io.github.IBazylchuk/paparats-mcpsearch

Paparats MCP: Self-Hosted Semantic Code Search

Verified · 23 days ago

Self-hosted semantic code search MCP for Claude Code & Cursor. Multi-repo, AST-aware, stays local.

Install

claude mcp add paparats-mcp -- npx -y @paparats/[email protected]

Our take

Local-first semantic code search stack for coding agents, backed by Qdrant/Ollama with a CLI and server package. It is more substantial than a thin wrapper: the repo includes server tests, indexing code, project management, and install/update flows. The setup is heavier than most MCP servers because it can start containers and download an embedding model, but that happens through explicit commands, not postinstall.

reviewed by hand · 2026-07-05

Something wrong or dead here? Report it

Verification record

last verified
23 days ago
github stars
14
last commit
23 days ago
archived
no
license
MIT
downloads / wk
2.4k
latest version
2.16.0
in registry since
2026-07-24

github.com/IBazylchuk/paparats-mcp

mcp-server-searchsearch

mcp-server-search

Verified · 12 days ago

MCP server for web search operations

hand-reviewed40k starschecked 12 days ago

repomixsearch

Repomix

Verified · 2 mo ago

Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search

hand-reviewed28k stars67k dl/wkchecked 2 mo ago

screenpipe-mcpsearch

screenpipe

Verified · 2 mo ago

Search your local screen recordings, audio transcripts, and computer activity from screenpipe.

hand-reviewed22k stars2.8k dl/wkchecked 2 mo ago

xerjsearch

XERJ

Verified · 26 days ago

The search engine for AI agents: cited answers from your local code, docs, specs and logs.

hand-reviewed15k starschecked 26 days ago

sui-kapasearch

Sui Knowledge Base (kapa.ai)

Verified · 15 days ago

Semantic search across Sui documentation and knowledge sources, powered by kapa.ai

hand-reviewed7.8k starschecked 15 days ago

firecrawl-mcp-serversearch

Firecrawl MCP Server

Verified · 29 days ago

Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.

hand-reviewed7.7k starschecked 29 days ago