Velocirag MCP Server
Lightning-fast RAG for AI agents. _Four-layer retrieval fusion powered by ONNX Runtime. No PyTorch. Sub-200ms warm search. Incremental graph updates. MCP-ready._. It runs locally over stdio via the published package.
People connecting memory tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.
VERIFIED ACTIVE
LAST COMMIT 2026-04-05 · ★ 11 · #176 OF 259 MAINTAINED MEMORY · VERIFIED 2026-08-25
MIT · Python servers · how we verify → /methodology
01 · Install Velocirag
before you install - you'll need
VELOCIRAG_DB
Environment variables documented in the project's README - it lists which are required and which have defaults.
Claude Code
claude mcp add haseebkhalid1507-velocirag -- uvx velocirag Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"haseebkhalid1507-velocirag": {
"command": "uvx",
"args": [
"velocirag"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license MIT - declared in the repository
pypi package velocirag - check the name against the project README before installing (PyPI has no namespace ownership)
registry namespace io.github.HaseebKhalid1507 is GitHub-verified and matches the repo owner
03 · What Velocirag can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
v0.7.4 · 2026-04-05
Performance · WAL mode on all SQLite connections - better concurrent read/write, prevents D-state hangs on HDDs · Async usage tracking - search hit logging moved to background thread, no longer blocks query responses…
v0.7.3 · 2026-04-05
Performance · WAL mode on all SQLite connections - better concurrent read/write, prevents D-state hangs on HDDs · Async usage tracking - search hit logging moved to background thread, no longer blocks query responses…
v0.7.2 · 2026-03-30
Fix BM25 score normalization - missing rank no longer scores as perfect match (was inflating keyword results in fusion) · Fix SQL wildcard injection in metadata LIKE queries (% and _ in filenames) · Fix resource leak…
04 · Who maintains Velocirag
velocirag is maintained by haseebkhalid1507. It's the only MCP server we track from this author; the repo dates to Mar 2026.
05 · Facts
- repository
- github.com/haseebkhalid1507/velocirag
- category
- memory - ranked #176 of 259 actively-maintained memory servers as of 2026-08-25.
- registry
- io.github.HaseebKhalid1507/velocirag (active, first published 2026-03-28 · 6 versions)
- packages
- pypi:velocirag
06 · Velocirag FAQ
What is Velocirag?
Lightning-fast RAG for AI agents. _Four-layer retrieval fusion powered by ONNX Runtime. No PyTorch. Sub-200ms warm search. Incremental graph updates. MCP-ready._. It runs locally over stdio via the published package.
Is Velocirag still maintained?
Yes - as of 2026-08-25, its last commit was 2026-04-05. We re-verify nightly.
How do I install Velocirag?
Run `uvx velocirag`. The README documents one environment variable (VELOCIRAG_DB) to set first. You can also paste the ready-made client config above.
Does Velocirag run locally?
Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Velocirag
Alternatives to Velocirag
Maintained memory servers if Velocirag isn't the fit.
- Codebase Memory Codebase knowledge graph for AI agents - 159 languages, sub-ms queries, 99% fewer tokens. ★ 40,198 · 2026-08-23
- Tradememory Protocol MCP memory for AI trading agents. Store trades, recall similar setups, track strategy performance. ★ 1,412 · 2026-08-11
- Superlog Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents. ★ 1,394 · 2026-08-23
- Persome Local-first personal memory and model server for trusted MCP agents on macOS. ★ 1,314 · 2026-08-21
- Neo4j Memory MCP Neo4j Knowledge Graph Memory Server ★ 979 · 2026-04-10
- Projectmem Local-first memory + judgment layer for AI coding agents - warns before repeating failed fixes. ★ 750 · 2026-08-06
Pairs well with
Servers that cover what Velocirag doesn't - only shown when the pairing reason fits the companion.
More memory MCP servers · Agent Magnet · Cogmemai · Google Knowledge Graph · Memex (iamtouchskyer) · Infranodus MCP Server Infranodus
More Python MCP servers · HOL Guard · Ragstack · Bde Score · Computer-Use Agents API · Web Search · see all