semble MCP Server
MinishLab/semble
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
MinishLab/semble is a Python tool licensed under MIT. Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read Topics: agents, code-search, embeddings, mcp, mcp-server, model-context-protocol, retrieval.
Ranked #66 out of 24840 indexed tools.
In the top 1% of all indexed tools.
Has 6,140 GitHub stars.
Has 10 contributors.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
6,140 stars → well-known project
Last commit today → actively maintained
99/101 issues closed → responsive maintainer
10 contributors → active community
No dependents → no downstream usage
18,801 weekly installs → widely installed
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/MinishLab--semble/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/MinishLab--semble/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/badge/tool/MinishLab--semble" alt="AgentRank"></a> Matched Queries
From the README
<h2 align="center">
<br/>
Fast and Accurate Code Search for Agents<br/>
<sub>Uses ~99% fewer tokens than grep+read</sub>
</h2>
<div align="center">
<h2>
<a href="https://pypi.org/project/semble/"></a>
<a href="https://app.codecov.io/gh/MinishLab/semble">
</a>
<a href="https://github.com/MinishLab/semble/blob/main/LICENSE">
</a>
</h2>
[Quickstart](#quickstart) •
[CLI](#cli) •
[MCP Server](#mcp-server) •
[Installation](docs/installation.md) •
[Benchmarks](#benchmarks)
</div>
Semble is a code search library built for agents. It returns the exact code snippets they need instantly, using ~99% fewer tokens than grep+read. Indexing and searching a full codebase end-to-end takes under a second for most repos, matching the retrieval quality of a code-specialized transformer while indexing ~380x faster and querying ~17x faster (see [benchmarks](#benchmarks)). Everything runs on CPU with no API keys, GPU, or external services. Use it as an MCP serve Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.