MCP100 Assessment

Editorial verdict

Airweave MCP server that lets AI clients search data synchronized into an Airweave collection. Capabilities: Search synced Airweave collection data; Run locally over stdio; Run hosted over Streamable HTTP

Reviewed October 21, 2026

Task Fit

Mapped

Web search and research

Trust

Status warning

maintenance_source_health; client_coverage; tool_contract; install_supply_chain; advisory_freshness; adoption_evidence_presence

Maintenance

Date unavailable

No dated repository or package update is currently stored.

Popularity

Signals available

Visible usage signals are shown for discovery only, not as proof of safety.

Best for

Teams that want MCP search over data already synchronized into Airweave.

Not ideal for

Users who need a broadly proven, low-risk, fully mature Recommended-grade integration today.

Avoid if

Avoid high-impact or sensitive production use unless the documented authentication, permissions, rollback, and data handling match your environment.

Trade-offs

Source ACL propagation, tenancy/retention guarantees and MCP operational maturity need stronger Recommended-grade evidence.

Evidence scope

Evidence

Current source snapshot

Popularity

6.6k shared-repository stars · not MCP-specific

2.8k package downloads / 30 days

Repository identity: airweave-ai/airweave

Package identity: airweave-mcp-search · version 0.9.62

Stars observed October 21, 2026 · Downloads observed October 21, 2026

Repository evidence: shared_archived_monorepo. Not MCP-specific/comparable for MCP-server adoption. Do not treat archived monorepo stars as MCP-specific adoption. Official docs and hosted endpoint remain current.

Package evidence: exact. Exact current MCP implementation/distribution. Do not treat archived monorepo stars as MCP-specific adoption. Official docs and hosted endpoint remain current.

Maintenance

Publisher activity observed October 21, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed October 21, 2026

Sources

GitHub repository ↗Official documentation ↗

Supporting evidence (3)

Evidence source — airweave.ai/ ↗Evidence source — registry.npmjs.org/airweave-mcp-search ↗Evidence source — mcp.airweave.ai/mcp ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Transport not recorded

Publisher documented

Hosted Streamable HTTP at `https://mcp.airweave.ai/mcp`; authenticate with API key or OAuth and select the collection using the official collection header. Local alternative: `npx -y airweave-mcp-search` with `AIRWEAVE_API_KEY`, `AIRWEAVE_COLLECTION`, optional `AIRWEAVE_BASE_URL`.

The publisher provides client-specific setup instructions.

Verify safely: Claude Code: `claude mcp list` and/or `/mcp` to confirm Connected; use any stronger vendor-documented smoke test where listed.

Uninstall and revoke

Claude Code: `claude mcp remove <name>`; also revoke OAuth/device/API credentials in the vendor account when the vendor provides such a control.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-09-20T00:00:00.000Z

Evidence 1 ↗

Reviewed setup

Type-appropriate, source-backed setup for this mcp server profile.

Endpoint: https://mcp.airweave.ai/mcp
Setup notes: Source rechecked October 21, 2026: Official Airweave MCP Search server; local stdio and hosted Streamable HTTP Lifecycle: current docs and service; historical implementation monorepo archived. Do not treat archived monorepo stars as MCP-specific adoption. Official docs and hosted endpoint remain current.

Read additional publisher installation details

From the publisher README

Publisher installation details

Original client setup and configuration retained from the publisher documentation.

View original README ↗

Quickstart

Cloud-hosted: app.airweave.ai

Self-hosted

git clone https://github.com/airweave-ai/airweave.git
cd airweave
./start.sh

→ http://localhost:8080

Requires Docker and docker-compose

Loading optional publisher installation details…

Show source-catalog configuration

Hosted Streamable HTTP at `https://mcp.airweave.ai/mcp`; authenticate with API key or OAuth and select the collection using the official collection header. Local alternative: `npx -y airweave-mcp-search` with `AIRWEAVE_API_KEY`, `AIRWEAVE_COLLECTION`, optional `AIRWEAVE_BASE_URL`.

Capability

What it does

Airweave MCP server that lets AI clients search data synchronized into an Airweave collection. Capabilities: Search synced Airweave collection data; Run locally over stdio; Run hosted over Streamable HTTP

Search & WebSoftware & Technology

Representative uses

Teams that want MCP search over data already synchronized into Airweave.

Important limits

Users who need a broadly proven, low-risk, fully mature Recommended-grade integration today.

Context Footprint

Not measured yet

Estimated token footprint of the MCP tool schemas exposed to the agent.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Hosted mode supports API key and OAuth 2.0.
Permissions: Effective access is bounded by the Airweave collection and source connections available to the authenticated identity.
Data handling: Queries can expose content synced from connected sources; cloud/local deployment and source connectors determine storage and residency.
Cost: Airweave service/infrastructure and source systems may have costs.
Risk and cautions: Source ACL propagation, tenancy/retention guarantees and MCP operational maturity need stronger Recommended-grade evidence.

Related reviewed MCPs

Other options

Hugging Face MCP

MCP100 Recommended

Search Hugging Face Hub resources and use explicitly enabled Jobs, sandboxes, and community Space tools.

Choose this instead if

Choose Hugging Face MCP instead if searching models, datasets, Spaces, papers, and Hugging Face documentation.

Search Hugging Face Hub resources and use explicitly enabled Jobs, sandboxes, and community Space tools.

Compare with Airweave Search View Hugging Face MCP details

Firecrawl MCP

MCP100 Recommended

Search, scrape, crawl, and extract web content through Firecrawl.

Choose this instead if

Choose Firecrawl MCP instead if scraping and extracting public web pages.

Search, scrape, crawl, and extract web content through Firecrawl.

Compare with Airweave Search View Firecrawl MCP details

Perplexity MCP

MCP100 Recommended

Connect compatible AI clients to Perplexity's documented MCP capabilities.

Choose this instead if

Choose Perplexity MCP instead if current web search and cited question answering with Perplexity APIs.

Recommended first-party Perplexity MCP for real-time search, question answering, reasoning, and deep research through a small four-tool surface.

Compare with Airweave Search View Perplexity MCP details

Read publisher documentation

Publisher documentation

Publisher README

Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.

View original README ↗

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

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

MIT License

Loading optional publisher documentation…

FAQ

Is this an official MCP?

endpoint:https: is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗