AI & Memory MCP Server

Haiku Rag

Name: Haiku Rag
Author: ggozad

Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling

Scan found nothing by ggozad498MITPythonIntermediatestdio

Install

Claude Code

claude mcp add haiku-rag -- uvx haiku-rag

Cursor

{
  "mcpServers": {
    "haiku-rag": {
      "command": "uvx",
      "args": [
        "haiku-rag"
      ]
    }
  }
}

VS Code

{
  "mcp": {
    "servers": {
      "haiku-rag": {
        "command": "uvx",
        "args": [
          "haiku-rag"
        ]
      }
    }
  }
}

Windsurf

{
  "mcpServers": {
    "haiku-rag": {
      "command": "uvx",
      "args": [
        "haiku-rag"
      ]
    }
  }
}

Claude Desktop

{
  "mcpServers": {
    "haiku-rag": {
      "command": "uvx",
      "args": [
        "haiku-rag"
      ]
    }
  }
}

Safety Report

50% Scan found nothing

Scanned 5 months ago

3 passed 3 warnings

Security

Authentication

details

Weak auth signals: auth_header

Warning

CORS Policy

details

stdio transport — CORS not applicable

N/A

Rate Limiting

details

No rate limiting mechanism detected

Info

Known CVEs

details

No known CVEs in dependencies

Pass

Code Quality

Dependency Audit

details

No known vulnerable dependencies detected

Pass

Dangerous Patterns

details

Dangerous patterns detected: eval_call

Warning

License

details

License: MIT

Pass

Community

Maintenance Status

details

Last commit 5 months ago

Warning

Learn about our security methodology →

Compatibility

Claude CodeFull support

Tested

CursorFull support

Tested

VS CodeFull support via Copilot

Tested

WindsurfFull support

Tested

Claude DesktopFull support

Tested

Frequently Asked Questions

What is Haiku Rag?

Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling

Is Haiku Rag safe to use?

We cannot tell you that, and nobody scanning at this scale can. What we did in March 2026 was shallow-clone Haiku Rag and run five keyword searches over its source: auth identifiers, CORS configuration, rate-limit identifiers, the dependency manifest against a hardcoded list of 18 known-vulnerable packages, and unguarded eval/exec calls. None of them matched. A text search cannot follow a variable, judge intent, or tell you what a server does once it is running, so "nothing matched" is not "safe". What the scan does and does not cover is written out at /mcp/security.

What are alternatives to Haiku Rag?

Similar MCP servers include Context7, Cognee, Hindsight. Each serves a similar purpose but may differ in features, language, and compatibility.