MCP/mcgibs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
9 Commits 1 Branch 2 Tags
Commit Graph

3 Commits

Author SHA1 Message Date
Ryan Malloy
0f3b2e392f Add MCP prompts, README, LICENSE, and PyPI metadata 
Five new prompts guide LLMs through multi-tool workflows:
satellite_snapshot, climate_monitor, layer_deep_dive,
multi_layer_story, polar_watch. README documents all 11 tools,
5 resources, and 7 prompts with example conversations.
MIT license, project URLs, and updated classifiers for PyPI.
 2026-02-18 19:36:08 -07:00
Ryan Malloy
db6ed2f550 Use FastMCP Image type, Context progress, and dynamic resources 
Replace hand-rolled base64 dicts with FastMCP's Image() helper in
get_imagery, compare_dates, get_imagery_composite, and get_legend.
FastMCP handles base64 encoding and MIME type automatically.

Add Context progress reporting to imagery tools so MCP clients can
display fetch status (resolving location, fetching imagery, etc).

Add dynamic resources:
  gibs://colormap/{layer_id} — colormap explanation text
  gibs://dates/{layer_id}    — date range + live DescribeDomains

Remove unused base64 import.
 2026-02-18 18:30:32 -07:00
Ryan Malloy
f7fad32a9e Implement mcgibs FastMCP server for NASA GIBS 
Complete implementation of all modules:
- constants.py: GIBS API endpoints, projections, TileMatrixSet defs
- models.py: Pydantic models for layers, colormaps, geocoding
- geo.py: Nominatim geocoding with rate limiting and caching
- capabilities.py: WMTS GetCapabilities XML parser with search
- colormaps.py: Colormap v1.3 parser with natural-language summaries
- client.py: Async GIBS HTTP client wrapping all API interactions
- server.py: FastMCP 3.0 tools, resources, and prompts

11 MCP tools, 3 resources, 2 prompts. 47 tests, all passing.
 2026-02-18 14:55:41 -07:00