Taking on 2–3 new engagements in 2026 — EST & PST hours

Start a Conversation
Search★ 4,200

Semble

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

by MinishLab · MinishLab/semble

How to use Semble with Claude

Semble is a Model Context Protocol (MCP) server that gives Claude and other AI agents direct access to search capabilities. Once installed, you can use it in Claude Desktop, Cursor, or any MCP-compatible client.

About Semble

Python★ 4,200 starsUpdated May 2026Source: github

Semble is an open-source MCP server in the Search category, built in Python. It connects Claude and other MCP-compatible clients to search systems directly. Source available on GitHub.

Use cases for Search MCP servers

  • Run semantic and keyword searches across multiple indices
  • Summarize and cluster search results automatically
  • Integrate external search APIs into AI agent workflows
  • Build RAG pipelines connecting AI to live search indexes

Where Semble fits in an MCP workflow

Teams use Semble to give Claude a direct bridge into search workflows, so routine actions happen inside the AI client instead of across separate tabs and dashboards.

Semble can be connected to MCP clients by following the repository setup instructions, making it useful for teams that want AI access to search systems.

More Search MCP servers

Built with MCP?

Altor deploys MCP servers into production for B2B engineering teams.

We connect AI agents to your live systems — ClickHouse, Linear, Stripe, GitHub — using MCP and deploy them to production in 3 weeks. Not demo.

Talk to Altor →