eo-mcp

Overview Schema Source Related Servers Discussions Admin

run_pipeline

Execute multi-step Earth Observation processing pipelines from satellite data, using pre-built recipes or custom JSON specs for hazard, flood, burn severity, and exposure analysis.

Instructions

Execute a declarative multi-step Earth Observation processing pipeline or pre-built recipe. Empowers users and AI agents to compose custom multi-hazard workflows without self-hosted infrastructure.

Pre-built Recipes:

'compound_wildfire_runoff_risk': Wildfire burn severity (dNBR) + DEM slope gradient -> Debris flow risk
'coastal_storm_surge_infrastructure_exposure': Copernicus DEM + SLR + surge -> OSM transport & hospital exposure
'agricultural_drought_thermal_stress': Sentinel-2 NDVI + Land Surface Temp + Surface water shrinkage
'maritime_environmental_patrol': Sentinel-1 SAR CFAR + Live Baltic AIS + Low-backscatter oil slick delineation

Or pass a custom declarative JSON specification defining steps:

'fetch_raster': Copernicus DEM or Sentinel-2 / Landsat windowed COG
'spectral_index': NDVI, NDWI, MNDWI, NBR
'terrain_analysis': Slope gradient, aspect, elevation stats
'inundation_model': 8-connected bathtub flood simulation
'wildfire_activity': NASA FIRMS active hotspots and perimeters
'burn_severity': Multi-temporal dNBR calculation
'maritime_sar_ais': SAR CFAR detection and AIS correlation
'exposure_overlay': Intersect hazard zone with OpenStreetMap roads and critical facilities
'compound_risk_synthesis': Weighted multi-hazard score and EU Directive alignment

Args: spec: Pre-built recipe name (e.g. 'compound_wildfire_runoff_risk') or JSON string containing pipeline definition. location: Optional location name ('Valencia, Spain') or bbox 'min_lon,min_lat,max_lon,max_lat'. format: Output format: 'summary' (JSON report with ASCII map), 'geojson' (RFC 7946), or 'csv'. parameters: Optional JSON string of parameter overrides (e.g. '{"water_level_rise_m": 1.8, "storm_surge_m": 0.5}').

Returns: Formatted summary JSON, GeoJSON FeatureCollection, or CSV string.

Input Schema

TableJSON Schema

Name	Required	Default
`spec`	Yes
`format`	No	summary
`location`	No
`parameters`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 20, 2026

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It explains what happens (pipeline execution, returns a formatted summary, GeoJSON, or CSV) and notes there is no self-hosted infrastructure. However, it does not disclose side effects, compute/quota implications, or failure behavior, which would be useful for an execution tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but the length is justified by a complex tool: purpose, recipes, step vocabulary, args, and returns are clearly separated. A short opening sentence front-loads the core purpose, and the enumerated lists are scannable; some marketing phrasing like 'Empowers users and AI agents' adds little.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 0% schema coverage and no annotations, the description covers the essentials: valid recipe names, available pipeline steps, parameter formats, and return types. It does not specify detailed schemas for custom JSON steps or error/edge-case behavior, but the provided output schema and sibling tools reduce that gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the Args section fully compensates: spec is explained with recipe names and JSON-structure options, location gives both a name and bbox format, format enumerates the three output options, and parameters provides a concrete JSON override example. This exceeds what the bare schema offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence uses a specific verb-resource combination: 'Execute a declarative multi-step Earth Observation processing pipeline or pre-built recipe.' It clearly separates the tool from single-step EO tools and from discovery siblings like list_pipeline_recipes by framing it as execution of a full pipeline.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides strong contextual guidance: it lists four ready-made recipes and explains that a custom declarative JSON can be supplied instead. It does not explicitly name alternatives or say when not to use this tool, but the recipe/step lists make the intended use obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.