Serveur MCP

AgentMD

io.github.djrobson5/agentmd
Connaissance et documentation Public et accessible MCP 2025-11-25

Ce que fait ce MCP

Converts PDF, DOCX, HTML, plain text, and web URLs into clean Markdown with preserved tables and selective extraction.

convert_document_to_markdown
Convert document to markdown
Convert a document you already have (PDF, DOCX, HTML, plain text) to clean, LLM-ready markdown. Pass the file contents as base64. Supports reading only part of a large document: PDF page ranges, a heading outline, a single section, or a token cap.
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['base64'], 'properties': {'mode': {'enum': ['full', 'outline'], 'type': 'string', 'description': '"full" (default) returns the document body. "outline" returns just the heading tree â\x80\x94 each line is `- [#3] Heading text (~120 tokens)`. For a long document, call with mode: \'outline\' first, then fetch only what you need with section: \'#3\' or a heading title.'}, 'pages': {'type': 'string', 'description': 'PDFs only: 1-indexed, inclusive page ranges to convert, e.g. "1-3,5,8-" (an open-ended range runs to the last page). Ignored with a warning for non-PDF formats.'}, 'base64': {'type': 'string', 'description': 'Base64-encoded file contents'}, 'section': {'type': 'string', 'description': 'Return only one section: either "#<n>" using the index from a mode: \'outline\' call (e.g. \'#3\'), or the heading text itself (case-insensitive; exact match wins, then prefix, then substring). Ignored when mode is \'outline\'.'}, 'filename': {'type': 'string', 'description': 'Original filename, e.g. report.pdf â\x80\x94 helps format detection'}, 'maxTokens': {'type': 'integer', 'maximum': 9007199254740991, 'description': 'Cap the returned markdown at roughly this many tokens, cutting at a paragraph boundary. When the output is cut, the result starts with a `> Truncated: ~X of ~Y tokens` line â\x80\x94 narrow with pages or section rather than raising this.', 'exclusiveMinimum': 0}}}
convert_url_to_markdown
Convert URL to markdown
Fetch a URL (web page, PDF, DOCX, etc.) and convert it to clean, LLM-ready markdown. Extracts the main article content from web pages and preserves tables. Supports reading only part of a large document: PDF page ranges, a heading outline, a single section, or a token cap.
Schéma d’entrée
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The http(s) URL of the document or page to convert'}, 'mode': {'enum': ['full', 'outline'], 'type': 'string', 'description': '"full" (default) returns the document body. "outline" returns just the heading tree â\x80\x94 each line is `- [#3] Heading text (~120 tokens)`. For a long document, call with mode: \'outline\' first, then fetch only what you need with section: \'#3\' or a heading title.'}, 'pages': {'type': 'string', 'description': 'PDFs only: 1-indexed, inclusive page ranges to convert, e.g. "1-3,5,8-" (an open-ended range runs to the last page). Ignored with a warning for non-PDF formats.'}, 'section': {'type': 'string', 'description': 'Return only one section: either "#<n>" using the index from a mode: \'outline\' call (e.g. \'#3\'), or the heading text itself (case-insensitive; exact match wins, then prefix, then substring). Ignored when mode is \'outline\'.'}, 'maxTokens': {'type': 'integer', 'maximum': 9007199254740991, 'description': 'Cap the returned markdown at roughly this many tokens, cutting at a paragraph boundary. When the output is cut, the result starts with a `> Truncated: ~X of ~Y tokens` line â\x80\x94 narrow with pages or section rather than raising this.', 'exclusiveMinimum': 0}}}
Ajouté
convert_document_to_markdown
17 September 2026 12:41
Ajouté
convert_url_to_markdown
17 September 2026 12:41