Airweave Search
- 6.5k repo stars
- Updated June 5, 2026
- airweave-ai/airweave
Airweave Search is an MCP server that lets agents run natural-language queries against a configured Airweave collection.
About
Airweave Search is an MCP server that exposes semantic search over your Airweave collections so Claude Code, Cursor, and similar agents can answer questions grounded in whatever you have already ingested—docs, tickets, notes, or internal knowledge. developers shipping RAG-backed assistants or in-repo copilots install it when hard-coding retrieval calls is too slow and they want a standard tool surface the agent can call during implementation and debugging. You choose one collection per configuration, authenticate with an API key, and point either stdio (npm) or the hosted streamable-http endpoint at your agent config. It is not a full ingestion pipeline; you still manage what lands in Airweave elsewhere. The payoff is faster integration: your agent gets NL query access without you maintaining bespoke search endpoints for every project.
- Natural-language search tools against a single Airweave collection per connection
- stdio npm package airweave-mcp-search v0.9.9 plus streamable-http remote at mcp.airweave.ai/mcp
- Auth via AIRWEAVE_API_KEY or X-API-Key header plus AIRWEAVE_COLLECTION or X-Collection-Readable-ID
- Optional AIRWEAVE_BASE_URL override defaulting to https://api.airweave.ai
Airweave Search by the numbers
- Data as of Jul 27, 2026 (Skillselion catalog sync)
claude mcp add --env AIRWEAVE_API_KEY=YOUR_AIRWEAVE_API_KEY --env AIRWEAVE_COLLECTION=YOUR_AIRWEAVE_COLLECTION --env AIRWEAVE_BASE_URL=YOUR_AIRWEAVE_BASE_URL airweave-mcp-search -- npx -y airweave-mcp-searchAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 6.5k |
|---|---|
| Package | airweave-mcp-search |
| Transport | STDIO, HTTP |
| Auth | Required |
| Last updated | June 5, 2026 |
| Repository | airweave-ai/airweave ↗ |
What it does
Let your coding agent query indexed docs and data in an Airweave collection with natural language instead of wiring a custom search API.
Who is it for?
Best when you have an existing Airweave collection and want agent-side retrieval without writing search microservices.
Skip if: Skip if you have no Airweave account, no indexed collection yet, or needs for multi-tenant search orchestration outside one collection ID.
What you get
After registration, the agent can search your Airweave collection through MCP tools using your API key and collection ID.
- MCP tools callable by the agent for NL search over one collection
- Configured stdio or remote MCP entry in the agent manifest
By the numbers
- Server version 0.9.9
- 1 npm package with stdio transport
- 1 streamable-http remote endpoint
README.md
Open-source context retrieval layer for AI agents and RAG systems.
What is Airweave?
Airweave connects to your apps, tools, and databases, continuously syncs their data, and exposes it through a unified, LLM-friendly search interface. AI agents query Airweave to retrieve relevant, grounded, up-to-date context from multiple sources in a single request.
Where it fits
Airweave sits between your data sources and AI systems as shared retrieval infrastructure. It handles authentication, ingestion, syncing, indexing, and retrieval so you don't have to rebuild fragile pipelines for every agent or integration.
How it works
- Connect your apps, databases, and documents (50+ integrations)
- Airweave syncs, indexes, and exposes your data through a unified retrieval layer
- Agents query Airweave via our SDKs, REST API, MCP, or native integrations with popular agent frameworks
- Agents retrieve relevant, grounded context on demand
Quickstart
Cloud-hosted: app.airweave.ai
Self-hosted
git clone https://github.com/airweave-ai/airweave.git
cd airweave
./start.sh
Requires Docker and docker-compose
Supported Integrations
SDKs
pip install airweave-sdk # Python
npm install @airweave/sdk # TypeScript
from airweave import AirweaveSDK
client = AirweaveSDK(api_key="YOUR_API_KEY")
results = client.collections.search.instant(
readable_id="my-collection",
query="Find recent failed payments"
)
CLI
Search collections, manage sources, and trigger syncs from your terminal:
pip install airweave-cli
airweave auth login
airweave search "quarterly revenue figures" --collection finance-data
The CLI outputs rich interactive results in your terminal and clean JSON when piped — making it work for both developers and AI agents.
Tech Stack
- Frontend: React/TypeScript with ShadCN
- Backend: FastAPI (Python)
- Databases: PostgreSQL (metadata), Vespa (vectors)
- Workers: Temporal (orchestration), Redis (pub/sub)
- Deployment: Docker Compose (dev), Kubernetes (prod)
Contributing
We welcome contributions! See our Contributing Guide.
License
Recommended MCP Servers
0Latency MemoryPersistent memory layer for AI agents.
0nMCP — Universal AI API OrchestratorUniversal AI API Orchestrator — 1,554 tools, 96 services.
0xHumans Protocol MCPMCP for AI agents: financing, skills, lending on Base1k Patient Mcp1k patient MCP server
1trippulse1trip PULSE: 21-tool AI travel planner.
3D AI Agent Avatar3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.89How it compares
MCP retrieval bridge over Airweave collections, not a document-ingestion or embedding pipeline skill.
FAQ
Who is Airweave Search for?
Developers using AI coding agents who already use Airweave and want natural-language search exposed as MCP tools.
When should I use Airweave Search?
Use it during Build when wiring agent context to private or project knowledge that lives in a specific Airweave collection.
How do I add Airweave Search to my agent?
Install the npm package airweave-mcp-search for stdio or add the remote https://mcp.airweave.ai/mcp with X-API-Key and X-Collection-Readable-ID, set AIRWEAVE_API_KEY and AIRWEAVE_COLLECTION for local runs, then restart the agent.