Koskamo

VelociRAG MCP

A community-built MCP server providing lightning-fast Retrieval-Augmented Generation for AI agents. It utilizes ONNX Runtime for local inference without PyTorch or GPUs, offering four-layer retrieval fusion including vector similarity, BM25, knowledge graph traversal, and metadata filtering. It supports Unix socket daemons for warm queries and integrates with agents like Claude Code and Cursor.

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

VelociRAG MCP logo, by HaseebKhalid1507Community listingLocal stdioSource reviewed; not executedPublished by HaseebKhalid1507
Vendor documentation

What you can do with it

  • Index local documents for semantic search
  • Perform multi-layer retrieval fusion (vector, BM25, KG)
  • Integrate RAG capabilities into Claude Code or Cursor
  • Run local AI inference without GPU dependencies

Source and maintenance

Community listingRegistry 0.7.4
mcp-registry: io.github.HaseebKhalid1507/velocirag@0.7.4Source repository
Maintenance checked

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

velocirag 0.7.4

pypi
velocirag package definition
{
  "version": "0.7.4",
  "transport": "stdio",
  "identifier": "velocirag",
  "registryType": "pypi",
  "registryBaseUrl": "https://pypi.org"
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.
Cursor configuration
{
  "mcpServers": {
    "velocirag-mcp": {
      "command": "uvx",
      "args": [
        "velocirag==0.7.4"
      ]
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.
Cline configuration
{
  "mcpServers": {
    "velocirag-mcp": {
      "command": "uvx",
      "args": [
        "velocirag==0.7.4"
      ]
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.
VS Code configuration
{
  "servers": {
    "velocirag-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "velocirag==0.7.4"
      ]
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.
Claude Desktop configuration
{
  "mcpServers": {
    "velocirag-mcp": {
      "command": "uvx",
      "args": [
        "velocirag==0.7.4"
      ]
    }
  }
}

Let your agent find its tools

Find servers like VelociRAG MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 3,761