Provides access to NASA's public APIs including Astronomy Picture of the Day (APOD), Mars rover photos, Near-Earth Objects tracking, DONKI space weather events, and EPIC Earth imagery from the DSCOVR satellite.
Click on "Install 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., "@MCP TypeScript NASA Server show me today's astronomy picture of the day"
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.
A TypeScript-based MCP (Model Context Protocol) server that provides seamless integration with NASA's public APIs, enabling AI assistants to access space and astronomy data including APOD, Mars rover photos, Near-Earth Objects, space weather, and Earth imagery.
š 5 NASA API Tools: APOD, Mars Rovers, NEO Feed, DONKI Space Weather, EPIC Earth Imagery
š Resources Support: Access NASA data via URI-based resources (static & dynamic)
š¬ Prompts Templates: Pre-built prompts for education and analysis
š¦ NPX Ready: Run instantly with npx mcp-ts-stdio-nasa
š§ Type-Safe: Full TypeScript implementation with Zod validation
šÆ MCP Compliant: Full Model Context Protocol specification support
ā” Easy Setup: Works with Claude Desktop and other MCP clients
š API Key Support: Use your own NASA API key or the demo key
Related MCP server: NASA MCP Server
npx mcp-ts-stdio-nasaThis command downloads and runs the latest version directly from npm.
npm install -g mcp-ts-stdio-nasa
mcp-ts-stdio-nasanpm install mcp-ts-stdio-nasaAdd this configuration to your Claude Desktop config file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"nasa": {
"command": "npx",
"args": ["mcp-ts-stdio-nasa"],
"env": {
"NASA_API_KEY": "your_api_key_here"
}
}
}
}Create a .env file in your project root:
# NASA API Configuration
NASA_API_KEY=your_api_key_here # Get from https://api.nasa.gov/
# Use "DEMO_KEY" for testing with rate limits
# Optional
DEBUG=false # Enable debug loggingnasa_apod - Astronomy Picture of the DayGet NASA's daily featured astronomy image with detailed explanation.
Parameters:
date (optional): Date in YYYY-MM-DD format
Example Query:
"Show me NASA's astronomy picture from January 1, 2024"nasa_mars_rover_photos - Mars Rover PhotographyFetch photos from Mars rovers including Curiosity, Opportunity, Spirit, and Perseverance.
Parameters:
rover: Rover name (curiosity, opportunity, spirit, perseverance)
sol (optional): Martian day
earth_date (optional): Earth date in YYYY-MM-DD
camera (optional): Camera type (FHAZ, RHAZ, NAVCAM, etc.)
limit: Maximum photos to return (1-25)
Example Query:
"Get recent photos from Perseverance rover's navigation camera"nasa_neo_feed - Near Earth ObjectsTrack asteroids and comets passing near Earth.
Parameters:
start_date (optional): Start date in YYYY-MM-DD
end_date (optional): End date in YYYY-MM-DD
Example Query:
"Show me potentially hazardous asteroids passing Earth this week"nasa_donki_space_weather - Space Weather EventsMonitor solar flares, coronal mass ejections, and other space weather phenomena.
Parameters:
event_type: Event type (FLR, SEP, CME, IPS, MPC, GST, RBE)
start_date (optional): Start date
end_date (optional): End date
Event Types:
FLR: Solar Flare
SEP: Solar Energetic Particle
CME: Coronal Mass Ejection
IPS: Interplanetary Shock
MPC: Magnetopause Crossing
GST: Geomagnetic Storm
RBE: Radiation Belt Enhancement
Example Query:
"Check for solar flares in the last week"nasa_epic_earth_imagery - Earth Polychromatic ImagingGet full-disc Earth images from the DSCOVR satellite.
Parameters:
image_type: natural or enhanced
date (optional): Date in YYYY-MM-DD
limit: Maximum images (1-20)
Example Query:
"Show me recent full Earth images from space"Resources provide direct access to NASA data via URIs:
nasa://config - NASA API configuration and status
nasa://missions/current - List of current NASA missions
nasa://neo/today - Today's Near-Earth Objects
nasa://apod/{date} - APOD for specific date (e.g., nasa://apod/2024-01-15)
nasa://rover/{rover}/latest - Latest photos from Mars rovers
Example Usage:
"Read the resource nasa://apod/2024-12-25"
"Show me nasa://rover/perseverance/latest"Pre-configured prompts for common NASA data queries:
explain-apod - Educational APOD ExplanationParameters:
date (optional): YYYY-MM-DD format
audience (optional): child, student, or expert
Example:
"Use the explain-apod prompt for today with audience set to child"space-weather-report - Space Weather AnalysisParameters:
days (optional): 1-7 days to analyze
focus (optional): solar-flares, cme, geomagnetic, or all
Example:
"Generate a space-weather-report for the last 3 days focusing on solar flares"asteroid-analysis - NEO Risk AssessmentParameters:
timeframe (optional): today, week, or month
hazardous_only (optional): true/false
Example:
"Run asteroid-analysis for this week with hazardous_only true"ā Published and Working - The package has been successfully published to npm and tested with Claude Desktop.
Latest Version: 0.2.0
npm Package: mcp-ts-stdio-nasa
Installation: Works via npx, global install, or as a dependency
# Clone the repository
git clone https://github.com/jezweb/mcp-ts-stdio-nasa.git
cd mcp-ts-stdio-nasa
# Install dependencies
npm install
# Build the project
npm run build
# Run in development mode
npm run devnpm run build - Build TypeScript to JavaScript
npm run clean - Clean build artifacts
npm run dev - Watch mode for development
npm run lint - Run ESLint
npm run format - Format with Prettier
npm run mcp:inspect - Test with MCP Inspector
npm run build
npm run mcp:inspectThis opens the MCP Inspector for interactive testing of all tools.
mcp-ts-stdio-nasa/
āāā src/
ā āāā index.ts # Main server entry point
ā āāā tools/ # NASA API tool implementations
ā ā āāā apod.tool.ts
ā ā āāā mars-rover.tool.ts
ā ā āāā neo.tool.ts
ā ā āāā donki.tool.ts
ā ā āāā epic.tool.ts
ā āāā services/ # NASA API service layer
ā ā āāā nasa.service.ts
ā āāā types/ # TypeScript type definitions
ā ā āāā nasa.ts
ā āāā utils/ # Utility functions
ā āāā config.ts
ā āāā logger.ts
āāā dist/ # Compiled JavaScript
āāā docs/ # Documentation
āāā package.json
āāā tsconfig.jsonThis server uses NASA's public APIs. You can:
Use DEMO_KEY for testing (limited rate)
Get a free API key at https://api.nasa.gov/
Most endpoints allow 1000 requests/hour with an API key
Contributions are welcome! Please feel free to submit a Pull Request.
Fork the repository
Create your feature branch (git checkout -b feature/AmazingFeature)
Commit your changes (git commit -m 'Add some AmazingFeature')
Push to the branch (git push origin feature/AmazingFeature)
Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
NASA for providing public APIs
Anthropic for the MCP specification
Model Context Protocol community
Author: Jez (Jeremy Dawes)
Email: jeremy@jezweb.net
Website: www.jezweb.com.au
Made with ā¤ļø for the space and AI communities
Get NASA Astronomy Picture of the Day with detailed explanation
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Date in YYYY-MM-DD format. Defaults to today. |
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 states what the tool does but lacks critical behavioral details such as whether it requires authentication, has rate limits, returns structured data or raw images, or handles errors. This is inadequate for a tool with no annotation coverage.
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 a single, efficient sentence that front-loads the core purpose without unnecessary words. Every part of the sentence contributes directly to understanding the tool's function, making it optimally concise and well-structured.
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 lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., image URL, metadata, explanation text), error conditions, or dependencies. For a tool with no structured behavioral data, this leaves significant gaps in understanding how to use it effectively.
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?
The input schema has 100% description coverage, with the single parameter 'date' fully documented in the schema. The description adds no additional parameter information beyond implying the tool fetches data for a specific day, which is already covered by the schema. This meets the baseline for high schema coverage.
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 action ('Get') and resource ('NASA Astronomy Picture of the Day with detailed explanation'), making the tool's purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'nasa_epic_earth_imagery' or 'nasa_mars_rover_photos', which also retrieve NASA imagery but for different subjects.
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 doesn't mention sibling tools or contexts where other NASA tools might be more appropriate, such as using 'nasa_donki_space_weather' for space weather data instead of daily astronomy images.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get space weather events from NASA DONKI (Database Of Notifications, Knowledge, Information)
| Name | Required | Description | Default |
|---|---|---|---|
| event_type | No | Type of space weather event: FLR (Solar Flare), SEP (Solar Energetic Particle), CME (Coronal Mass Ejection), IPS (Interplanetary Shock), MPC (Magnetopause Crossing), GST (Geomagnetic Storm), RBE (Radiation Belt Enhancement) | FLR |
| start_date | No | Start date in YYYY-MM-DD format | |
| end_date | No | End date in YYYY-MM-DD format |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'Get[s] space weather events', implying a read-only operation, but doesn't clarify aspects like authentication requirements, rate limits, response format, or error handling. For a data retrieval tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves in practice.
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 a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized for a simple data retrieval tool and front-loads the key information ('Get space weather events'). Every part of the sentence contributes value by specifying the what and where.
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, no output schema, no annotations), the description is minimally adequate. It explains what the tool does but lacks details about behavioral traits, usage context, and output format. Without annotations or output schema, users must rely on the description alone, which doesn't fully address these gaps despite the clear parameter documentation in the schema.
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?
The input schema has 100% description coverage, with clear documentation for all three parameters (event_type with enum details, start_date, end_date). The description doesn't add any parameter-specific information beyond what's in the schema. According to the rules, when schema_description_coverage is high (>80%), the baseline score is 3 even with no param info in the description.
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: 'Get space weather events from NASA DONKI (Database Of Notifications, Knowledge, Information)'. It specifies the verb ('Get') and resource ('space weather events'), and provides context about the source (NASA DONKI). However, it doesn't explicitly distinguish this tool from its siblings (nasa_apod, nasa_epic_earth_imagery, etc.), which all access NASA data but for different purposes.
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 doesn't mention the sibling tools or any specific scenarios where this tool is preferred (e.g., for space weather analysis vs. general NASA data). Without such context, users must infer usage based on the tool name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get full disc imagery of Earth from DSCOVR's Earth Polychromatic Imaging Camera
| Name | Required | Description | Default |
|---|---|---|---|
| image_type | No | Type of image: natural color or enhanced | natural |
| date | No | Date in YYYY-MM-DD format. Defaults to most recent available. | |
| limit | No | Maximum number of images to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions 'Get' imagery but does not disclose behavioral traits such as whether this is a read-only operation, if it requires authentication, rate limits, or what the return format looks like (e.g., image URLs, metadata). For a tool with no annotations, this is a significant gap in 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 a single, efficient sentence that front-loads the core purpose ('Get full disc imagery of Earth') without unnecessary details. Every word earns its place, making it highly concise and well-structured.
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 no annotations and no output schema, the description is incomplete. It does not explain what is returned (e.g., image data, links, metadata), error conditions, or other behavioral aspects needed for effective use. For a tool with 3 parameters and no structured output information, the description should provide more context.
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?
Schema description coverage is 100%, so the schema already documents all parameters (image_type, date, limit) with descriptions and defaults. The description does not add any meaning beyond what the schema provides, such as explaining the significance of 'natural' vs 'enhanced' imagery or date constraints. Baseline 3 is appropriate when the schema does the heavy lifting.
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 action ('Get'), the resource ('full disc imagery of Earth'), and the source ('from DSCOVR's Earth Polychromatic Imaging Camera'). It specifically distinguishes this tool from sibling tools like 'nasa_apod' or 'nasa_mars_rover_photos' by focusing on Earth imagery from a specific satellite instrument.
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 implies usage for Earth imagery, but does not explicitly state when to use this tool versus alternatives like 'nasa_apod' (astronomy) or 'nasa_mars_rover_photos' (Mars). It provides context (Earth imagery from EPIC) but lacks explicit guidance on exclusions or comparisons to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get photos from Mars rovers (Curiosity, Opportunity, Spirit, Perseverance)
| Name | Required | Description | Default |
|---|---|---|---|
| rover | No | Mars rover name | perseverance |
| sol | No | Martian sol (day) to get photos from | |
| earth_date | No | Earth date in YYYY-MM-DD format | |
| camera | No | Camera abbreviation (e.g., FHAZ, RHAZ, NAVCAM) | |
| limit | No | Maximum number of photos to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure but offers minimal information. It doesn't mention whether this is a read-only operation, what authentication might be required, rate limits, error conditions, or what format the photos are returned in. The description only states what the tool does at a high level without behavioral details.
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 extremely concise - a single sentence that efficiently communicates the core functionality. It's front-loaded with the main action and resource, with no wasted words or unnecessary elaboration. Every word earns its place in this minimal description.
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?
For a tool with 5 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what the tool returns (photo metadata, URLs, image data), how results are structured, or important behavioral aspects like whether both 'sol' and 'earth_date' can be used together. The high parameter count and lack of structured metadata require more descriptive context than provided.
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?
The description adds no parameter-specific information beyond what's already in the schema, which has 100% coverage with clear descriptions for all 5 parameters. The baseline score of 3 reflects that the schema adequately documents parameters, so the description doesn't need to compensate, but it also adds no additional semantic context about how parameters interact or typical usage patterns.
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 action ('Get photos') and resource ('from Mars rovers'), specifying which rovers are supported. It distinguishes this tool from its NASA API siblings by focusing on Mars rover photos rather than astronomy pictures, space weather, Earth imagery, or asteroid data. However, it doesn't explicitly contrast with those siblings in the description text itself.
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, nor any context about prerequisites or constraints. It doesn't mention that users must choose between 'sol' and 'earth_date' parameters or explain the relationship between this tool and other NASA tools in the server.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get Near Earth Objects (asteroids) passing near Earth within a date range
| Name | Required | Description | Default |
|---|---|---|---|
| start_date | No | Start date in YYYY-MM-DD format. Defaults to today. | |
| end_date | No | End date in YYYY-MM-DD format. Defaults to 7 days from start date. |
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 states what the tool does but lacks critical behavioral details: it doesn't mention rate limits, authentication requirements, data freshness, error conditions, or what the return format looks like (especially important since there's no output schema).
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 a single, efficient sentence that directly states the tool's purpose with zero wasted words. It's appropriately sized for a simple data retrieval tool and front-loads the essential information.
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 absence of annotations and output schema, the description is incomplete. It doesn't explain what data is returned (e.g., asteroid names, sizes, distances), how results are structured, or any behavioral constraints. For a tool with no structured metadata, the description should provide more context about the operation.
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?
The schema description coverage is 100%, with both parameters clearly documented in the input schema. The description adds no additional parameter semantics beyond what's already in the schema (e.g., it doesn't explain date range constraints beyond 'within a date range'). Baseline 3 is appropriate when the schema does the heavy lifting.
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 verb 'Get' and the resource 'Near Earth Objects (asteroids) passing near Earth within a date range'. It specifies the exact scope (asteroids passing near Earth) and distinguishes it from sibling tools like NASA APOD or Mars rover photos, which serve completely different purposes.
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 implies usage for retrieving asteroid data within a date range, but provides no explicit guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, exclusions, or compare it to other asteroid-related tools (though none are listed among siblings).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose targeting different NASA data sources: APOD, space weather, Earth imagery, Mars rover photos, and near-Earth objects. There is no overlap in functionality, making tool selection straightforward for an agent.
All tools follow a consistent 'nasa_' prefix and descriptive snake_case naming pattern (e.g., nasa_apod, nasa_donki_space_weather). This predictability aids in understanding and usage across the toolset.
With 5 tools, the server is well-scoped for providing access to various NASA APIs. Each tool serves a distinct data source, making the count appropriate and manageable for the domain without being overwhelming or insufficient.
The toolset covers a broad range of NASA data sources, but there are minor gaps such as missing tools for other NASA APIs (e.g., NASA Image and Video Library, planetary data). However, the included tools provide solid coverage for common use cases without major dead ends.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
NASA MCP ā wraps NASA Open APIs (api.nasa.gov)
Live space data for AI agents - rocket launches, ISS passes, launch news. Free, no auth.
NASA data: near-Earth objects, space weather, and astronomy pictures
Turn any task into the right API calls: discover, evaluate, and integrate public APIs.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jezweb/mcp-ts-stdio-nasa'
If you have feedback or need assistance with the MCP directory API, please join our Discord server