Server definition

Hash: sha256:52e767f2f184f2a8d5a882eb55ed6fc09979d2d7a2d414dcb960614fd69b9952
What it is: What a remote MCP server returned when asked what it offers: 29 tools

The blob, as servednamed by its sha256

{
  "instructions": "PreteWorks API — one metered key for the whole document-to-web pipeline; no install, nothing to host. Web: turn any public URL into clean Markdown (read_url), structured JSON via AI (extract_data), a PDF (url_to_pdf), or a screenshot (url_to_screenshot). PDF: create (from HTML, Markdown, images, .docx, or invoice/receipt/report templates), edit (merge, split, select/rotate/watermark/number pages, read/set metadata), and read (extract text, read/fill forms). Tools chain: most return a `file_id` you can pass as the input to another tool (e.g. url_to_pdf → watermark_pdf → extract_pdf_text) with no re-upload. Free tier: 500 units/month, no card; then pay per call. Every fetch is SSRF-guarded (private/internal hosts blocked).",
  "tools": [
    {
      "description": "Answer a question grounded ONLY in a source document — a web page, PDF, Office file, or raw text. Provide 'question' plus ONE source: 'url', 'pdf', 'file' (base64), or 'text'. Says so when the answer isn't in the document.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "file": {
            "description": "A base64-encoded .docx, .xlsx or .csv file.",
            "type": "string"
          },
          "pdf": {
            "description": "A file_id from a prior tool, or a base64-encoded PDF.",
            "type": "string"
          },
          "question": {
            "description": "The question to answer from the document.",
            "type": "string"
          },
          "text": {
            "description": "Raw text to answer from directly.",
            "type": "string"
          },
          "url": {
            "description": "A public http/https URL to read.",
            "type": "string"
          }
        },
        "required": [
          "question"
        ],
        "type": "object"
      },
      "name": "answer_from_document",
      "outputSchema": null
    },
    {
      "description": "Fetch up to 10 public URLs and return each as clean Markdown, in one call — for research/RAG over several pages at once. Private/internal hosts are blocked.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "urls": {
            "description": "1–10 http/https URLs.",
            "items": {
              "type": "string"
            },
            "maxItems": 10,
            "minItems": 1,
            "type": "array"
          }
        },
        "required": [
          "urls"
        ],
        "type": "object"
      },
      "name": "batch_scrape",
      "outputSchema": null
    },
    {
      "description": "Fetch a URL plus up to 7 more same-origin pages it links to (≤8 total), each as clean Markdown. Bounded and synchronous. Private/internal hosts are blocked.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "limit": {
            "description": "Max pages incl. root (default 5, max 8).",
            "maximum": 8,
            "minimum": 1,
            "type": "integer"
          },
          "url": {
            "description": "The root http/https URL.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "crawl_site",
      "outputSchema": null
    },
    {
      "description": "Turn rows of data into a downloadable XLSX (default) or CSV. 'rows' is an array of objects (keys → header row) or an array of arrays (first row is the header). Returns a file_id (for chaining) and a ~1h download URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "format": {
            "description": "Output format (default xlsx).",
            "enum": [
              "xlsx",
              "csv"
            ],
            "type": "string"
          },
          "rows": {
            "description": "Array of objects (keys→columns) or array of arrays (first row = header).",
            "items": {},
            "minItems": 1,
            "type": "array"
          },
          "sheet_name": {
            "description": "Worksheet name (default 'Sheet1').",
            "type": "string"
          }
        },
        "required": [
          "rows"
        ],
        "type": "object"
      },
      "name": "data_to_spreadsheet",
      "outputSchema": null
    },
    {
      "description": "Convert a .docx document (base64) to a PDF. Returns a file_id and a ~1h URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "docx": {
            "description": "Base64-encoded .docx file.",
            "type": "string"
          }
        },
        "required": [
          "docx"
        ],
        "type": "object"
      },
      "name": "docx_to_pdf",
      "outputSchema": null
    },
    {
      "description": "Extract the text of a .docx document (base64). Returns the text inline.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "docx": {
            "description": "Base64-encoded .docx file.",
            "type": "string"
          }
        },
        "required": [
          "docx"
        ],
        "type": "object"
      },
      "name": "docx_to_text",
      "outputSchema": null
    },
    {
      "description": "Extract specified fields from a web page, PDF, or Office file as JSON, using AI. Provide 'fields' plus ONE source: a 'url', a 'pdf' (file_id or base64), or a 'file' (base64 .docx/.xlsx/.csv). Returns a JSON object mapping each field to its value, or null when absent.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "fields": {
            "description": "Field names to extract, e.g. ['invoice total','due date'].",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "file": {
            "description": "A base64-encoded .docx, .xlsx or .csv file (converted to text first).",
            "type": "string"
          },
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          },
          "url": {
            "description": "A public http/https URL to read.",
            "type": "string"
          }
        },
        "required": [
          "fields"
        ],
        "type": "object"
      },
      "name": "extract_data",
      "outputSchema": null
    },
    {
      "description": "Extract the text content of a PDF — for RAG, summarization, or search. Accepts a file_id (from a prior tool) or a base64-encoded PDF, and returns the text inline. Not OCR: a scanned/image-only PDF returns little or no text.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          }
        },
        "required": [
          "pdf"
        ],
        "type": "object"
      },
      "name": "extract_pdf_text",
      "outputSchema": null
    },
    {
      "description": "Convert a Word (.docx), Excel (.xlsx) or CSV file (base64) into clean Markdown — for RAG, agents and pipelines. DOCX keeps headings/lists/tables; spreadsheets become Markdown tables (one per sheet). Returns Markdown inline. Optional 'format' (docx|xlsx|csv) overrides auto-detection.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "file": {
            "description": "Base64-encoded .docx, .xlsx or .csv file.",
            "type": "string"
          },
          "format": {
            "description": "Optional format hint; auto-detected if omitted.",
            "enum": [
              "docx",
              "xlsx",
              "csv"
            ],
            "type": "string"
          }
        },
        "required": [
          "file"
        ],
        "type": "object"
      },
      "name": "file_to_markdown",
      "outputSchema": null
    },
    {
      "description": "Fill a PDF's form fields from a map of field -> value; optionally flatten. Returns a file_id and a ~1h URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "fields": {
            "additionalProperties": {},
            "description": "Map of field name to value.",
            "propertyNames": {
              "type": "string"
            },
            "type": "object"
          },
          "flatten": {
            "description": "Flatten the form after filling (default false).",
            "type": "boolean"
          },
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          }
        },
        "required": [
          "pdf",
          "fields"
        ],
        "type": "object"
      },
      "name": "fill_pdf_form",
      "outputSchema": null
    },
    {
      "description": "Combine PNG/JPEG images (base64) into a PDF, one image per page. Returns a file_id and a ~1h URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "images": {
            "description": "Base64-encoded PNG/JPEG images, one per page (max 20).",
            "items": {
              "type": "string"
            },
            "type": "array"
          }
        },
        "required": [
          "images"
        ],
        "type": "object"
      },
      "name": "images_to_pdf",
      "outputSchema": null
    },
    {
      "description": "Discover the same-origin URLs linked from a page — the site map, with no page content fetched. Private/internal hosts are blocked.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "url": {
            "description": "The http/https URL to map.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "map_site",
      "outputSchema": null
    },
    {
      "description": "Render Markdown to a clean, print-styled PDF. Returns a file_id and a ~1h URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "markdown": {
            "description": "The Markdown to render.",
            "type": "string"
          },
          "title": {
            "description": "Document title.",
            "type": "string"
          }
        },
        "required": [
          "markdown"
        ],
        "type": "object"
      },
      "name": "markdown_to_pdf",
      "outputSchema": null
    },
    {
      "description": "Combine 2+ PDFs into a single PDF, in the order given. Inputs are file_ids (from prior tools) or base64 PDFs. Returns a file_id (for chaining) and a ~1h download URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "pdfs": {
            "description": "2+ PDF sources. Each: A file_id from a prior tool result, or a base64-encoded PDF.",
            "items": {
              "type": "string"
            },
            "minItems": 2,
            "type": "array"
          }
        },
        "required": [
          "pdfs"
        ],
        "type": "object"
      },
      "name": "merge_pdfs",
      "outputSchema": null
    },
    {
      "description": "Stamp a page number on every page. position: bottom-center (default) | bottom-left | bottom-right | top-center | top-left | top-right. format supports {n} and {total}. Returns a file_id + ~1h URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "format": {
            "description": "e.g. '{n}' or '{n} / {total}' (default '{n}').",
            "type": "string"
          },
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          },
          "position": {
            "description": "Where to place it (default bottom-center).",
            "type": "string"
          },
          "start": {
            "description": "First page's number (default 1).",
            "type": "number"
          }
        },
        "required": [
          "pdf"
        ],
        "type": "object"
      },
      "name": "number_pdf",
      "outputSchema": null
    },
    {
      "description": "Read a PDF's metadata (title, author, subject, keywords, creator, producer, dates) plus page count and page size, as JSON.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          }
        },
        "required": [
          "pdf"
        ],
        "type": "object"
      },
      "name": "pdf_info",
      "outputSchema": null
    },
    {
      "description": "List a PDF's form fields (name, type, value, options) as JSON.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          }
        },
        "required": [
          "pdf"
        ],
        "type": "object"
      },
      "name": "read_pdf_form",
      "outputSchema": null
    },
    {
      "description": "Fetch a public http/https URL and return its main content as clean Markdown — ideal for giving an agent readable web content for research or RAG. Private/internal hosts are blocked.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "url": {
            "description": "The http/https URL to read.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "read_url",
      "outputSchema": null
    },
    {
      "description": "Render a structured document to a PDF from a named template (invoice, receipt, report). Money/totals are computed for you. Returns a file_id (for chaining) and a ~1h download URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "data": {
            "additionalProperties": {},
            "description": "Template data. invoice/receipt: {seller:{name,address?,email?,logo_url?(data: URI)}, buyer?:{name,address?,email?}, number?, issued?/date?, due?, currency?, items:[{description,qty,unit_price}], tax_rate?, notes?, terms?}; receipt also takes amount_paid?, payment_method?. report: {title, subtitle?, author?, date?, sections:[{heading?,body?}]}. Money is computed server-side.",
            "propertyNames": {
              "type": "string"
            },
            "type": "object"
          },
          "template": {
            "description": "Document template.",
            "enum": [
              "invoice",
              "receipt",
              "report"
            ],
            "type": "string"
          }
        },
        "required": [
          "template",
          "data"
        ],
        "type": "object"
      },
      "name": "render_document",
      "outputSchema": null
    },
    {
      "description": "Render a full HTML document to a PDF. External subresources are blocked for safety — inline images/fonts as data: URIs. Returns a file_id (for chaining) and a ~1h download URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "html": {
            "description": "The complete HTML document to render.",
            "type": "string"
          }
        },
        "required": [
          "html"
        ],
        "type": "object"
      },
      "name": "render_html_to_pdf",
      "outputSchema": null
    },
    {
      "description": "Rotate every page of a PDF by 90, 180, or 270 degrees (clockwise). Returns a file_id (for chaining) and a ~1h download URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "degrees": {
            "description": "90, 180, or 270.",
            "type": "number"
          },
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          }
        },
        "required": [
          "pdf",
          "degrees"
        ],
        "type": "object"
      },
      "name": "rotate_pdf",
      "outputSchema": null
    },
    {
      "description": "Fetch a public http/https URL and return its rendered HTML, the links on the page, and page metadata (title/description/OpenGraph/canonical/favicon) — in one render. For clean Markdown use read_url instead. Private/internal hosts are blocked.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "formats": {
            "description": "Which representations to return (default: all three).",
            "items": {
              "enum": [
                "html",
                "links",
                "metadata"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "url": {
            "description": "The http/https URL to scrape.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "scrape_page",
      "outputSchema": null
    },
    {
      "description": "Keep only the specified pages of a PDF (e.g. [1,3,5]) and drop the rest, preserving order. Returns a file_id (for chaining) and a ~1h download URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "pages": {
            "description": "Pages to keep, e.g. '1,3,5-7'.",
            "type": "string"
          },
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          }
        },
        "required": [
          "pdf",
          "pages"
        ],
        "type": "object"
      },
      "name": "select_pages",
      "outputSchema": null
    },
    {
      "description": "Set a PDF's title, author, subject, keywords (array or comma string) and/or creator. Only the fields you provide change. Returns a file_id + ~1h URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "author": {
            "type": "string"
          },
          "creator": {
            "type": "string"
          },
          "keywords": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              }
            ]
          },
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          },
          "subject": {
            "type": "string"
          },
          "title": {
            "type": "string"
          }
        },
        "required": [
          "pdf"
        ],
        "type": "object"
      },
      "name": "set_pdf_metadata",
      "outputSchema": null
    },
    {
      "description": "Split a PDF into multiple PDFs — one per page by default, or by page ranges like '1-3;4-6'. Returns a file_id + URL per part.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          },
          "ranges": {
            "description": "e.g. '1-3;4-6'. Omit to split every page.",
            "type": "string"
          }
        },
        "required": [
          "pdf"
        ],
        "type": "object"
      },
      "name": "split_pdf",
      "outputSchema": null
    },
    {
      "description": "Summarize a web page, PDF, Office file (.docx/.xlsx/.csv), or raw text using AI. Provide ONE source: 'url', 'pdf' (file_id or base64), 'file' (base64), or 'text'. Optional 'max_words'. Returns the summary.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "file": {
            "description": "A base64-encoded .docx, .xlsx or .csv file.",
            "type": "string"
          },
          "max_words": {
            "description": "Approximate target length in words.",
            "exclusiveMinimum": 0,
            "maximum": 9007199254740991,
            "type": "integer"
          },
          "pdf": {
            "description": "A file_id from a prior tool, or a base64-encoded PDF.",
            "type": "string"
          },
          "text": {
            "description": "Raw text to summarize directly.",
            "type": "string"
          },
          "url": {
            "description": "A public http/https URL to read.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "summarize_document",
      "outputSchema": null
    },
    {
      "description": "Fetch a public http/https URL and render the live page to a PDF. Returns a file_id (chainable into the PDF tools) and a ~1h download URL. Private/internal hosts are blocked.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "url": {
            "description": "The http/https URL to snapshot.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "url_to_pdf",
      "outputSchema": null
    },
    {
      "description": "Fetch a public http/https URL and capture a PNG screenshot. Set full_page for the entire scroll height. Returns a file_id and a ~1h download URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "full_page": {
            "description": "Capture the full scroll height (default: viewport).",
            "type": "boolean"
          },
          "url": {
            "description": "The http/https URL to capture.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "url_to_screenshot",
      "outputSchema": null
    },
    {
      "description": "Stamp a diagonal grey text watermark (e.g. \"DRAFT\", \"CONFIDENTIAL\") across every page of a PDF. Returns a file_id (for chaining) and a ~1h download URL.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "pdf": {
            "description": "A file_id from a prior tool result, or a base64-encoded PDF.",
            "type": "string"
          },
          "text": {
            "description": "The watermark text.",
            "type": "string"
          }
        },
        "required": [
          "pdf",
          "text"
        ],
        "type": "object"
      },
      "name": "watermark_pdf",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:52e767f2f184f2a8d5a882eb55ed6fc09979d2d7a2d414dcb960614fd69b9952 | sha256sum