Server definition
- Hash
- sha256:6d7b14a1f89760ffaa7c0657014a298dc224abc8dd55a5e861fedb02184210e0
- What it is
- What a remote MCP server returned when asked what it offers: 3 tools
The blob, as servednamed by its sha256
{
"instructions": "Read complex documents with two focused tools. Use pdf_to_markdown for searchable, agent-ready Markdown from a PDF. Use extract_document_fields for structured fields and full text from a PNG or JPEG document image; it does not accept PDFs. Use check_document_service to verify availability. Provide exactly one URL or base64 source to a conversion tool. Authentication uses a Bearer API key available at https://app.brainiall.com.",
"tools": [
{
"description": "Check whether document conversion and extraction are available.\n\nUse this before a workflow or when another document tool reports a\ntemporary availability problem. No document input is required.\n\nReturns:\n A dictionary with status='healthy', or an actionable error object.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "check_document_service",
"outputSchema": null
},
{
"description": "Extract structured fields and full text from a document image.\n\nUse this for invoices, receipts, forms, and similar PNG or JPEG images\nwhen the agent needs named fields rather than Markdown. PDF input is\nintentionally rejected; use pdf_to_markdown for PDFs.\n\nReturns:\n A dictionary containing request metadata, extracted fields, and text,\n or an actionable error object on failure.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"doc_type": {
"default": "invoice",
"description": "Document type that guides field extraction, such as 'invoice' (default), 'receipt', or 'form'.",
"type": "string"
},
"image_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Base64-encoded PNG or JPEG bytes. Provide this or url, never both."
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Public URL pointing directly to a PNG or JPEG document image. Provide this or image_base64, never both."
}
},
"type": "object"
},
"name": "extract_document_fields",
"outputSchema": null
},
{
"description": "Convert a PDF into readable Markdown for analysis and retrieval.\n\nUse this when an agent needs the text, headings, tables, and document\nstructure from a PDF. Supply exactly one source: a public URL or base64\nPDF bytes. The optional page range is useful for large documents.\n\nReturns:\n Markdown text on success, or an actionable error object on failure.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"page_range": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional pages to convert, such as '1-5'. Omit to convert the entire PDF."
},
"pdf_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Base64-encoded PDF bytes. Provide this or url, never both."
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Public URL pointing directly to a PDF. Provide this or pdf_base64, never both."
}
},
"type": "object"
},
"name": "pdf_to_markdown",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:6d7b14a1f89760ffaa7c0657014a298dc224abc8dd55a5e861fedb02184210e0 | sha256sum