Rec-MCP
Uses Google Maps Geocoding API to convert city names to coordinates for location-based campground searches.
The code was generated using JetBrains AI Pro in PyCharm.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Rec-MCPfind campgrounds near Yosemite National Park"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Rec-MCP: Recreation & Campground Search
A Model Context Protocol (MCP) server that provides tools for finding camping facilities and recreational areas using Recreation.gov's Recreation Information Database (RIDB) API and Google Maps Geocoding API.
Features
🏕️ Find Camping Facilities: Search for campgrounds and recreational facilities near any location
🌍 Geocoding Support: Convert city names to coordinates using Google Maps API
🔍 Flexible Search: Customize search radius, result limits, and activity types. Change your prompts to locate reservable vs. first-come, first-serve campgrounds, etc.
📊 Rich Data: Get detailed facility information including contact details, amenities, and image URLs
🛠️ MCP Integration: Works seamlessly with MCP clients
Prerequisites
Python 3.12 or higher
API keys for:
Setup
Clone the repository
Install dependencies
uv add requests python-dotenv mcp
Create a
.envfile in the project root:env RIDB_API_KEY=your_recreation_gov_api_key_here
GOOGLE_GEOCODE_KEY=your_google_maps_api_key_here
Run the server
uv --directory /your_file_path/rec_mcp/ run ridb_mcp_server.py
Testing the MCP Server
Use the MCP Inspector to ensure the MCP Server is working before integrating it into any clients.
Install MCP inspector globally
npm install -g @modelcontextprotocol/inspector
Run the inspector
mcp-inspector uv run python ridb_mcp_server.py
Integrating the MCP Server with Clients
The MCP Server can be integrated into clients such as Claude Desktop and VSCode.
For Claude Desktop, add the server to the claude_desktop_config.json file.
Credits
JetBrains AI Pro generated 90 % of the code written for this project in PyCharm.
Available Tools
1 toolfind_campgroundsC
Find camping facilities near a specified location.
Searches for camping facilities within a customizable radius of a city using the Recreation Information Database (RIDB) API. First geocodes the city to get coordinates, then searches for campgrounds and camping facilities in the surrounding area.
Returns a JSON string containing facility information including any available image URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| location_name | Yes | ||
| radius | No | ||
| limit | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the two-step process (geocoding then searching) and the JSON return format with image URLs, but doesn't cover important aspects like rate limits, authentication requirements, error handling, or whether this is a read-only operation. For a tool that performs external API calls, this represents significant gaps in behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured and reasonably concise. It starts with a clear purpose statement, then explains the two-step process, and ends with information about the return format. Each sentence adds value, though the mention of 'JSON string' could be slightly more precise. The description avoids unnecessary repetition and is appropriately sized for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (3 parameters, external API calls, no output schema), the description provides a basic but incomplete picture. It covers the core functionality and return format but lacks important context about error conditions, rate limits, authentication, and parameter details. Without annotations or output schema, the description should do more to compensate, but only partially succeeds.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate but only partially succeeds. It mentions 'customizable radius' and 'city' for location, which helps interpret the parameters, but doesn't explain the units for radius (miles/kilometers), the purpose of the limit parameter, or provide examples of valid location_name formats. The description adds some value but doesn't fully compensate for the complete lack of schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Find camping facilities near a specified location' using the RIDB API. It specifies the verb 'find' and resource 'camping facilities', and mentions geocoding and searching processes. However, with no sibling tools, it cannot demonstrate differentiation from alternatives, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It explains what the tool does but offers no context about when it's appropriate, what prerequisites might exist, or when other approaches might be better. With no sibling tools mentioned, this gap is particularly notable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
find_campgrounds
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'find_campgrounds' has a clear, distinct purpose focused on locating camping facilities near a specified location, leaving no room for confusion or misselection.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'find_campgrounds' follows a clear verb_noun pattern (find + campgrounds), which would be consistent if more tools were added, but as a standalone, it sets a good precedent without any deviations or mixed conventions.
A single tool is too few for a server named 'Rec-MCP', which suggests a broader recreation domain. While the tool is well-defined for finding campgrounds, the server lacks coverage for other recreation activities (e.g., hiking trails, parks, events), making it feel thin and incomplete for its apparent scope, leading to potential agent failures in broader tasks.
The tool surface is severely incomplete for a recreation domain. It only provides a 'find' operation for campgrounds, with no CRUD/lifecycle coverage (e.g., no create, update, delete, or get details for campgrounds or other recreation resources). This creates significant gaps that will hinder agents from performing comprehensive recreation-related tasks.
Maintenance
Related MCP Connectors
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
MCP server for US nursing facility search and ownership lookup (NursingHomeDatabase).
- earthOAuthcom.mireye
MCP server for Mireye Earth — federal-source-cited geospatial data for any MCP-aware agent.
An MCP server that provides congressional transcripts
Related MCP Servers
- AlicenseBqualityAmaintenanceA Model Context Protocol server that provides Google Maps API integration, allowing users to search locations, get place details, geocode addresses, calculate distances, obtain directions, and retrieve elevation data through LLM processing capabilities.73,246 npm459MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) based search API server that provides standardized access to Google Maps, Google Flights, Google Hotels and other services. This server enables AI assistants to access various search services through a unified interface.74MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables web search with category support, website content scraping with citation metadata, and timezone-aware date/time tools.55MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server providing web search capabilities using Google Custom Search API and webpage content extraction functionality.2MIT