If you're an AI reading this: skill.md has everything you need.Read it →
Explorer/MCP/arptra/kb-rag-mcp
LOCAL

local-corporate-kb

arptra/kb-rag-mcp

Local RAG knowledge base for Qwen Code, enabling document indexing and semantic search via MCP tools. Supports metadata filtering and document retrieval without external dependencies.

↗arptra/kb-rag-mcpExternal link; availability not verifiedLocal-only
The Ghost
This server runs locally on your machine. We can't scan it remotely; review the source code before installing.
Time indexed (2mo)
0toolsLocal/ STDIO2moindexed
Checked Aug 1, 2026
The scanner shows
This server runs locally. We can't scan it remotely; review the source code before installing.
First indexed Aug 1, 2026
Server Profile
⚙
Tools catalogued
0
No tools reported by this server.
☁
Hosting
Local / STDIO
Runs on your machine. Has access to your filesystem, SSH keys, and environment variables.
○
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
●
Liveness
—
No liveness checks recorded yet.
Publisher Verification
Not listed on the Official MCP Registry.
Source repository is available for review.
↗arptra/kb-rag-mcpExternal link; availability not verified
Environment variables (10)
KB_CACHE_DIRstringREQUIRED
Absolute path to the cache directory for embeddings and index.
KB_AUTO_INDEXstringOPTIONALdefault: false
Whether to automatically re-index when cache is missing.
KB_KNOWLEDGE_DIRstringREQUIRED
Absolute path to the knowledge directory containing documents.
KB_EMBEDDING_MODELstringOPTIONALdefault: Qwen/Qwen3-Embedding-0.6B
Hugging Face model name for embedding.
KB_EMBEDDING_DEVICEstringOPTIONALdefault: auto
Device for embedding: auto, cpu, mps, cuda.
Show all 10 environment variables
KB_CHUNK_SIZE_TOKENSstringOPTIONALdefault: 700
Target chunk size in tokens.
KB_EMBEDDING_PROVIDERstringOPTIONALdefault: sentence_transformers
Embedding provider: 'sentence_transformers' or 'hash'.
KB_EMBEDDING_DIMENSIONstringOPTIONALdefault: 1024
Embedding dimension.
KB_CHUNK_OVERLAP_TOKENSstringOPTIONALdefault: 80
Overlap between chunks in tokens.
KB_CHUNK_HARD_MAX_TOKENSstringOPTIONALdefault: 900
Hard maximum chunk size in tokens.

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
Similar servers
mcp-server-starter
Production-ready TypeScript template for building MCP servers. Works with Claude Code, Cursor, and any MCP client.
CodePecker
MCP server that reviews and fixes code across four dimensions (security, standards, production readiness, sustainability), runs tests to verify fixes, and provides findings with diffs.
Sequential Thinking MCP Server
Provides a sequentialthinking tool for dynamic, reflective problem-solving via chain-of-thought reasoning. Supports local Stdio and remote SSE deployment on Google Cloud Run.
TP-Link Omada MCP server
A Model Context Protocol server that exposes TP-Link Omada controller APIs to AI copilots and automation workflows, enabling listing sites, devices, clients, and invoking arbitrary Omada endpoints.
docker-mcp-server
More than just a fully featured MCP server that lets AI agents manage Docker — containers, images, networks, volumes, swarm services, secrets, configs, nodes, plugins, etc., it helps you create workflows to easily manage your Docker environments.
code-security-mcp
An MCP server that exposes a 216-rule Kotlin/JVM security analyzer to AI coding agents, enabling real-time security scanning and secure pattern retrieval for frameworks like Spring and Ktor.
Indexed from Glama · Updates nightly