get_server

Get the full VerifyMCP trust report for one MCP server: score with per-category verdicts and reasons, the tools it exposes with their context-token cost, and its recent change history. Use before installing or trusting a server. Accepts a package name, endpoint URL, registry name or verifymcp slug.

read-only

Argument	Type	Description
component	string	Which channel to report on when a server ships several.
identifier*	string	Package name, endpoint URL, registry name or verifymcp slug.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {
      "identifier": "@modelcontextprotocol/server-github"
    },
    {
      "identifier": "https://mcp.example.com/mcp"
    },
    {
      "component": "npm",
      "identifier": "io.github.acme/tools"
    },
    {
      "identifier": "acme-tools"
    }
  ],
  "required": [
    "identifier"
  ],
  "properties": {
    "component": {
      "type": "string",
      "description": "Which channel to report on when a server ships several."
    },
    "identifier": {
      "type": "string",
      "description": "Package name, endpoint URL, registry name or verifymcp slug."
    }
  },
  "additionalProperties": false
}

get_server_alternatives

Other MCP servers doing a similar job to a given one, with their trust scores. Neighbours share a product, publisher namespace or category; this is not a semantic search.

read-only

Argument	Type	Description
identifier*	string	Package name, endpoint URL, registry name or verifymcp slug.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {
      "identifier": "@modelcontextprotocol/server-github"
    },
    {
      "identifier": "https://mcp.example.com/mcp"
    },
    {
      "identifier": "acme-tools"
    }
  ],
  "required": [
    "identifier"
  ],
  "properties": {
    "identifier": {
      "type": "string",
      "description": "Package name, endpoint URL, registry name or verifymcp slug."
    }
  },
  "additionalProperties": false
}

get_server_comparison

Compare up to 5 MCP servers side by side: trust scores, per-category breakdown, tool counts and context-token cost. Use when choosing between candidates that do the same job. Accepts package names, endpoint URLs, registry names or verifymcp slugs.

read-only

Argument	Type	Description
identifiers*	array	Two to 5 servers to compare, as names, URLs or slugs.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {
      "identifiers": [
        "@acme/mcp-server",
        "@other/mcp-server"
      ]
    },
    {
      "identifiers": [
        "acme-tools",
        "beta-tools",
        "gamma-tools"
      ]
    }
  ],
  "required": [
    "identifiers"
  ],
  "properties": {
    "identifiers": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "minItems": 2,
      "description": "Two to 5 servers to compare, as names, URLs or slugs."
    }
  },
  "additionalProperties": false
}

get_server_diagnostics

The evidence behind one server's score: TLS, DNSSEC, authorization, redirects, transports, provenance, install scripts, known CVEs and dependency health. Use to explain a low score.

read-only

Argument	Type	Description
component	string	Which channel to report on when a server ships several.
identifier*	string	Package name, endpoint URL, registry name or verifymcp slug.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {
      "identifier": "@modelcontextprotocol/server-github"
    },
    {
      "identifier": "https://mcp.example.com/mcp"
    },
    {
      "component": "npm",
      "identifier": "io.github.acme/tools"
    }
  ],
  "required": [
    "identifier"
  ],
  "properties": {
    "component": {
      "type": "string",
      "description": "Which channel to report on when a server ships several."
    },
    "identifier": {
      "type": "string",
      "description": "Package name, endpoint URL, registry name or verifymcp slug."
    }
  },
  "additionalProperties": false
}

get_server_install_config

Ready-to-paste install snippets for one MCP server, for every client we support. An MCPB bundle has no launch command, so it returns the download URL, the registry's SHA-256 and commands to verify the file instead. Read get_server first: this returns configuration, not a safety judgement.

read-only

Argument	Type	Description
component	string	Which channel to report on when a server ships several.
identifier*	string	Package name, endpoint URL, registry name or verifymcp slug.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {
      "identifier": "@modelcontextprotocol/server-github"
    },
    {
      "identifier": "https://mcp.example.com/mcp"
    },
    {
      "component": "npm",
      "identifier": "acme-tools"
    }
  ],
  "required": [
    "identifier"
  ],
  "properties": {
    "component": {
      "type": "string",
      "description": "Which channel to report on when a server ships several."
    },
    "identifier": {
      "type": "string",
      "description": "Package name, endpoint URL, registry name or verifymcp slug."
    }
  },
  "additionalProperties": false
}

get_server_tools

Every tool one MCP server exposes, with its parameters, output schema and context-token cost. Use when get_server reported the tool list was truncated.

read-only

Argument	Type	Description
component	string	Which channel to report on when a server ships several.
identifier*	string	Package name, endpoint URL, registry name or verifymcp slug.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {
      "identifier": "@modelcontextprotocol/server-github"
    },
    {
      "identifier": "https://mcp.example.com/mcp"
    },
    {
      "component": "npm",
      "identifier": "acme-tools"
    }
  ],
  "required": [
    "identifier"
  ],
  "properties": {
    "component": {
      "type": "string",
      "description": "Which channel to report on when a server ships several."
    },
    "identifier": {
      "type": "string",
      "description": "Package name, endpoint URL, registry name or verifymcp slug."
    }
  },
  "additionalProperties": false
}

list_known_malware

List MCP server components carrying a supply-chain malware finding. Use to check whether anything in the register is flagged before installing.

read-only

Argument	Type	Description
status	string	Which findings to return: active, unverified, cleared or all. Defaults to active.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {},
    {
      "status": "active"
    },
    {
      "status": "all"
    }
  ],
  "properties": {
    "status": {
      "enum": [
        "active",
        "unverified",
        "cleared",
        "all"
      ],
      "type": "string",
      "default": "active",
      "description": "Which findings to return: active, unverified, cleared or all. Defaults to active."
    }
  },
  "additionalProperties": false
}

list_products

List the products MCP servers integrate with, such as github or notion, and how many servers cover each. Use to find the product slug that list_servers accepts.

read-only

Argument	Type	Description
query	string	Name fragment to match against product names and slugs.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {},
    {
      "query": "git"
    },
    {
      "query": "notion"
    }
  ],
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 100,
      "description": "Name fragment to match against product names and slugs."
    }
  },
  "additionalProperties": false
}

list_servers

Filter the VerifyMCP directory of scored MCP servers. Use to discover servers by name fragment, ecosystem, product or trust score. Name matching only: descriptions and capabilities are not searched, so a plain-English question matches nothing. Returns the first 100.

read-only

Argument	Type	Description
sort	string	Default: best match (then trust) with a query, else trust. A given sort is applied exactly.
query	string	Name fragment to match against server and package names.
types	array	Restrict to these ecosystems; a server matches any one of them.
scored	string	Include unscored servers. Defaults to scored only.
product	string	Restrict to servers classified as working with this product, e.g. github.
maxScore	integer	Highest trust score to include.
minScore	integer	Lowest trust score to include.

Input schema (JSON)

{
  "type": "object",
  "examples": [
    {
      "query": "github"
    },
    {
      "product": "github",
      "minScore": 70
    },
    {
      "sort": "score_desc",
      "types": [
        "remote"
      ],
      "minScore": 80
    },
    {
      "types": [
        "npm",
        "pypi"
      ],
      "scored": "scored"
    },
    {
      "query": "postgres",
      "types": [
        "npm"
      ]
    }
  ],
  "properties": {
    "sort": {
      "enum": [
        "score_desc",
        "score_asc",
        "name_asc",
        "name_desc",
        "channels_asc",
        "channels_desc"
      ],
      "type": "string",
      "description": "Default: best match (then trust) with a query, else trust. A given sort is applied exactly."
    },
    "query": {
      "type": "string",
      "maxLength": 100,
      "description": "Name fragment to match against server and package names."
    },
    "types": {
      "type": "array",
      "items": {
        "enum": [
          "remote",
          "npm",
          "pypi",
          "oci",
          "nuget",
          "mcpb"
        ],
        "type": "string"
      },
      "description": "Restrict to these ecosystems; a server matches any one of them."
    },
    "scored": {
      "enum": [
        "scored",
        "unscored",
        "all"
      ],
      "type": "string",
      "default": "scored",
      "description": "Include unscored servers. Defaults to scored only."
    },
    "product": {
      "type": "string",
      "description": "Restrict to servers classified as working with this product, e.g. github."
    },
    "maxScore": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "Highest trust score to include."
    },
    "minScore": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "Lowest trust score to include."
    }
  },
  "additionalProperties": false
}

VerifyMCP

Try it

get_server Read-only

VerifyMCP

Try it

get_server Read-only

Tools (9)