PharosRAG — security grade SAFE, quality 52/100

Security audit verdict: SAFE · quality 52/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Laurent00TT · MCP Server · ★ 243

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is PharosRAG safe to install? View the security audit →

About PharosRAG

Pharos Turn PDFs, scans, docx, pptx and xlsx into a local knowledge base you can ask questions of — with enterprise access control and citations you can trace back to the page. Each RAG component was sharpened on its own, then folded into one repository: multi-identity auth, observability and systemd supervision come with it. A note on language. The code, CLI and commit history are in English; the documentation — including the 12-part learning series — is written in Chinese. This README is the English entry point and covers what the system is, how it is put together and how to run it. For anything deeper, you will be reading Chinese (or machine-translating it). The

agentic-ragembeddingsfastapihybrid-searchknowledge-basellmlocal-firstmcpmodel-context-protocolpython

Quick Facts

Stars243
Forks0
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score51.8460768631138/100
Last Updated2026-08-19
Created2026-05-25
Platformsmcp, python
Est. Tokens~13k

Compatible Skills

These tools work well together with PharosRAG for enhanced workflows:

  • scholar-rag-agent — semantic(0.35)+complementary+rare_topics+same_lang+similar_pop+shared_platform (67%)
  • arag — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (62%)
  • SR-Agents — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)

PharosRAG alternative? Top 6 similar tools

Looking for a PharosRAG alternative? If you're comparing PharosRAG with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • pdf-mcp by jztan · ⭐ 147

    MCP server that lets Claude Code and other AI agents read and search large PDFs, one file or a whole folder: a

  • gno by gmickel · ⭐ 115

    Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP

  • CoWork-OS by CoWork-OS · ⭐ 469

    Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and ar

  • mcp-local-rag by shinpr · ⭐ 405

    Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP o

  • knowledge-rag by lyonzin · ⭐ 288

    Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools,

  • OmoiOS by kivo360 · ⭐ 78

    Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is PharosRAG?

PharosRAG is Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.. It is categorized as a MCP Server with 243 GitHub stars.

What programming language is PharosRAG written in?

PharosRAG is primarily written in Python. It covers topics such as agentic-rag, embeddings, fastapi.

How do I install or use PharosRAG?

You can find installation instructions and usage details in the PharosRAG GitHub repository at github.com/Laurent00TT/PharosRAG. The project has 243 stars and 0 forks, indicating an active community.

What license does PharosRAG use?

PharosRAG is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to PharosRAG?

The top alternatives to PharosRAG on Agent Skills Hub include pdf-mcp, gno, CoWork-OS. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools