Skip to content

Probity Wallet Reputation MCP server

ai.probitylabs/wallet-reputationprobitylabs.aistreamable-httpv1.0.4Scanned

Pre-transaction risk screening for Ethereum addresses: signed score, sanctions, audit trail.

7 tools: 1 change things and 6 only read.

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

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes 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 Probity Wallet Reputation MCP server can do

The Probity Wallet Reputation MCP server is published by probitylabs.ai, a domain the MCP Registry verified. It has 7 tools. It can create or change data (1 tool: screen_address), but cannot delete data. 6 tools only read.

2 tools bring in text other people can write (screen_address and get_screening_narrative).

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 10, 2026, version 1.0.4.

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.

7 tools

Changes things 1Claude Code: ask
  • screen_addressScreen an Ethereum address or `.eth` ENS name for on-chain reputation risk.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
    Screen an Ethereum address or `.eth` ENS name for on-chain reputation risk. Costs 1 credit. Returns a signed reputation score (-100 to +100), a risk band, a confidence level, a sanctioned flag, the top evidence factors, a screeningId, and a link to the full report. The enhanced review is generated in the background. Fetch it with get_screening_narrative(screeningId). Use the score, band, and sanctioned flag to gate pre-trade or payout flows.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
Only reads 6Show 6 read-only tools
  • compare_screening_runsCompare two completed screens by their screeningId and see what changed.No findings

    Why it is in this group

    • The name "compare_screening_runs" says "compare": a word for reading.
    Description, as the server wrote it
    Compare two completed screens by their screeningId and see what changed. Costs zero credits. Two runs of the same address show why the reputation score moved. Two different addresses show a side by side. Returns each run score, band, and confidence, a reason level diff, and the score change broken into its drivers. Small differences between runs of one address can be normal variation rather than a data change.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_address_screening_historyRetrieve the authenticated user's prior screening runs for a specific Ethereum address, each with the same detail as screen_address: reputation score, band, confidence, sanctioned …No findings

    Why it is in this group

    • The name "get_address_screening_history" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve the authenticated user's prior screening runs for a specific Ethereum address, each with the same detail as screen_address: reputation score, band, confidence, sanctioned flag, and the top evidence signals. Use it to recall context for an already-screened address. Costs zero credits, unlike screen_address which always runs a fresh screen. For runs across all your addresses, use get_screening_history.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_credit_balanceReturns the authenticated user's current credit balance as a whole number of credits.No findings

    Why it is in this group

    • The name "get_credit_balance" says "get": a word for reading.
    Description, as the server wrote it
    Returns the authenticated user's current credit balance as a whole number of credits. One credit screens one address: screen_address costs 1 credit, while this call and the history, narrative, and compare tools cost zero. Check it before screen_address to confirm a screen can be afforded.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_monitoring_eventsReturns the authenticated user's monitoring events: material reputation changes detected on their monitored addresses, oldest first, each with the change type, a summary, and the b…No findings

    Why it is in this group

    • The name "get_monitoring_events" says "get": a word for reading.
    Description, as the server wrote it
    Returns the authenticated user's monitoring events: material reputation changes detected on their monitored addresses, oldest first, each with the change type, a summary, and the band transition. Also returns a deterministic digest that rolls up the window into one sentence. Page forward by passing the returned nextCursor as cursor. Bound the window with since and until, or restrict to one address with address. Costs zero credits.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_screening_historyReturns the authenticated user's most recent screening runs across all addresses, newest first, each with the same detail as screen_address: score, band, confidence, sanctioned fla…No findings

    Why it is in this group

    • The name "get_screening_history" says "get": a word for reading.
    Description, as the server wrote it
    Returns the authenticated user's most recent screening runs across all addresses, newest first, each with the same detail as screen_address: score, band, confidence, sanctioned flag, and the top evidence signals. Returns up to `limit` runs (default 20), so raise `limit` to reach older runs. Costs zero credits. For the history of one specific address, use get_address_screening_history instead.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_screening_narrativeRetrieve the enhanced Probity review for a completed screen by its screeningId.Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe description's first sentence says "retrieve" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Retrieve the enhanced Probity review for a completed screen by its screeningId. Costs zero credits. Returns the narrative and the key concerns it raises. It is generated in the background after screen_address returns, so it may briefly be pending. Retry shortly if so.

    Annotations the server declares

    • readOnlyHint: 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 write2
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 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
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.probitylabs.ai/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.probitylabs.ai
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

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

    Matched text

    https://mcp.probitylabs.ai/mcp: tools/list returned 7 tools to an anonymous client, including screen_address (write)

    What this check looks for

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. Tools6 changed.~6 changedView diff

Install

Pinned to version 1.0.4. Values in angle brackets are yours to fill in.

claude mcp add --transport http wallet-reputation https://mcp.probitylabs.ai/mcp
claude mcp add --transport http wallet-reputation https://mcp.probitylabs.ai/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__wallet-reputation__get_screening_narrative",
      "mcp__wallet-reputation__get_address_screening_history",
      "mcp__wallet-reputation__compare_screening_runs",
      "mcp__wallet-reputation__get_screening_history",
      "mcp__wallet-reputation__get_monitoring_events",
      "mcp__wallet-reputation__get_credit_balance"
    ],
    "ask": [
      "mcp__wallet-reputation__screen_address"
    ],
    "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 wallet-reputation. Review it before you use it.

Capability tags behind 2 rules
  • mcp__wallet-reputation__screen_address untrusted-input
  • mcp__wallet-reputation__get_screening_narrative 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.probitylabs/wallet-reputation/verify?hash=b8f7d8c30f2bd3305766bb576e3be1d8513ba4f3769a69cb498c4187c34d7aec" | jq -e '.changed == false'

Pinned hash b8f7d8c30f2b, from Nov 10, 2026, 13:18 UTC.

Watch

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

https://radar.anlyon.com/servers/ai.probitylabs/wallet-reputation/changes.xml

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

Badge

Anlyon Radar badge for ai.probitylabs/wallet-reputation
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.probitylabs/wallet-reputation.svg)](https://radar.anlyon.com/servers/ai.probitylabs/wallet-reputation)

Source: MCP Registry. Synced Oct 29, 2026, 05:17 UTC.

Probity Wallet Reputation MCP server: questions and answers

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

Is the Probity Wallet Reputation MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 1 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 Probity Wallet Reputation MCP server delete data?

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

Can the Probity Wallet Reputation 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 Probity Wallet Reputation MCP server have?

7 tools: 1 write, 6 read. screen_address, get_screening_narrative, get_address_screening_history, compare_screening_runs, get_screening_history, get_monitoring_events and get_credit_balance.

Does the Probity Wallet Reputation MCP server need sign-in or OAuth?

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

Does the Probity Wallet Reputation MCP server send data to outside services?

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

Has the Probity Wallet Reputation MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 29, 2026. Every change is on this page and in its Atom feed.