# Verdict: the due-diligence house for DeFi (npm · verdict-finance-mcp)

Verdict, the due-diligence house for DeFi: keyless ratings, methodology and a hack incident feed.

- Trust score: 82/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- npm · `verdict-finance-mcp`: 82/100 (this document), [markdown](https://verifymcp.io/servers/charles-verdict-verdict-finance-mcp/verdict-finance-mcp.md), [page](https://verifymcp.io/servers/charles-verdict-verdict-finance-mcp/verdict-finance-mcp)

## Channel facts

- Registry: `npm`
- Package: `verdict-finance-mcp`
- Version: `0.4.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-09-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 23 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1895 tokens (~236/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 93/100
  - Stability observed for 28 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Verdict: the due-diligence house for DeFi MCP server?

Verdict: the due-diligence house for DeFi runs locally as an npm package, launched with npx -y verdict-finance-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add charles-verdict-verdict-finance-mcp -- npx -y verdict-finance-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "charles-verdict-verdict-finance-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "verdict-finance-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "charles-verdict-verdict-finance-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "verdict-finance-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add charles-verdict-verdict-finance-mcp -- npx -y verdict-finance-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "charles-verdict-verdict-finance-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "verdict-finance-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add charles-verdict-verdict-finance-mcp --command npx --arg -y --arg verdict-finance-mcp
```

### Hermes

```yaml
mcp_servers:
  charles-verdict-verdict-finance-mcp:
    command: "npx"
    args: ["-y", "verdict-finance-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "charles-verdict-verdict-finance-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "verdict-finance-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add charles-verdict-verdict-finance-mcp -t stdio -c npx -a -y verdict-finance-mcp
```

### Other

```json
{
  "mcpServers": {
    "charles-verdict-verdict-finance-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "verdict-finance-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-09-21 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (8)

### `search_ratings` (~138 tokens)

Search Verdict ratings

Verdict (the due-diligence house for DeFi) rates DeFi across 7 entity types: protocol, chain, token, oracle, vault, organisation, bridge. Search those ratings by name or keyword, and pass entity_type to narrow to one type. Returns matching entities with their letter grade + composite score. Example: search_ratings({ query: 'aave' }).

Input parameters:

- `entity_type` (string): Optional: restrict to one entity type. Omit to search all 7 types at once.
- `query` (string, required): Name or keyword to search for, e.g. 'aave' or 'chainlink'.

### `get_rating` (~142 tokens)

Get a Verdict rating

Get the Verdict rating for one DeFi entity: letter grade, composite score 0-100, and public metadata. Identify it by slug (e.g. 'aave-v4') or UUID. Keyless. For the per-domain scores behind the grade, use get_rating_breakdown. Example: get_rating({ entity_type: 'protocol', identifier: 'aave-v4' }).

Input parameters:

- `entity_type` (string, required): The kind of entity: protocol, chain, token, oracle, vault, organisation, or bridge.
- `identifier` (string, required): The entity's slug (e.g. 'aave-v4' or 'ethereum') or UUID.

### `list_ratings` (~149 tokens)

List / browse Verdict ratings

Browse Verdict's DeFi ratings for one entity type, optionally filtered by category or chain. Returns entities with their letter grade + composite score, best-rated first. Example: list_ratings({ entity_type: 'protocol', category: 'lending' }).

Input parameters:

- `category` (string): Optional category filter, lowercase, e.g. 'lending'.
- `chain` (string): Optional chain filter by chain slug, e.g. 'ethereum' or 'base'.
- `entity_type` (string, required): The kind of entity to browse: protocol, chain, token, oracle, vault, organisation, or bridge.
- `limit` (integer): Max results (default 25, cap 50).

### `quantum_readiness` (~121 tokens)

Post-quantum readiness (LayerQu)

Post-quantum cryptographic readiness for blockchains, data by LayerQu. With a chain slug: that chain's QRI (0-100), readiness band, migration stage, and hybrid-signature status. Without a slug: the full league table of 72+ chains, including ones Verdict has not rated. Companion data only - never part of a Verdict grade. Example: quantum_readiness({ chain: 'ethereum' }).

Input parameters:

- `chain` (string): Optional chain slug (e.g. 'ethereum'). Omit for the full league table.

### `get_recent_incidents` (~541 tokens)

Recent hack incidents

Hack incidents across DeFi, newest first. Every incident is corroborated by more than one public hack-reporting source before it appears, so the feed lags the first rumour of an exploit by design and is not a real-time exploit alarm. Incidents carry a confidence tier in `status`: corroborated, then confirmed. By default only confirmed incidents are returned, which is exactly the set this tool has always returned; pass min_status: 'corroborated' to also see multi-source leads that have not yet reached confirmation. Poll with `since` set to the newest detected_at you have already seen. An incident that escalates keeps its incident_id and refreshes its detected_at, so the same id reappears at the top of a `since` poll at its new tier: key on incident_id and expect to see an incident more than once as it climbs. A tier never goes down in the feed. Covers protocols, including ones Verdict does not rate: `matched_protocol` says whether the incident matched a rated protocol, and matching re-runs when an incident escalates and its payload improves, so matched_protocol reads as of the incident's current tier; it is still never retroactive when Verdict's own coverage grows. An incident is a signal to look, never an automatic downgrade: a matched entity may be flagged under review, but re-rating is always a human decision, so do not infer a grade change from an incident appearing here. Examples: get_recent_incidents({ limit: 10 }), get_recent_incidents({ since: '2026-08-01T00:00:00Z' }), get_recent_incidents({ min_status: 'corroborated' }).

Input parameters:

- `limit` (integer): Optional maximum number of incidents to return (default 25, cap 200).
- `min_status` (string): Optional lowest confidence tier to return. Omit for the default of confirmed, which is the same set this tool has always returned. Pass 'corroborated' to also see multi-source leads that have not yet…
- `since` (string): Optional ISO datetime (e.g. '2026-08-01T00:00:00Z'). Returns only incidents detected after it. Use the timestamp of the newest incident you have already seen to poll for what is new.
- `slug` (string): Optional Verdict protocol slug (e.g. 'aave-v4'). Exact match, not a search.

### `get_rating_breakdown` (~158 tokens)

Domain breakdown behind a rating

The per-domain scores behind one entity's Verdict grade: which domains carried the rating and which dragged it down, alongside the intrinsic (pre-dependency) pair. Needs an API key: set VERDICT_API_KEY in this server's environment. Without one this tool answers with where to get a key, and get_rating still returns the headline grade and composite score keylessly. Example: get_rating_breakdown({ entity_type: 'protocol', slug: 'aave-v4' }).

Input parameters:

- `entity_type` (string, required): The kind of entity: protocol, chain, token, oracle, vault, organisation, or bridge.
- `slug` (string, required): The entity's slug, e.g. 'aave-v4' or 'ethereum'.

### `get_methodology` (~82 tokens)

How Verdict scores

The published Verdict ratings methodology: how many testable criteria each entity type is scored on, which domains those criteria sit in, and the AAA to D grade scale with the composite-score band each grade needs. Read this to explain or sanity-check a grade rather than guessing at what it measures. No arguments, no API key. Example: get_methodology({}).

### `request_coverage` (~212 tokens)

Request Verdict coverage

Ask Verdict to rate an entity it does not cover yet, and get a reference id back. Requesting coverage never buys a grade or moves one: ratings stay independent, and the resulting rating is public either way, readable by anyone through these tools. The team replies to the email address you pass, so ask the user for a real one first. Example: request_coverage({ entity_name: 'Morpho Blue', entity_type: 'protocol', contact_email: 'team@example.com' }).

Input parameters:

- `contact_email` (string, required): Email the Verdict team replies to. Ask the user for it; never invent one.
- `entity_name` (string, required): The entity to cover, as it is publicly known, e.g. 'Morpho Blue'.
- `entity_type` (string, required): What kind of entity it is: protocol, chain, token, oracle, vault, organisation, or bridge.
- `note` (string): Optional context: links, chains it is live on, why it matters, any deadline.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/charles-verdict-verdict-finance-mcp/verdict-finance-mcp#diagnostics

## Score history

- 2026-09-21: 82
- 2026-09-20: 81
- 2026-09-19: 81
- 2026-09-18: 80
- 2026-09-17: 80
- 2026-09-16: 79
- 2026-09-15: 79
- 2026-09-14: 78
- 2026-09-13: 78
- 2026-09-12: 77
- 2026-09-11: 77
- 2026-09-10: 77
- 2026-09-09: 76
- 2026-09-08: 76
- 2026-09-07: 75
- 2026-09-06: 75
- 2026-09-05: 74
- 2026-09-04: 74
- 2026-09-03: 73
- 2026-09-02: 73
- 2026-09-01: 72
- 2026-08-31: 72
- 2026-08-30: 71
- 2026-08-29: 71
- 2026-08-28: 70
- 2026-08-27: 71
- 2026-08-26: 70
- 2026-08-25: 68
- 2026-08-24: 69

## Common questions

### What is the Verdict: the due-diligence house for DeFi MCP server?

Verdict: the due-diligence house for DeFi is an MCP server listed in the public MCP registry as io.github.charles-verdict/verdict-finance-mcp. Verdict, the due-diligence house for DeFi: keyless ratings, methodology and a hack incident feed. This page covers its npm package (verdict-finance-mcp).

### Is the Verdict: the due-diligence house for DeFi MCP server safe to use?

Verdict: the due-diligence house for DeFi scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Verdict: the due-diligence house for DeFi MCP server expose?

Verdict: the due-diligence house for DeFi exposes 8 tools: search_ratings, get_rating, list_ratings, quantum_readiness, get_recent_incidents, and 3 more. Their descriptions and schemas cost roughly 1,543 tokens of context every time the server is loaded.

### Is the Verdict: the due-diligence house for DeFi MCP server still maintained?

Verdict: the due-diligence house for DeFi is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Verdict: the due-diligence house for DeFi MCP server under?

Verdict: the due-diligence house for DeFi declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/verdict-finance-mcp
- Socket report: https://socket.dev/npm/package/verdict-finance-mcp
- Repository: https://github.com/Verdict-Capital/verdict-finance-mcp
- Website: https://www.verdict.finance/
- Changelog RSS feed: https://verifymcp.io/servers/charles-verdict-verdict-finance-mcp/verdict-finance-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/charles-verdict-verdict-finance-mcp/verdict-finance-mcp.json
- HTML version of this page: https://verifymcp.io/servers/charles-verdict-verdict-finance-mcp/verdict-finance-mcp