, return the state the claim earns (the weakest among them), each record's hash and location, and how to check it independently of RUTHVEN.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
    Given the evidence ids a claim rests on, return the state the claim earns (the weakest among them), each record's hash and location, and how to check it independently of RUTHVEN. Deterministic; no model is involved.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 6Show 6 read-only tools
  • ruthven_describeWhat RUTHVEN is and what an agent may do with it: the verification states, the permission model (READ and ANALYSE only), the asset types (live and placeholder), and the JSON API en…No findings

    Why it is in this group

    • The name "ruthven_describe" says "describe": a word for reading.
    Description, as the server wrote it
    What RUTHVEN is and what an agent may do with it: the verification states, the permission model (READ and ANALYSE only), the asset types (live and placeholder), and the JSON API endpoints.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ruthven_get_assetThe universal RUTHVEN asset record: identity, tokenization, provenance, source works, components, construction sequence, hashes, documents, rights, verified / contextual / inferred…Reads private dataNo findings

    Why it is in this group

    • The name "ruthven_get_asset" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "document": it reads documents.
    Description, as the server wrote it
    The universal RUTHVEN asset record: identity, tokenization, provenance, source works, components, construction sequence, hashes, documents, rights, verified / contextual / inferred facts, unknowns, and counts. Claims carry evidence ids; pass include_evidence=true for the full evidence records as well (large).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ruthven_get_evidenceRetrieve the source record behind a stable evidence id (EVID-…) or an unknown id (UNK-…): where it was read from, its hash, its state, and how fresh it is.No findings

    Why it is in this group

    • The name "ruthven_get_evidence" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve the source record behind a stable evidence id (EVID-…) or an unknown id (UNK-…): where it was read from, its hash, its state, and how fresh it is.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ruthven_get_proofA Merkle proof that evidence records are part of the issued Origin Passport, with the entry each rests on and the steps to check it without trusting RUTHVEN: SHA-256 over the entry…No findings

    Why it is in this group

    • The name "ruthven_get_proof" says "get": a word for reading.
    Description, as the server wrote it
    A Merkle proof that evidence records are part of the issued Origin Passport, with the entry each rests on and the steps to check it without trusting RUTHVEN: SHA-256 over the entry, keccak256 up the proof, and the root compared with the one in the published Passport. It proves that the record contains the entry; it does not make a statement true. With neither evidence_ids nor paths, returns the paths that can be proved. Deterministic; no model is involved.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ruthven_get_provenanceProvenance and lineage: the timeline, source works, generated elements, components, the construction sequence, relationships, chain identity, tokenization, and the evidence graph (…No findings

    Why it is in this group

    • The name "ruthven_get_provenance" says "get": a word for reading.
    Description, as the server wrote it
    Provenance and lineage: the timeline, source works, generated elements, components, the construction sequence, relationships, chain identity, tokenization, and the evidence graph (cut_from, placed_as, pinned_as, pictured_by, hash_of).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ruthven_list_evidenceThe evidence records behind an asset, each with a stable evidence_id, its source (document, locator, ipfs uri, gateway url, ledger claim id), a SHA-256, a verification state and fr…Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "document": it reads documents.
    • untrusted-inputThe description's first sentence says "uri": it reads web pages, which anyone can write.
    Description, as the server wrote it
    The evidence records behind an asset, each with a stable evidence_id, its source (document, locator, ipfs uri, gateway url, ledger claim id), a SHA-256, a verification state and freshness timestamps. Filter by status (VERIFIED, CONTEXT, INFERRED), type, kind, or a text query.

    Annotations the server declares

    • 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 outbound.

Reads private data2
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 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, 18:27 UTC, unchanged since Oct 29, 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
4
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://ruthven.ai/api/ruthven/mcp: tools/list returned 10 tools to an anonymous client, including ruthven_verify_claim (write), ruthven_ask (write), ruthven_agent_stage_records (write), ruthven_for_sale (write)

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 3 to 4

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

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ruthven https://ruthven.ai/api/ruthven/mcp
claude mcp add --transport http ruthven https://ruthven.ai/api/ruthven/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__ruthven__ruthven_get_asset",
      "mcp__ruthven__ruthven_list_evidence",
      "mcp__ruthven__ruthven_get_evidence",
      "mcp__ruthven__ruthven_get_provenance",
      "mcp__ruthven__ruthven_get_proof",
      "mcp__ruthven__ruthven_describe"
    ],
    "ask": [
      "mcp__ruthven__ruthven_verify_claim",
      "mcp__ruthven__ruthven_ask",
      "mcp__ruthven__ruthven_agent_stage_records",
      "mcp__ruthven__ruthven_for_sale"
    ],
    "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 ruthven. Review it before you use it.

Capability tags behind 2 rules
  • mcp__ruthven__ruthven_get_asset private-data
  • mcp__ruthven__ruthven_list_evidence private-data, 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/ai.ruthven/ruthven/verify?hash=0649edda015e2fab3ee6cd084f26bc1c4d2998b79ba7e7d5bf7b33e2ef8d2f47" | jq -e '.changed == false'

Pinned hash 0649edda015e, from Nov 8, 2026, 21:17 UTC.

Watch

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

https://radar.anlyon.com/servers/ai.ruthven/ruthven/changes.xml

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

Badge

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

Source: MCP Registry · repository. Synced Oct 23, 2026, 16:24 UTC.

ruthven MCP server: questions and answers

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

Is the ruthven MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 4 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 ruthven MCP server delete data?

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

Can the ruthven 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 ruthven MCP server have?

10 tools: 4 write, 6 read. ruthven_verify_claim, ruthven_ask, ruthven_agent_stage_records, ruthven_for_sale, ruthven_get_asset, ruthven_list_evidence, ruthven_get_evidence, ruthven_get_provenance and 2 more.

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

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

Does the ruthven MCP server send data to outside services?

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

Has the ruthven MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 23, 2026. Every change is on this page and in its Atom feed.