About ezmd
ezmd-mcp converts files, URLs, and pasted text into paginated Markdown for LLM workflows. It preserves section and page references for citations and reports issues such as skipped pages, truncated tables, and suspected prompt injection.
Key features
- 01Convert files, URLs, and text to Markdown
- 02Paginate output to a token budget
- 03Include section IDs and page markers
- 04Report conversion warnings
- 05Expose job results as resources
Use cases
- 01Prepare web pages for LLM analysis
- 02Convert local documents for citation
- 03Review warnings in converted content
MCP support
Provides MCP tools for URL, file, and text conversion, job pagination, and capability discovery. It also exposes full Markdown and sidecar JSON as resources and includes a provenance-focused prompt.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx ezmd-mcpEZMD_PROFILEDefault output profile: full, compact, rag or agentEZMD_MCP_ALLOWED_DIRSDirectories convert_file may read, separated by the OS path separator (default: working directory)EZMD_REMOTEBase URL of an ezmd instance; converts there instead of in-processEZMD_API_KEYSecretAPI key for EZMD_REMOTE, sent as X-API-KeyLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
5Saved tool list · updated 5d ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | |
| options | any | No | |
| profile | any | No | |
| max_tokens | any | No |
Details
From the project READMEezmd-mcp
An MCP server for ezmd: convert files, URLs and pasted text to LLM-ready Markdown from Claude Desktop, Claude Code, Cursor, VS Code and any other MCP client. Results are paginated to your token budget, carry section ids and page markers for citations, and report every warning (skipped pages, truncated tables, suspected prompt injection) instead of dropping content silently.
uvx ezmd-mcp # stdio, converts in-process
uvx ezmd-mcp --allowed-dirs ~/docs
uvx ezmd-mcp --remote https://ezmd.example # forward to an instance; EZMD_API_KEY is sent as X-API-Key
uvx ezmd-mcp --transport http --port 8765 # streamable HTTP on 127.0.0.1, bearer token required
Tools
| Tool | What it does |
|---|---|
convert_url(url, profile?, max_tokens?, options?) | Fetch (through the SSRF guard) and convert an http(s) URL. |
convert_file(path? | data_url?, profile?, max_tokens?, options?) | Convert a local file inside the allowed directories, or a base64 data: URL under 1 MB. |
convert_text(text, source_hint?, profile?, max_tokens?) | Convert pasted text, HTML, Markdown, CSV, JSON. |
get_job(job_id, cursor?, max_tokens?, profile?) | Job status, or the page at cursor: the pagination endpoint for every convert tool. |
list_capabilities() | Supported types, missing extras, limits, whether fetching is allowed. |
Every result has job_id, title, source, tokens_total, pages_total, page, next_cursor, warnings, frontmatter, content (page 1 adds sections). The default profile is agent (untrusted-content fence,
section ids); max_tokens defaults to 8000 and is capped at 50000. Resources ezmd://jobs/{id} and
ezmd://jobs/{id}/sidecar expose the full Markdown and sidecar JSON; the prompt
summarize_with_provenance asks the model to cite section ids and pages.
See docs/mcp.md for client configuration, security notes and every option. Apache-2.0.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.