Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/trsdn/markitdown-mcp/agents-mdgit clone --depth 1 https://github.com/trsdn/markitdown-mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.05197 | $0.05197 |
| Opus 5 | $0.02599 | $0.02599 |
| Sonnet 5 | $0.01039 | $0.01039 |
| Haiku 4.5 | $0.00520 | $0.00520 |
Grade A, and why
markitdown-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing โ 759 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
AI Agents Integration Guide
This guide provides comprehensive information for AI agents and assistants on how to effectively use the MarkItDown MCP server for document conversion tasks.
๐ค Quick Reference for AI Agents
Primary Use Cases
- Convert documents (PDF, Word, Excel, PowerPoint) to markdown
- Extract readable text from various file formats
- Batch process directories of documents
- Support users with document analysis workflows
Available Tools
convert_file- Convert individual filesconvert_directory- Batch convert directorieslist_supported_formats- Show supported formats
๐ ๏ธ Tool Usage Guide
convert_file Tool
When to use:
- User provides a file path for conversion
- User shares base64 content that needs conversion
- Single document analysis required
Parameters:
{
"file_path": "/path/to/document.pdf", // For local files
"file_content": "base64encoded...", // For shared content
"filename": "document.pdf" // Required with file_content
}
Example scenarios:
- "Convert this PDF to markdown"
- "Extract text from this Word document"
- "Make this Excel file readable"
convert_directory Tool
When to use:
- User wants to process multiple files
- Batch conversion workflows
- Directory cleanup/organization tasks
Parameters:
{
"input_directory": "/path/to/input",
"output_directory": "/path/to/output" // Optional
}
Example scenarios:
- "Convert all documents in this folder"
- "Process my downloads directory"
- "Batch convert these reports"
list_supported_formats Tool
When to use:
- User asks about supported file types
- Error troubleshooting (unsupported format)
- Capability discovery
Parameters: None
Example scenarios:
- "What file types can you convert?"
- "Can you handle PowerPoint files?"
- "Is Excel supported?"
๐ก Best Practices for AI Agents
1. Format Detection
# Always check format support first if unsure
if user_asks_about_unknown_format:
call_tool("list_supported_formats")
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen ยท 759 lines ยท 5,197 tokens per session scan A 979d4ca116ac
markitdown-mcp AGENTS.md is an instructions file published in the GitHub repository trsdn/markitdown-mcp (32 stars, last pushed 3d ago), licensed MIT. It adds 5,197 tokens to every session, about $0.0260 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
docsift CLAUDE.md
Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.
agentic-reviewer AGENTS.md
Instructions for FilippoScaramuzza/agentic-reviewer, covering agentic reviewer โ journal paper review framework, project overview, directory structure, workflow and phase 0: setup & paper conversion.
markitdown-for-ai AGENTS.md
Instructions for OpenTechIL/markitdown-for-ai, covering agents.md, project overview, conventional commits, types and examples.
markitdown-mcp-server AGENTS.md
AGENTS.md instructions for RECTOR-LABS/markitdown-mcp-server, covering apify actors development guide, what are apify actors?, core concepts, do and don't.
markitdown-mcp-server CLAUDE.md
Claude Code instructions for RECTOR-LABS/markitdown-mcp-server, covering claude.md - markitdown mcp server, actor overview, technical architecture, core technology stack and repository structure.
markdown-exporter AGENTS.md
Instructions for bowenliang123/markdown-exporter, covering agent coding guidelines for md-exporter, ๐ง build, lint, and test commands, package management, code quality and formatting and alternative: run from project root using provided script.