Bring Neural Search
to CrewAI
Learn how to connect Exa to CrewAI and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Exa MCP Server?
Connect Exa (formerly Metaphor) to any AI agent and simplify how you discover relevant web data, research topics using neural embeddings, and extract cleaned content through natural conversation.
What you can do
- Neural Search — Perform AI-powered searches that understand the meaning and intent of your query, not just keywords.
- Semantic Similarity — Find web pages and articles that are semantically similar to a specific seed URL.
- Content Extraction — Fetch cleaned, readable text and metadata from multiple URLs or page IDs in a single request.
- Research Automation — Discover high-quality sources and analyze web content programmatically via AI.
- Data Insights — retrieve comprehensive metadata for search results to identify top-performing resources.
- Intelligent Discovery — Use 'Autoprompt' to automatically optimize your queries for neural search accuracy.
How it works
1. Subscribe to this server
2. Enter your Exa API Key (found in your account dashboard)
3. Start searching the web for your AI projects from Claude, Cursor, or any MCP client
Who is this for?
- AI Developers & Researchers — quickly find semantically relevant data and clean web content via simple AI commands.
- Content Strategists — discover similar articles and research topics across the web directly from the workspace.
- Knowledge Workers — automate information discovery and extract key insights via the AI assistant.
Built-in capabilities (10)
Get an AI answer
Great for competitive analysis and research. Find similar pages
Find similar pages with content
Extract page contents
Returns titles, URLs, and relevance scores for matching pages. Search the web with AI
Useful for site-specific research or documentation lookups. Search within a domain
Traditional keyword search
Ideal for conceptual queries and research topics. Neural semantic search
Ideal for news and trending topics. Search recent content
Search and extract page content
Why CrewAI?
When paired with CrewAI, Exa becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Exa 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 in CrewAI
Exa and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Exa 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 | 3,400+ 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 in CrewAI
The Exa 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 10 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 for CrewAI
Every tool call from CrewAI to the Exa MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I perform a meaning-based search instead of keywords via AI?
Yes! Use the search tool. Provide your query and enable useAutoprompt. Exa will use its neural embeddings to find links that match the intent of your question.
How do I find articles similar to a specific URL?
Use the find_similar tool. Provide the seed URL, and the agent will retrieve a list of pages that are semantically related to that content.
Is it possible to extract cleaned text from multiple pages via AI?
Absolutely. Use the get_contents query. Provide an array of URLs or Exa IDs, and the agent will return the cleaned text content and metadata for each page.
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.