Official descriptionMCP servers3d ago
GitHub
bloop is a fast code search engine written in Rust.
- Source
- collected from the e2b-dev/awesome-ai-agents list · type: MCP server
- Harvest history
- first seen 2026-10-14 · last seen 2026-10-16 · seen 5× · listed by 1 sources
- Score
- score 103 · 1 sources · mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
first catalogued 2026-10-14;last seen 2026-10-16。There is no official certification or quality rating here — we record sources and dates only.
Third-party quality signals




bloop is ChatGPT for your code. Ask questions in natural language, search for co
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Engineers are increasing their productivity by using bloop to:
- Explain how files or features work in simple language
- Write new features, using their code as context
- Understand how to use poorly documented open source libraries
- Pinpoint errors
- Ask questions about English language codebases in other languages
- Reduce code duplication by checking for existing functionality
https://github.com/BloopAI/bloop/assets/7957964/01db3ccb-4af0-49a0-92d6-5a9c42357a51
Features
- AI-based conversational search
- Code Studio, an LLM playground that uses your code as context
- Blazing fast regex search
- Sync your local and GitHub repositories
- Sophisticated query filters so you can narrow down your results
- Find functions, variables or traits with symbol search
- Precise code navigation (go-to-reference and go-to-definition) for 10+ of the most popular languages built with Tree-sitter
- Privacy focussed on-device embedding for semantic search
bloop stands on the shoulders of the Rust ecosystem. Our search indexes are powered by Tantivy and Qdrant, and our multi-platform app is built with Tauri.
https://github.com/BloopAI/bloop/assets/7957964/93715188-d8d5-477b-8cd1-95d9cbd368cb
Get Started
The simplest way to get started with bloop is to download the app and follow the onboarding steps. Checkout our getting started guide and our references for conversational and regex search and Code Studio.
For instructions on how to build from source or run bloop from the command line, check out these pages:
- Build bloop app from source
- Run bloop from the command line
If you encounter any index issues you can wipe the bloop cache and reindex. Instructions on how to do this on different platforms are here.
Building From Source
You can build bloop from source and run it with your own OpenAI API key. Clone the repo, make sure the oss branch is checked out, and create a file called local_config.json at the top-level of the repo. local_config.json should contain the following fields:
Then follow these installation instructions. If built from source, bloop will not collect any telemetry.
Contributing
We welcome contributions big and small! Before jumping in please read our contributors guide and our code of conduct.
Here's how to find your way around the repo:
- apps/desktop: The Tauri app
- server/bleep: The Rust backend which contains the core search and navigation logic
- client: The React frontend
We use Git LFS for dependencies that are expensive to build.
To make sure you have everything you need to start building, you'll need to
- Source
- awesome
· https://github.com/BloopAI/bloop
- Browse by field
- MCP servers
- added
- yesterday
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.
Browse all fields →
← Back to index