Skip to main content The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery
Live 29 Actions

National Park Service MCP Server
for AI Agents

Connect your AI agent to StackOne's National Park Service MCP server and give it 29 MCP tools out of the box. Auth, tool execution, and security all managed.

National Park Service logo
National Park Service MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

29 Agent Actions

Create, read, update, and delete across National Park Service — and extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your National Park Service MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every National Park Service tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every National Park Service call.

Tools Discovery →

What is the National Park Service MCP Server?

A National Park Service MCP server lets AI agents read and write National Park Service data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's National Park Service MCP server ships with 29 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All National Park Service MCP Tools

Every action from National Park Service's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Other (29)

  • List Parks

    Retrieve a list of national parks with details such as descriptions, directions, operating hours, and contact information.

  • Get Park Boundaries

    Retrieve GeoJSON boundary data for a specific national park site.

  • List Activities

    Retrieve activity categories available across national parks.

  • List Parks By Activity

    Find national parks that offer a specific activity type.

  • List Things To Do

    Retrieve recommended activities and things to do at national parks.

  • List Alerts

    Retrieve park safety alerts, closures, and condition updates.

  • List Amenities

    Retrieve amenity types available across national parks.

  • List Amenities At Park Places

    Find amenities available at specific places within national parks.

  • List Amenities At Visitor Centers

    Find amenities available at national park visitor centers.

  • List Articles

    Retrieve articles and editorial content about national parks.

  • List People

    Retrieve articles about notable people associated with national parks.

  • List Places

    Retrieve articles about specific locations and landmarks within national parks.

  • List News Releases

    Retrieve news releases and press announcements from national parks.

  • List Lesson Plans

    Retrieve educational lesson plans and materials from national parks.

  • List Campgrounds

    Retrieve campground information including availability, amenities, and reservation details.

  • List Visitor Centers

    Retrieve visitor center details including hours, directions, and contact information.

  • List Parking Lots

    Retrieve parking lot information for national park sites.

  • List Events

    Search for events happening at national parks by date, type, and location.

  • List Audio

    Access audio file metadata from national parks.

  • List Galleries

    Retrieve photo galleries from national parks.

  • List Gallery Assets

    Retrieve individual photos and assets from park galleries.

  • List Videos

    Access video metadata from national parks.

  • List Topics

    Retrieve topic categories used to classify national park content.

  • List Parks By Topic

    Find national parks associated with specific topics.

  • List Fees And Passes

    Retrieve entrance fee and pass information for national parks.

  • List Passport Stamp Locations

    Find passport stamp locations within national parks.

  • List Tours

    Retrieve guided tour information for national parks.

  • List Road Events

    Retrieve road incidents, closures, and work zone information for national parks.

  • List Webcams

    Access webcam streams and metadata from national parks.

Set Up Your National Park Service MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to National Park Service in under 10 lines of code.

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

National Park Service MCP Server FAQ

Does StackOne have a National Park Service MCP server?
Yes. StackOne offers a hosted National Park Service MCP server with 29 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
National Park Service MCP server vs direct API integration — what's the difference?
A National Park Service MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling National Park Service. A National Park Service MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling National Park Service at runtime. StackOne provides both.
How does National Park Service authentication work for AI agents?
National Park Service authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own National Park Service account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are National Park Service MCP tools vulnerable to prompt injection?
Yes — National Park Service MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a National Park Service agent and how do I avoid it?
Context bloat happens when National Park Service tool schemas and API responses eat your National Park Service agent's memory, preventing it from reasoning effectively. A single National Park Service query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my National Park Service agent can access?
Yes — you can limit which actions your National Park Service agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my National Park Service MCP server?
Yes — you can create custom agent actions for your National Park Service MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research National Park Service's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a National Park Service MCP server?
Skip a National Park Service MCP server if your integration is purely software-to-software — direct National Park Service API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call National Park Service actions at runtime.
What AI frameworks and AI clients does the StackOne National Park Service MCP server support?
The StackOne National Park Service MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.