Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "verdict-finance-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}

claude mcp add verdict-finance-mcp -- npx -y [email protected]

[mcp_servers.verdict-finance-mcp]
command = "npx"
args = ["-y", "[email protected]"]

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

{
  "mcpServers": {
    "verdict-finance-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=verdict-finance-mcp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsInZlcmRpY3QtZmluYW5jZS1tY3BAMC40LjAiXX0%3D"
}

{
  "servers": {
    "verdict-finance-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}

{
  "mcpServers": {
    "verdict-finance-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}

extensions:
  "verdict-finance-mcp":
    enabled: true
    name: "verdict-finance-mcp"
    type: stdio
    cmd: "npx"
    args:
      - "-y"
      - "[email protected]"
    timeout: 300

This is a local package: the command runs on your machine.

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

protocoln/a · weight 25

n/a
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygienen/a · weight 30

n/a
tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool list unknown

dependencies50 · weight 15

warn
deps.known_vulns1 advisory of lower severity or without a published fix: GHSA-5r4p-p66f-jhc7 in [email protected] (indirect, fixed in 4.13.11)
fail
deps.mcp_sdk_version@modelcontextprotocol/sdk 1.30.1 has 3 known advisories (GHSA-22jm-h49p-29qw, GHSA-6prh-2h8m-c8cw, GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.32.0 or later
pass
deps.resolvable[email protected] resolved: 98 packages

Tool list unknown · checked 2026-10-20 23:27 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 85 / 100

provenance75

livenessn/a

freshness85

hygiene100

+repository +website ~liveness-unmeasured ~updated-53d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

[email protected] npm97 dependencies, resolved · MCP SDK @modelcontextprotocol/sdk 1.30.1 · advisories checked 2026-10-20

advisory	severity	package	fixed in
GHSA-22jm-h49p-29qwMCP TypeScript SDK: Experimental tasks were not tied to the session that created them	high	`@modelcontextprotocol/[email protected]`MCP SDK, direct	fixed in `1.32.0`
GHSA-6qxp-vccf-f47hMCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server	high	`@modelcontextprotocol/[email protected]`MCP SDK, direct	fixed in `1.31.0`
GHSA-6prh-2h8m-c8cwMCP TypeScript client SDK: HTTP client transports and OAuth requests followed cross-origin redirects and re-sent custom headers and request bodies	moderate	`@modelcontextprotocol/[email protected]`MCP SDK, direct	fixed in `1.32.0`
GHSA-5r4p-p66f-jhc7Hono: `serveStatic` decodes the request path a second time, leading to bypass of middleware on static paths	moderate	`[email protected]`indirect	fixed in `4.13.11`

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

package	registry	version	runtime	secrets
`verdict-finance-mcp`	npm	0.4.0	–

Tools (0)

No tools observed. Local packages are never executed by the registry.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.github.charles-verdict/verdict-finance-mcp",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "tools": [
        {
          "name": "search_ratings",
          "task": "Find rated entities by name or keyword across all seven types"
        },
        {
          "name": "get_rating",
          "task": "Letter grade and composite score for one protocol, chain, token, oracle, vault, organisation or bridge"
        },
        {
          "name": "list_ratings",
          "task": "Browse a rated set best-first, filtered by category or chain"
        },
        {
          "name": "quantum_readiness",
          "task": "Post-quantum cryptographic readiness for a chain, or the full league table"
        },
        {
          "name": "get_recent_incidents",
          "task": "DeFi hack incidents, newest first (confirmed by default), pollable with a since cursor"
        },
        {
          "name": "get_methodology",
          "task": "How a grade is produced: criteria counts and domains per entity type, and the AAA to D scale"
        },
        {
          "name": "get_rating_breakdown",
          "task": "Per-domain scores behind one entity's grade (needs VERDICT_API_KEY)"
        },
        {
          "name": "request_coverage",
          "task": "Ask Verdict to rate an entity it does not cover yet"
        }
      ],
      "keywords": [
        "defi",
        "risk ratings",
        "credit ratings",
        "protocol risk",
        "smart contract risk",
        "hack incidents",
        "exploits",
        "post-quantum readiness",
        "bridges",
        "oracles",
        "stablecoins",
        "vaults",
        "due diligence",
        "audits",
        "marketplace",
        "methodology"
      ],
      "useCases": [
        "Check what Verdict rates a DeFi protocol before allocating to it",
        "Screen a portfolio's chains, oracles and bridges for dependency risk",
        "Poll a hack incident feed to drive an agent's risk workflow",
        "Explain a grade from the published methodology and its domain breakdown"
      ],
      "categories": [
        "finance",
        "security",
        "developer-tools",
        "data-analysis"
      ],
      "documentation": "https://github.com/Verdict-Capital/verdict-finance-mcp#readme"
    }
  },
  "title": "Verdict: the due-diligence house for DeFi",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "0.4.0",
  "packages": [
    {
      "version": "0.4.0",
      "transport": {
        "type": "stdio"
      },
      "identifier": "verdict-finance-mcp",
      "registryType": "npm"
    }
  ],
  "repository": {
    "url": "https://github.com/Verdict-Capital/verdict-finance-mcp",
    "source": "github"
  },
  "websiteUrl": "https://www.verdict.finance",
  "description": "Verdict, the due-diligence house for DeFi: keyless ratings, methodology and a hack incident feed."
}