Airweave Search

airweave-ai/airweave

Connects Claude directly to your Airweave collections so you can search across synced data from 50+ sources using natural language. Instead of building separate integrations for GitHub, Notion, Jira, Google Drive, and everything else, you point Airweave at your data sources once and then query everything through a single search interface. The MCP server exposes search operations that let Claude retrieve context from your connected apps on demand. Useful when you're building agents that need grounded, up-to-date information from multiple tools without maintaining a mess of API clients and sync jobs. Works with both Airweave Cloud and self-hosted instances.

GitHub stars: 6.4K
tools: 2
auth: Secret needed
transport: STDIO, HTTP
env vars: 3
last updated: Apr 7, 2026

View on GitHub

Tools

2 tools

Public tool metadata for what this MCP can expose to an agent.

web_search_previewPurpose: Perform web searches and return results in an LLM-friendly format and with parameters tuned for LLMs.2 params

Purpose: Perform web searches and return results in an LLM-friendly format and with parameters tuned for LLMs.

Parameters* required

objectivestring

Natural-language description of what the web search is trying to find. Try to make the search objective atomic, looking for a specific piece of information. May include guidance about preferred sou...

search_queriesarray

List of keyword search queries of 3-6 words, which may include search operators. The search queries should be related to the objective. Limited to 3 entries of 100 characters each.

web_fetchPurpose: Fetch and extract relevant content from specific web URLs. Ideal Use Cases: - Extracting content from specific URLs you've already identified - Exploring URLs returned by a web search in greater depth2 params

Purpose: Fetch and extract relevant content from specific web URLs. Ideal Use Cases: - Extracting content from specific URLs you've already identified - Exploring URLs returned by a web search in greater depth

Parameters* required

objectivevalue

Natural-language description of what information you're looking for from the URLs. Limit to 200 characters.

urlsarray

List of URLs to extract content from. Must be valid HTTP/HTTPS URLs. Maximum 10 URLs per request.

Configuration

AIRWEAVE_API_KEY*secret

Your Airweave API key for authentication

AIRWEAVE_COLLECTION*

The Airweave collection to search

AIRWEAVE_BASE_URL

Airweave API base URL (defaults to https://api.airweave.ai)

Readme

Airweave

Open-source context retrieval layer for AI agents and RAG systems.

View the full README on GitHub

Details

Repository: github.com/airweave-ai/airweave
Category: Search & Web Crawling
Package: airweave-mcp-search
Transport: STDIO, HTTP
Auth: Required
Registry: MCP registry, active

Related Search & Web Crawling MCP servers

View all

Paper Searchopenags/paper-search-mcpA MCP for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.1.5Kstars

Fetchzcaceres/fetch-mcpA flexible HTTP fetching Model Context Protocol server.758stars

Everything Searchmamertofabian/mcp-everything-searchFast file search: Everything SDK on Windows, Spotlight (mdfind) on macOS, locate/plocate on Linux.367stars

G-Searchjae-jae/g-search-mcpA powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously.263stars

Pare Searchdave-london/parePare Search ג€” Structured code search operations (ripgrep + fd) as typed JSON.128stars

Documentation Extractornirholas/extract-llms-docsExtract llms.txt from any docs site - Mintlify Docusaurus GitBook parser29stars