# Probity Wallet Reputation (remote · mcp.probitylabs.ai)

Screen an Ethereum address or ENS name for on-chain reputation risk, sanctions, and reasoning.

- Trust score: 83/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-12

## Components

- remote · `mcp.probitylabs.ai`: 83/100 (this document), [markdown](https://verifymcp.io/servers/ai-probitylabs-wallet-reputation/mcp.md), [page](https://verifymcp.io/servers/ai-probitylabs-wallet-reputation/mcp)

## Channel facts

- Endpoint: `https://mcp.probitylabs.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-12.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 773 tokens (~128/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (83% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-probitylabs-wallet-reputation https://mcp.probitylabs.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-probitylabs-wallet-reputation]
url = "https://mcp.probitylabs.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-probitylabs-wallet-reputation": {
      "type": "remote",
      "url": "https://mcp.probitylabs.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-probitylabs-wallet-reputation --url https://mcp.probitylabs.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-probitylabs-wallet-reputation:
    url: "https://mcp.probitylabs.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-probitylabs-wallet-reputation": {
      "type": "http",
      "url": "https://mcp.probitylabs.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-11 (score 83, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-09 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-07 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-05 (score 79, +1)

- [security] Tool “get_address_screening_history” rewrote its description, which is the text the model reads
- [security] Tool “get_screening_history” rewrote its description, which is the text the model reads
- [security] Tool “get_credit_balance” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 50% → 83%
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Tool “get_address_screening_history” now declares an output schema
- [functional improvement] Tool “get_screening_history” now declares an output schema
- [cosmetic] “compare_screening_runs” reworded the description of “runIdA”
- [cosmetic] “compare_screening_runs” reworded the description of “runIdB”
- [cosmetic] “get_screening_narrative” reworded the description of “screeningId”
- [cosmetic] “screen_address” reworded the description of “address”

### 2026-08-04 (score 78)

First indexed and scored.

## MCP tools (6)

### `screen_address` (~167 tokens)

Screen address

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.

Input parameters:

- `address` (string, required): Ethereum address (0x...) or `.eth` ENS name (e.g. vitalik.eth) to screen. ENS names resolve to their current mainnet address and must resolve or the call errors. Addresses are case-insensitive and ne…

Output parameters:

- `address` (string): The screened address
- `band` (string): Reputation band, e.g. Low Risk, Reputable
- `bandCode` (string): Band identifier, e.g. LOW_RISK, REPUTABLE
- `confidence` (string): Engine confidence in the result
- `evidence` (array): Up to 10 signals behind the verdict, most severe first
- `reportUrl` (string): Link to the full report on the Probity dashboard
- `sanctioned` (boolean): True if the address is a direct OFAC match
- `score` (number): Signed reputation score from -100 to +100. Lower is worse.
- `screenedAt` (string): When the screen ran (ISO-8601)
- `screeningId` (string): Immutable identifier for this screen (rsr_...)
- `summary` (string): One line verdict headline
- `transactionCount` (integer): Number of transactions analysed

### `get_screening_narrative` (~103 tokens)

Get screening narrative

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.

Input parameters:

- `screeningId` (string, required): The rsr_... id returned by screen_address. Must reference a completed screen; the narrative can be pending for a few seconds right after the screen returns.

Output parameters:

- `address` (string): The screened address
- `concerns` (array): Key concerns raised by the review
- `narrative` (string): The enhanced review text
- `reportUrl` (string): Link to the full report on the Probity dashboard
- `screeningId` (string): The screen this review belongs to

### `get_address_screening_history` (~136 tokens)

Get address screening history

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.

Input parameters:

- `address` (string, required): Ethereum address (0x...) or .eth ENS name to look up historic screenings for
- `limit` (integer): Number of past runs to return (1-50, default 5, newest first)

Output parameters:

- `items` (array): Recent screening runs, newest first, each with the same detail as screen_address

### `compare_screening_runs` (~138 tokens)

Compare screening runs

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.

Input parameters:

- `runIdA` (string, required): First screeningId (rsr_...). Must be a completed screen you own.
- `runIdB` (string, required): Second screeningId (rsr_...). Must be a completed screen you own.

Output parameters:

- `compositionDiff` (array): Which score drivers differ between the runs
- `mode` (string): temporal_delta when both runs are the same address, else side_by_side
- `reasonDiff` (object): What changed between the two runs at the reason level
- `runA` (object)
- `runB`
- `scoreDelta` (number): runA score minus runB score

### `get_screening_history` (~114 tokens)

Get screening history

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) with no cursor paging, so raise `limit` to reach older runs. Costs zero credits. For the history of one specific address, use get_address_screening_history instead.

Input parameters:

- `limit` (integer): Number of results (1-100, default 20)

Output parameters:

- `items` (array): Recent screening runs, newest first, each with the same detail as screen_address

### `get_credit_balance` (~64 tokens)

Get credit balance

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.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-probitylabs-wallet-reputation/mcp#diagnostics

## Score history

- 2026-08-12: 83
- 2026-08-11: 83
- 2026-08-10: 81
- 2026-08-09: 81
- 2026-08-08: 80
- 2026-08-07: 80
- 2026-08-06: 79
- 2026-08-05: 79
- 2026-08-04: 78

## Links

- Remote endpoint: https://mcp.probitylabs.ai/mcp
- Website: https://www.probitylabs.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-probitylabs-wallet-reputation/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-probitylabs-wallet-reputation/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-probitylabs-wallet-reputation/mcp