haiku.rag
MCP server by ggozad
Search and question your own documents with hybrid retrieval, reranking and answers cited to page numbers and headings.
Install haiku.rag
Runs on your machine. Your client starts it with this command:
Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.
Share this server
Opens this page, with the install command and setup steps.
mcp.tc/i/haiku-ragAbout
haiku.rag is a local-first agentic RAG system built on embedded LanceDB, Pydantic AI and Docling. It indexes PDFs, office documents, HTML, Markdown and images, then lets an assistant search them, read documents and run sandboxed Python over them. Answers cite page numbers and section headings.
It runs locally over stdio with the command haiku-rag mcp --stdio, installed from the PyPI package haiku-rag (run with uvx). It needs Python 3.12 or newer. No server or API key is needed by default, since it uses open models through Ollama. Other providers supported by Pydantic AI can be used instead.
What you can do
- Hybrid vector and full-text search over indexed documents
- Optional reranking and section-aware context expansion
- Read indexed documents with page and heading provenance
- Run sandboxed Python over documents for counting and aggregation
- Ingest PDFs, office files, HTML, Markdown and images
- Multimodal image search with a supported embedder
Tools
Local servers list their tools once they’re running, so we can’t show them here. Look for the list in its documentation; your client shows them after you add it.
Example prompts
Search my indexed papers for the attention mechanism and cite page numbers.
What datasets were used for evaluation in paper.pdf?
How many documents in my knowledge base mention transformers?
Read the section on methodology from the indexed spec document.
Set up
Every client starts haiku.rag on your machine with the same command. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport stdio haiku-rag -- uvx haiku-rag mcp --stdio- Start Claude Code and type
/mcp. haiku-rag should show as connected.
Add --scope user to make it available in every project.
Claude Desktop
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag",
"mcp",
"--stdio"
]
}
}
}- Save the file and restart Claude Desktop.
Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag",
"mcp",
"--stdio"
]
}
}
}Needs uv (Python) on your computer.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"haiku-rag","type":"stdio","command":"uvx","args":["haiku-rag","mcp","--stdio"]}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"haiku-rag": {
"type": "stdio",
"command": "uvx",
"args": [
"haiku-rag",
"mcp",
"--stdio"
]
}
}
}Needs uv (Python) on your computer.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag",
"mcp",
"--stdio"
]
}
}
}- Refresh the MCP server list in Cascade.
Devin Desktop is the new name for Windsurf.
Codex
codex mcp add haiku-rag -- uvx haiku-rag mcp --stdioOr edit ~/.codex/config.toml directly:
[mcp_servers.haiku-rag]
command = "uvx"
args = ["haiku-rag", "mcp", "--stdio"]Needs uv (Python) on your computer.
Gemini CLI
gemini mcp add haiku-rag uvx -- haiku-rag mcp --stdioThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients that start local servers accept this shape:
{
"mcpServers": {
"haiku-rag": {
"command": "uvx",
"args": [
"haiku-rag",
"mcp",
"--stdio"
]
}
}
}Zed puts servers under context_servers in its settings, with the same command, args and env fields.
Needs uv (Python) on your computer.
Embed
Show haiku.rag in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/haiku-rag)<a href="https://mcp.tc/i/haiku-rag"><img src="https://mcp.tc/i/haiku-rag/badge.svg" alt="haiku.rag on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/haiku-rag.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/haiku-rag" title="haiku.rag on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/haiku-rag.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the haiku.rag card to your site.
Add the mcp.tc card for haiku.rag, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/haiku-rag.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="haiku-rag"><a href="https://mcp.tc/i/haiku-rag">haiku.rag on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/haiku-rag)
```
Reference: https://mcp.tc/embedChange history
This server runs on your computer, so we follow its PyPI package: each new version shows up here, with edits by its owner.
-
New version 0.112.1 (was 0.112.0). Read from PyPI.
-
New version 0.112.0 (was 0.111.1). Read from PyPI.
-
New version 0.111.1 (was 0.111.0). Read from PyPI.
-
New version 0.111.0 (was 0.110.0). Read from PyPI.
-
New version 0.110.0 (was 0.109.0). Read from PyPI.
-
New version 0.109.0 (was 0.108.0). Read from PyPI.
-
New version 0.107.0 (was 0.106.0). Read from PyPI.
-
New version 0.106.0 (was 0.105.0). Read from PyPI.
-
New version 0.105.0 (was 0.104.0). Read from PyPI.
-
New version 0.104.0 (was 0.103.0). Read from PyPI.
-
New version 0.102.0 (was 0.101.2). Read from PyPI.
-
New version 0.101.2 (was 0.101.1). Read from PyPI.
-
New version 0.101.1 (was 0.101.0). Read from PyPI.
-
New version 0.101.0 (was 0.100.0). Read from PyPI.
-
New version 0.99.0 (was 0.98.0). Read from PyPI.
-
New version 0.98.0 (was 0.97.0). Read from PyPI.
-
New version 0.97.0 (was 0.96.1). Read from PyPI.
-
Tracking started: version 0.96.1.
FAQ
Can I paste mcp.tc/i/haiku-rag into my MCP client?
No. haiku.rag runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx haiku-rag mcp --stdio.
Does haiku.rag need an API key?
No. It doesn’t declare any keys or environment variables. It runs with your user account’s permissions, so check what its tools can reach.
Is haiku.rag a remote or a local server?
Local. Your client starts it as a process on your computer with uvx haiku-rag mcp --stdio, which needs uv (Python).
What can haiku.rag do?
You can hybrid vector and full-text search over indexed documents, optional reranking and section-aware context expansion and read indexed documents with page and heading provenance.
Which clients can use it?
Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.
Does mcp.tc track changes to haiku.rag?
Partly. It runs on your computer, so we follow its PyPI package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read haiku.rag’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with ggozad. This page was built from haiku.rag’s public metadata, last checked on 12 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.