Read markdown with inlined images and index headings for agentic RAG workflows.
Connect Md to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Read markdown with inlined images and index headings for agentic RAG workflows. The md mcp server is what makes that connection.
stdio MCP server with two read-only tools for agentic RAG over markdown documentation:
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Requirements — The Requirements tool exposed by this serverread_md_with_images — Read a markdown file and inline referenced images as MCP image contentindex_md — 1. YAML frontmatter when present. 2. A fenced tsv code block with columns: heading, line_start, n_images, char_countInstallation goes through your MCP client rather than a global install: point it at md-vision on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Md's toolset — Requirements, read_md_with_images, index_md — is a fair guide to whether it matches your workflow. It is maintained by japlete; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Md's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Requirements | The Requirements tool exposed by this server. |
| read_md_with_images | Read a markdown file and inline referenced images as MCP image content. |
| index_md | 1. YAML frontmatter when present. 2. A fenced tsv code block with columns: heading, line_start, n_images, char_count. |
{
"mcpServers": {
"md-vision": {
"command": "npx",
"args": [
"md-vision",
"--allow-path",
"/absolute/path/to/docs",
"--allow-domain",
"none"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.