Server definition

Hash: sha256:a1c5b7d67d54aab495b6c878151594047262e11e3a6a6cfd49b73ab8e06d2194
What it is: What a remote MCP server returned when asked what it offers: 4 tools

The blob, as servednamed by its sha256

{
  "instructions": null,
  "tools": [
    {
      "description": "Read a product skill file by its skill:// URI.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "uri": {
            "description": "e.g. skill://<product>/<skill-name>/SKILL.md\n Get valid URIs from `skills_list_tool`.",
            "type": "string"
          }
        },
        "required": [
          "uri"
        ],
        "type": "object"
      },
      "name": "read_skill",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "List this product's skills. Each entry carries the SKILL.md URI,\nits name and description, verbatim frontmatter, and a per-file\nsha256 manifest. Read a body with `read_skill`.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "skills_list_tool",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Security-scan a single file for invisible Unicode, dangerous patterns, and secrets.\n\nReturns a severity-weighted score and per-finding detail (rule, severity,\nlocation). Read-only: the file is never modified.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "filepath": {
            "description": "absolute path of the file to scan",
            "type": "string"
          }
        },
        "required": [
          "filepath"
        ],
        "type": "object"
      },
      "name": "trust_scan_file",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Security-scan an MCP server or skill package before trusting it.\n\nRuns all four checks — invisible Unicode prompt-injection, dangerous code\npatterns (MCP001–006), hardcoded secrets, typosquat package names — and\nreturns a 0-100 score, letter grade, and detailed findings. Run this on\nany directory BEFORE wiring it into your agent. Read-only: never modifies\nthe scanned target.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "package_name": {
            "default": "",
            "description": "package name for typosquat detection (e.g. \"mcp-server\")",
            "type": "string"
          },
          "path": {
            "description": "directory or file path to scan (on the TrustScan host)",
            "type": "string"
          }
        },
        "required": [
          "path"
        ],
        "type": "object"
      },
      "name": "trust_scan_server",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:a1c5b7d67d54aab495b6c878151594047262e11e3a6a6cfd49b73ab8e06d2194 | sha256sum