Server definition

Hash: sha256:e92f9052114eb1458342cf2bcfc1ee0ab8a86e38c927e8665cad99405de00268
What it is: What a remote MCP server returned when asked what it offers: 8 tools

The blob, as servednamed by its sha256

{
  "instructions": "AIDataParser extracts schema-guaranteed JSON from PDFs, images, and raw text. START HERE: call try_parse with a short 4000-character text excerpt to run a real extraction with NO API key, no email and no signup (3 calls per caller per day) — that is the fastest way to see whether the output fits. No API key yet? Call create_api_key with the user's email first — it returns a live adp_live_ key with 50 free credits, no card, and you then set it on this server as `Authorization: Bearer <key>`. With a key: call parse_document with a `url` or `base64` document, or parse_text with a `text` string; each costs 1 credit per call. No schema template fits? Call infer_schema with one sample to generate a reusable schema, then reuse it across parses. Use validate (free, no key) to check that a JSON object conforms to a schema before acting on it.",
  "tools": [
    {
      "description": "Return the number of extraction credits remaining on the authenticated API key. Free — does not consume a credit.",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "check_credits",
      "outputSchema": null
    },
    {
      "description": "Start here if you do not have an AIDataParser API key. Provide the user's `email` and receive a live adp_live_ API key with 50 free credits — no card, no signup form. Configure it on this MCP server as `Authorization: Bearer <api_key>` to unlock parse_document, parse_text and infer_schema. The key is returned ONCE and is never shown again, so surface it to the user and store it. Ask the user for their address; do not invent one. Free — does not consume a credit.",
      "inputSchema": {
        "properties": {
          "email": {
            "description": "The user's email address. The account and its free credits belong to this address; an address that already has an account is refused rather than issued a second key.",
            "type": "string"
          }
        },
        "required": [
          "email"
        ],
        "type": "object"
      },
      "name": "create_api_key",
      "outputSchema": null
    },
    {
      "description": "Given one sample document's `text`, propose a reusable JSON Schema for that document type. Use this when no built-in schema_id fits: infer a schema once, review it, then reuse it as `schema` on parse_document / parse_text across many documents for consistent output. Returns the JSON Schema plus a flat field list and an inferred doc_type. Costs 1 credit per successful call.",
      "inputSchema": {
        "properties": {
          "doc_type": {
            "description": "Optional hint for what kind of document this is, e.g. \"purchase order\", \"lab report\".",
            "type": "string"
          },
          "instructions": {
            "description": "Optional guidance on which fields matter or how to shape the schema.",
            "type": "string"
          },
          "text": {
            "description": "A single representative sample of the document type, as text.",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "infer_schema",
      "outputSchema": null
    },
    {
      "description": "Return the built-in schema templates you can pass to parse_document as `schema_id` (invoice, receipt, resume, etc.), each with its id and the fields it extracts. Free — does not consume a credit and needs no API key.",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "list_schemas",
      "outputSchema": null
    },
    {
      "description": "Extract clean, schema-guaranteed JSON from a PDF or image. Provide the document via `url` or `base64`. Pass an optional JSON `schema` to constrain the output shape, and `instructions` to guide extraction. Returns the extracted data plus a confidence score and a review_needed flag. Costs 1 credit per successful call.",
      "inputSchema": {
        "properties": {
          "base64": {
            "description": "Base64-encoded document bytes (alternative to `url`). Provide `media_type` alongside it.",
            "type": "string"
          },
          "instructions": {
            "description": "Optional natural-language guidance for what to extract.",
            "type": "string"
          },
          "media_type": {
            "description": "MIME type for `base64` input, e.g. application/pdf, image/png, image/jpeg.",
            "type": "string"
          },
          "redact": {
            "description": "When true, PII (emails, SSNs, card numbers, phones, etc.) is masked in the output before it leaves the server.",
            "type": "boolean"
          },
          "schema": {
            "description": "Optional JSON Schema describing the exact output shape you want. When provided, the returned `data` conforms to it.",
            "type": "object"
          },
          "schema_id": {
            "description": "Optional named template to use instead of a hand-written schema, e.g. \"invoice\", \"receipt\", \"resume\". Call the list_schemas tool for the full set. Ignored when `schema` is provided.",
            "type": "string"
          },
          "url": {
            "description": "Public http(s) URL of the PDF or image to parse.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "parse_document",
      "outputSchema": null
    },
    {
      "description": "Extract clean, schema-guaranteed JSON from raw/messy text you already have — scraped web content, email bodies, chat logs, OCR output, or pasted tables. Pass the text in `text`. Use this instead of parse_document when you don't have a file. Optional JSON `schema` (or `schema_id`) constrains the output shape and `instructions` guides extraction. Returns the extracted data plus a confidence score and a review_needed flag. Costs 1 credit per successful call.",
      "inputSchema": {
        "properties": {
          "instructions": {
            "description": "Optional natural-language guidance for what to extract.",
            "type": "string"
          },
          "redact": {
            "description": "When true, PII (emails, SSNs, card numbers, phones, etc.) is masked in the output before it leaves the server.",
            "type": "boolean"
          },
          "schema": {
            "description": "Optional JSON Schema describing the exact output shape you want. When provided, the returned `data` conforms to it.",
            "type": "object"
          },
          "schema_id": {
            "description": "Optional named template to use instead of a hand-written schema, e.g. \"invoice\", \"receipt\", \"resume\". Call the list_schemas tool for the full set. Ignored when `schema` is provided.",
            "type": "string"
          },
          "text": {
            "description": "The raw text to extract structured data from.",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "parse_text",
      "outputSchema": null
    },
    {
      "description": "Run a REAL extraction with no API key, no email and no signup, so you can see the output shape before committing to anything. Pass up to 4000 characters of messy text in `text` (an invoice, a receipt, a resume, scraped HTML, an email body) and optionally a `schema` or `schema_id` to constrain the result. Returns the same structured data, confidence and review_needed flag the paid tools return. Limited to 3 calls per caller per day — for real volume call create_api_key for 50 free credits, then use parse_text or parse_document.",
      "inputSchema": {
        "properties": {
          "instructions": {
            "description": "Optional natural-language guidance for what to extract.",
            "type": "string"
          },
          "schema": {
            "description": "Optional JSON Schema describing the exact output shape you want. When provided, the returned `data` conforms to it.",
            "type": "object"
          },
          "schema_id": {
            "description": "Optional named template to use instead of a hand-written schema, e.g. \"invoice\", \"receipt\", \"resume\". Call list_schemas for the full set. Ignored when `schema` is provided.",
            "type": "string"
          },
          "text": {
            "description": "The raw text to extract structured data from, up to 4000 characters. Send a representative excerpt rather than a whole corpus.",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "try_parse",
      "outputSchema": null
    },
    {
      "description": "Check whether a JSON object conforms to a JSON `schema` (or a built-in `schema_id` template) and get back a valid flag plus per-field errors. Use this to verify data you already hold — a prior parse result, your own output, or an upstream feed — before acting on it or spending a credit. Deterministic, free, and needs no API key.",
      "inputSchema": {
        "properties": {
          "data": {
            "description": "The JSON value to validate."
          },
          "schema": {
            "description": "JSON Schema to validate against. Takes precedence over schema_id.",
            "type": "object"
          },
          "schema_id": {
            "description": "Built-in template id to validate against instead of a hand-written schema (invoice, receipt, resume, etc.). Call list_schemas for the full set.",
            "type": "string"
          }
        },
        "required": [
          "data"
        ],
        "type": "object"
      },
      "name": "validate",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:e92f9052114eb1458342cf2bcfc1ee0ab8a86e38c927e8665cad99405de00268 | sha256sum