Compatible with every major AI agent and IDE
What is the Exa AI MCP Server?
Connect your Exa AI (formerly Metaphor) account to any AI agent and take full control of your web research and data extraction workflows through natural conversation.
What you can do
- Semantic Search Orchestration — Perform AI-native searches that understand intent and meaning to retrieve the most relevant web pages programmatically
- Content Intelligence — Programmatically extract clean, parsed text or highlights from any URL, excluding ads and boilerplate automatically
- Similarity Discovery — Find pages semantically similar to a source URL to build comprehensive and high-fidelity research datasets
- Deep Data Mapping — Discover all reachable links on a domain and retrieve discovery metadata to understand site structures programmatically
- Search Filtering — Restricted searches by domain, category (company, blog, news), or discovery date directly through your agent
How it works
- Subscribe to this server
- Retrieve your API Key from the Exa AI dashboard (Settings > API Keys)
- Start searching the web semantically from Claude, Cursor, or any MCP client
No more manual keyword-based searching or messy scraping scripts. Your AI acts as your dedicated neural research assistant.
Who is this for?
- AI Developers — build RAG pipelines by programmatically ingesting semantically relevant web data using natural language
- Market Researchers — instantly identify competitors and find similar companies across the web using semantic discovery
- Content Analysts — automate the extraction of highlights and clean text from technical blogs and news without leaving your workspace
Built-in capabilities (12)
Complex search query
Retrieve web page text
Find matches for a URL
Check connection
Extract relevant snippets
Search by exact keywords
Fresh web extraction
Search by site type
Search by discovery date
Search within sites
Search and extract text
Perform AI-native search
Why CrewAI?
When paired with CrewAI, Exa AI becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Exa AI tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
- —
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the
mcpsparameter and agents auto-discover every available tool at runtime - —
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
- —
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
Exa AI in CrewAI
Exa AI and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Exa AI to CrewAI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Exa AI in CrewAI
The Exa AI MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in CrewAI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Exa AI for CrewAI
Every tool call from CrewAI to the Exa AI MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find my Exa AI API Key?
Log in to your Exa AI dashboard, and copy your unique API Key from the settings section.
What makes semantic search different?
Traditional search uses keywords. Semantic search uses neural embeddings to understand the meaning and context of your query, finding better matches.
Can I extract text from multiple URLs at once?
Yes! The extract_page_content tool accepts a JSON array of URLs and retrieves the parsed content for all of them programmatically.
How does CrewAI discover and connect to MCP tools?
CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
Can different agents in the same crew use different MCP servers?
Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
What happens when an MCP tool call fails during a crew run?
CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
Can CrewAI agents call multiple MCP tools in parallel?
CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
Can I run CrewAI crews on a schedule (cron)?
Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.
MCP tools not discovered
Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
Agent not using tools
Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
Timeout errors
CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
Rate limiting or 429 errors
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.
Explore More MCP Servers
View all →
Piwik PRO
6 toolsManage privacy-first analytics via Piwik PRO — list apps, execute custom queries, and monitor goals directly from any AI agent.

Holded
12 toolsRun your business in Spain and Latin America with invoicing, accounting, CRM, and inventory that speaks your language natively.

Moodle
12 toolsPower your e-learning environment with the world most flexible open-source LMS for course creation and student management.

Common Paper
10 toolsCommon Paper helps you create, send, and sign standard commercial contracts faster. Use this MCP server to automate your contract workflow and track agreement status.
