Bring Historical Records
to CrewAI
Learn how to connect National Archives Catalog to CrewAI and start using 40 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the National Archives Catalog MCP Server?
Connect to the National Archives Catalog (NARA) and explore the history of the United States through natural conversation. This MCP server allows your AI agent to act as a specialized research assistant, retrieving historical data, metadata, and digital objects from one of the world's largest archival collections.
What you can do
- Deep Search — Query records by text, tags, comments, or transcriptions to find specific historical context and documents.
- Record Hierarchy — Navigate complex archival structures by retrieving immediate children of specific parent records (NaId).
- User Contributions — Manage and search through tags, comments, and transcriptions provided by the citizen archivist community.
- Metadata Retrieval — Get detailed information, status metrics, and descriptions for specific National Archives Identifiers.
- Tagging & Interaction — Create or delete tags and comments to organize research findings directly within the catalog ecosystem.
How it works
- Subscribe to this server
- Enter your NARA API Key
- Start researching history from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Historians & Researchers — instantly retrieve primary source documents and metadata without manual catalog navigation.
- Educators — find relevant historical photos and records to build curriculum materials directly from a chat interface.
- Genealogists — search through millions of records and transcriptions to find family history data and archival links.
Built-in capabilities (40)
Add a new comment to a record
Add a new tag to a record
Add a new transcription
Remove or deactivate a comment
Deactivate or remove multiple contributions
Remove or deactivate a tag
Utility to fetch JSON data from S3 based on a provided URL
Retrieve a list of all announcements
Retrieve a single comment by ID
Retrieve comments for a specific record
Retrieve comments by a specific contributor
Retrieve contributions for a specific record ID
Retrieve contributions by user ID
Retrieve a list of justifications for administrative actions
Retrieve active announcements
Retrieve immediate children of a specified parent ID
Retrieve statistics on user contributions
Retrieve a single tag by ID
Retrieve tags for a specific record
Retrieve tags by a specific contributor
Retrieve a single transcription by ID
Retrieve transcription history
Retrieve transcriptions for a specific record
Retrieve transcriptions by a specific contributor
Retrieve public data for a specific user
Retrieve user notifications
Retrieve public account data (filterable by email, username, role, etc.)
Search for comment data
Search for contribution data
Search for records using URL parameters
Search records by comments
Search records related to user contributions
Search records by tags
Search records by other extracted text
Search records by transcriptions
Search for tag data
Search for transcription data
Update an existing comment
Add or update a transcription
Update user information
Why CrewAI?
When paired with CrewAI, National Archives Catalog becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call National Archives Catalog 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
National Archives Catalog in CrewAI
National Archives Catalog and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect National Archives Catalog 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 National Archives Catalog in CrewAI
The National Archives Catalog 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 40 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
National Archives Catalog for CrewAI
Every tool call from CrewAI to the National Archives Catalog MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I search for records specifically by the text in their transcriptions?
Yes. Use the search_records_by_transcription tool. This is particularly useful for handwritten documents that have been digitized and transcribed by volunteers.
How do I see the individual items within a larger archival series?
Use the get_record_children tool with the parent NaId. This will list the immediate sub-records or files contained within that specific collection or series.
Can I contribute to the archives by adding tags via the AI?
Yes, the create_tag tool allows you to add descriptive tags to a record using its National Archives Identifier (NaId), helping improve searchability for the community.
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 →
Simian
12 toolsVideo sharing and collaboration platform.
Correlation Matrix Engine
1 toolsGenerate exact Pearson and Spearman correlation matrices across all numeric columns local. Find the strongest relationships in your data without LLM math errors.
Deterministic Codec Engine
4 toolsEmpower your AI to perfectly serialize and deserialize data. Effortlessly switch between URL Encoding, HTML Entities, Unicode Escapes, and DNS Punycode with a native V8 engine.
Aracaju
5 toolsAccess Aracaju's transparency data—revenues, expenses, bids, contracts, and payroll—directly from your AI agent.