Pydantic AISDK

National Archives Catalog MCP Server

Bring Historical Records
to Pydantic AI

Name: National Archives Catalog MCP Server
Price: 29 USD
Availability: InStock
Rating: 0.2 (1 reviews)
Author: Vinkius

Learn how to connect National Archives Catalog to Pydantic AI 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 Subscribers

Create CommentCreate TagCreate TranscriptionDelete CommentDelete ContributionsDelete TagFetch CoordsGet AnnouncementsGet CommentGet Comments By NaidGet Comments By UseridGet Contributions By Target NaidGet Contributions By UseridGet JustificationsGet Latest AnnouncementsGet Record ChildrenGet Record StatsGet TagGet Tags By NaidGet Tags By UseridGet TranscriptionGet Transcription HistoryGet Transcriptions By NaidGet Transcriptions By UseridGet UserGet User NotificationsGet UsersSearch CommentsSearch ContributionsSearch RecordsSearch Records By CommentSearch Records By ContributionSearch Records By TagSearch Records By TextSearch Records By TranscriptionSearch TagsSearch TranscriptionsUpdate CommentUpdate TranscriptionUpdate User

Unlock for AI Agents

Ask AI about this MCP Server ChatGPT Claude Perplexity

Compatible with every major AI agent and IDE

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

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)

create_comment

Add a new comment to a record

create_tag

Add a new tag to a record

create_transcription

Add a new transcription

delete_comment

Remove or deactivate a comment

delete_contributions

Deactivate or remove multiple contributions

delete_tag

Remove or deactivate a tag

fetch_coords

Utility to fetch JSON data from S3 based on a provided URL

get_announcements

Retrieve a list of all announcements

get_comment

Retrieve a single comment by ID

get_comments_by_naid

Retrieve comments for a specific record

get_comments_by_userid

Retrieve comments by a specific contributor

get_contributions_by_target_naid

Retrieve contributions for a specific record ID

get_contributions_by_userid

Retrieve contributions by user ID

get_justifications

Retrieve a list of justifications for administrative actions

get_latest_announcements

Retrieve active announcements

get_record_children

Retrieve immediate children of a specified parent ID

get_record_stats

Retrieve statistics on user contributions

get_tag

Retrieve a single tag by ID

get_tags_by_naid

Retrieve tags for a specific record

get_tags_by_userid

Retrieve tags by a specific contributor

get_transcription

Retrieve a single transcription by ID

get_transcription_history

Retrieve transcription history

get_transcriptions_by_naid

Retrieve transcriptions for a specific record

get_transcriptions_by_userid

Retrieve transcriptions by a specific contributor

get_user

Retrieve public data for a specific user

get_user_notifications

Retrieve user notifications

get_users

Retrieve public account data (filterable by email, username, role, etc.)

search_comments

Search for comment data

search_contributions

Search for contribution data

search_records

Search for records using URL parameters

search_records_by_comment

Search records by comments

search_records_by_contribution

Search records related to user contributions

search_records_by_tag

Search records by tags

search_records_by_text

Search records by other extracted text

search_records_by_transcription

Search records by transcriptions

search_tags

Search for tag data

search_transcriptions

Search for transcription data

update_comment

Update an existing comment

update_transcription

Add or update a transcription

update_user

Update user information

Why Pydantic AI?

Pydantic AI validates every National Archives Catalog tool response against typed schemas, catching data inconsistencies at build time. Connect 40 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

—
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
—
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your National Archives Catalog integration code
—
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
—
Dependency injection system cleanly separates your National Archives Catalog connection logic from agent behavior for testable, maintainable code

See it in action

National Archives Catalog in Pydantic AI

AI Agent→Vinkius

High Security·Kill Switch·Plug and Play

Why Vinkius

National Archives Catalog and 4,000+ other MCP servers. One platform. One governance layer.

Teams that connect National Archives Catalog to Pydantic AI 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.

4,000+MCP Servers ready

<40msCold start

60%Token savings

	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

Unlock for AI Agents View step-by-step setup guide for Pydantic AI →

Enterprise Security

Why teams choose Vinkius for National Archives Catalog in Pydantic AI

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 Pydantic AI 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.

Unlock for AI Agents View full National Archives Catalog details →

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

The Vinkius Advantage

How Vinkius secures
National Archives Catalog for Pydantic AI

Every tool call from Pydantic AI to the National Archives Catalog MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.

< 40msCold start

Ed25519Signed audit chain

60%Token savings

FAQ

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 Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your National Archives Catalog MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.