Skip to main content
Glama
ShafHaider007

EO-MCP

by ShafHaider007
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

EO-MCP

EO-MCP is a Python Model Context Protocol (MCP) server for discovering and analysing Sentinel-2 Level-2A imagery. It gives AI agents a small, focused toolset for finding scenes, checking their suitability, computing spectral indices, and summarising an index inside a polygon.

The server reads only the required windows from cloud-optimized GeoTIFFs hosted by the Microsoft Planetary Computer. It does not download complete Sentinel-2 scenes.

Features

  • Search the live Sentinel-2 L2A STAC catalog by bounding box, date, and cloud cover.

  • Inspect scene-level cloud and nodata metadata before performing analysis.

  • Confirm that a scene footprint covers the requested area of interest.

  • Compute NDVI, NDWI, and NBR from remote raster windows.

  • Calculate polygon-clipped min, max, mean, and pixel count.

  • Return structured, agent-friendly results with processing metadata.

The intended workflow is:

stac_search → scene_quality → compute_index
                          └─→ quick_stats

Always call scene_quality before computing an index.

Related MCP server: Planetary Computer MCP Server

Tools

Tool

Purpose

Key inputs

stac_search

Find the clearest Sentinel-2 L2A scenes intersecting an area.

bbox, start_date, end_date, max_cloud_cover, limit

scene_quality

Check cloud cover, nodata, and scene-footprint coverage.

scene_id, bbox

compute_index

Compute summary statistics for NDVI, NDWI, or NBR over a rectangular area.

scene_id, bbox, index_name

quick_stats

Compute index statistics clipped to a WGS84 GeoJSON Polygon or MultiPolygon.

scene_id, polygon, index_name, all_touched

Bounding boxes use WGS84 coordinates in this order:

[west, south, east, north]

Dates use ISO YYYY-MM-DD format.

Supported indices

Index

Formula

Typical use

NDVI

(B08 - B04) / (B08 + B04)

Vegetation condition and greenness

NDWI

(B03 - B08) / (B03 + B08)

Surface-water detection

NBR

(B08 - B12) / (B08 + B12)

Burn severity and fire impact

Sentinel-2 digital numbers are converted to reflectance before the index is calculated. EO-MCP also accounts for the offset introduced with processing baseline 04.00 and later.

Requirements

  • Python 3.12 or newer

  • uv

  • Internet access to the Planetary Computer STAC API and Sentinel-2 COG assets

No Planetary Computer API key is required for the current public-data workflow.

Quick start

From the repository root:

uv sync --frozen
uv run python -c "import eo_mcp; print('eo_mcp import: ok')"
uv run fastmcp inspect src/eo_mcp/app.py

The inspect command should report the server name EO-MCP and four tools.

To start the STDIO server manually:

uv run fastmcp run src/eo_mcp/app.py

An STDIO server waits for an MCP client and usually produces no interactive prompt. Use an MCP client or fastmcp call to invoke its tools.

Test from the command line

Search for Sentinel-2 scenes:

uv run fastmcp call \
  --server-spec src/eo_mcp/app.py \
  --target stac_search \
  --input-json '{
    "bbox": [73.0, 33.65, 73.12, 33.75],
    "start_date": "2024-06-01",
    "end_date": "2024-08-31",
    "max_cloud_cover": 10,
    "limit": 1
  }' \
  --json

Check the selected scene:

uv run fastmcp call \
  --server-spec src/eo_mcp/app.py \
  --target scene_quality \
  --input-json '{
    "scene_id": "S2B_MSIL2A_20240603T054639_R048_T43SCT_20240603T090813",
    "bbox": [73.0, 33.65, 73.12, 33.75]
  }' \
  --json

Compute NDVI after the quality check passes:

uv run fastmcp call \
  --server-spec src/eo_mcp/app.py \
  --target compute_index \
  --input-json '{
    "scene_id": "S2B_MSIL2A_20240603T054639_R048_T43SCT_20240603T090813",
    "bbox": [73.0, 33.65, 73.02, 33.67],
    "index_name": "NDVI"
  }' \
  --json

For the installed FastMCP version, pass src/eo_mcp/app.py as the server specification without appending :mcp.

Connect to Codex or another MCP client

EO-MCP currently runs as a local STDIO server. Configure the client with an absolute project path so it can launch the server from any working directory.

{
  "mcpServers": {
    "eo-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--project",
        "/absolute/path/to/eo-mcp",
        "--frozen",
        "fastmcp",
        "run",
        "/absolute/path/to/eo-mcp/src/eo_mcp/app.py"
      ]
    }
  }
}

If the client cannot find uv, replace "uv" with the absolute path returned by:

command -v uv

With the Codex CLI, the equivalent registration command is:

codex mcp add eo-mcp -- \
  /absolute/path/to/uv run \
  --project /absolute/path/to/eo-mcp \
  --frozen fastmcp run \
  /absolute/path/to/eo-mcp/src/eo_mcp/app.py

Restart the client or open a new session after saving the configuration. In Codex, use /mcp to confirm that eo-mcp is connected.

Example agent request:

Find a low-cloud Sentinel-2 scene for Lahore during July 2026. Check the
scene's quality, then compute NDVI for a small area and report the mean.

GeoJSON polygon example

quick_stats accepts either a GeoJSON geometry or a GeoJSON Feature:

{
  "type": "Polygon",
  "coordinates": [
    [
      [73.002, 33.652],
      [73.018, 33.652],
      [73.018, 33.668],
      [73.002, 33.668],
      [73.002, 33.652]
    ]
  ]
}

Coordinates must be WGS84 longitude/latitude values. Polygon and MultiPolygon geometries are supported.

How index processing works

  1. EO-MCP retrieves the requested STAC item and signs its asset URLs.

  2. It transforms the WGS84 area into the source raster coordinate system.

  3. Rasterio reads only the intersecting COG window over HTTPS.

  4. Bands on a different grid are aligned to the reference band.

  5. Digital numbers are converted to reflectance and the selected index is calculated.

  6. The server returns statistics and processing metadata rather than the full raster array.

compute_index reports min, max, mean, median, standard deviation, 2nd and 98th percentiles, pixel counts, CRS, resolution, and the source window. quick_stats clips the index raster to the supplied polygon and reports min, max, mean, and count.

Quality rules and operational limits

A scene is marked usable when all of the following are true:

  • Scene-level cloud cover is at most 20%.

  • Scene-level nodata is at most 10%.

  • The scene footprint covers at least 99% of the requested area.

Important limitations:

  • Cloud and nodata percentages come from scene-level STAC metadata; they are not calculated specifically for the requested bounding box.

  • Index calculations do not apply a per-pixel cloud mask. Select a suitable scene with scene_quality first.

  • A rectangular index request is limited to 4,000,000 reference-grid pixels. Reduce the bounding box if this limit is exceeded.

  • compute_index summarises the full rectangular window. Use quick_stats when results must be clipped to an exact administrative, farm, water, or other polygon boundary.

  • Signed Planetary Computer asset URLs expire. Search again instead of storing them as permanent download links.

  • Large requests depend on remote-network speed and upstream service availability.

Project structure

eo-mcp/
├── pyproject.toml
├── src/
│   └── eo_mcp/
│       ├── __init__.py
│       ├── app.py       # FastMCP server and registered tools
│       ├── tools.py     # STAC, raster, index, and zonal-stat logic
│       └── utils.py     # Input validation helpers
└── README.md

Technology

Remote deployment

STDIO is intended for local clients. To share EO-MCP across machines, expose it using FastMCP's Streamable HTTP transport, add authentication, and deploy it on a Python or container hosting platform. Do not publish an unauthenticated analysis endpoint to the public internet.

See the FastMCP HTTP deployment guide for the supported remote-server patterns.

Available Tools

4 tools
compute_indexA

Compute NDVI, NDWI, or NBR after checking the scene with scene_quality.

ParametersJSON Schema
NameRequiredDescriptionDefault
bboxYes
scene_idYes
index_nameNoNDVI

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A3.5/5.0
Behavior2/5

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 only states the core function without revealing side effects, error handling, or safety properties. The behavior regarding scene quality failure is not addressed.

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?

One sentence efficiently conveys the purpose and a key prerequisite. No extraneous information, but slightly more detail on parameters could be included without harming conciseness.

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

Completeness3/5

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

Given the presence of an output schema, return values need not be described. The description mentions a prerequisite (scene_quality) and lists index options, but fails to explain bbox and scene_id, leaving the tool incomplete for a 3-parameter tool.

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

Parameters2/5

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

Schema coverage is 0%, but the description adds meaning only for index_name by listing possible indices (NDVI, NDWI, NBR). Bbox and scene_id remain unexplained, leaving significant gaps.

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 description clearly states the verb 'compute' and the specific resources 'NDVI, NDWI, or NBR', distinguishing it from siblings like scene_quality and stac_search.

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?

Explicitly advises checking the scene with scene_quality first, providing clear context for when to use this tool. However, no exclusions or alternatives are mentioned.

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

quick_statsC

Return zonal index statistics inside a WGS84 GeoJSON polygon.

ParametersJSON Schema
NameRequiredDescriptionDefault
polygonYes
scene_idYes
index_nameNoNDVI
all_touchedNo

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

C2.7/5.0
Behavior2/5

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

With no annotations, the description must fully disclose behavioral traits, but it only states the basic action. It does not mention performance implications, error handling, data limits, or side effects. For example, it is silent on whether the polygon must be simple, what happens if the scene_id is invalid, or if the tool modifies data.

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

Conciseness3/5

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

The description is a single concise sentence of 8 words, which is efficient but overly terse given the tool's complexity. It front-loads the core action, but could add essential parameter details without losing conciseness. It is acceptable but not optimally balanced.

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

Completeness2/5

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

For a tool with 4 parameters (2 required), a nested object, and an output schema, the description is too sparse. It does not explain the return structure, the role of the polygon and scene_id, the default index, or the 'all_touched' flag. Although an output schema exists, the description should provide enough context to understand the tool's scope and usage, which it fails to do.

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

Parameters1/5

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

The schema has 0% documentation coverage (no descriptions in the schema properties), so the description must compensate. However, it adds no meaning beyond the parameter names: it does not explain what 'polygon' (expected format), 'scene_id' (identifier meaning), 'index_name' (valid values beyond NDVI), or 'all_touched' (behavior) entail. The description fails to provide any parameter semantics.

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 description clearly states the tool returns zonal index statistics within a WGS84 GeoJSON polygon. The verb 'Return' and resource 'zonal index statistics' are specific, and the scope distinguishes it from siblings like 'scene_quality' (quality metrics) and 'compute_index' (index computation).

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, constraints, or when not to use it. The description only states what the tool does, leaving the agent to infer usage context.

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

scene_qualityB

Check scene cloud, nodata, and AOI coverage before index computation.

ParametersJSON Schema
NameRequiredDescriptionDefault
bboxYes
scene_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

B3.3/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden. It only mentions 'check' but does not disclose if the tool is read-only, what side effects occur, or what happens if checks fail (e.g., errors or warnings).

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 a single sentence of 8 words, with no redundant information. It is efficiently front-loaded with the purpose, though it could benefit from additional structure like bullet points or examples.

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

Completeness3/5

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

Given the existence of an output schema (not shown), the description does not need to detail return values. However, it lacks information on parameter semantics and behavioral details, making it minimally complete for a two-parameter tool.

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

Parameters2/5

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

Schema description coverage is 0%, so description must compensate. It mentions 'cloud, nodata, and AOI coverage' but does not explain how the two parameters ('scene_id' and 'bbox') relate to these concepts. No details on format or constraints are provided.

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 description clearly states the verb 'Check' and specifies the resources: 'scene cloud, nodata, and AOI coverage'. It also provides context ('before index computation'), which distinguishes it from sibling tools like 'compute_index' or 'stac_search'.

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

Usage Guidelines3/5

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

The description implies this tool is a prerequisite for index computation but does not explicitly state when to use it versus alternatives like 'quick_stats' or 'compute_index'. No exclusions or specific conditions are given.

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. Dates show when Glama detected each change.

  1. 4 tool updatesv0.1.0
    • First observedcompute_index
    • First observedquick_stats
    • First observedscene_quality
    • First observedstac_search
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: searching for scenes, checking scene quality, computing indices, and getting statistics. No overlap or ambiguity.

Naming Consistency4/5

All tool names use snake_case with a noun_noun or verb_noun pattern (e.g., stac_search, scene_quality). While not all are strictly verb_noun, they are consistent in format and readable.

Tool Count5/5

Four tools is appropriate for the domain of satellite imagery analysis, covering the essential workflow from search to statistics without unnecessary bloat.

Completeness4/5

The tool set covers the key steps: search, quality check, index computation, and statistics. A minor gap is the lack of scene metadata retrieval, but stac_search likely provides some metadata.

Maintenance

ActivitySlowing
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • MCP Data Server

    boettiger-lab
    A
    license
    Not graded
    quality
    A
    maintenance
    An MCP server that connects AI agents to cloud-native geospatial data via STAC metadata and DuckDB with H3 spatial indexing, enabling zero-configuration SQL queries on terabyte-scale datasets over S3.
    23
    BSD 3-Clause

  • geopera-mcp

    geo-pera
    A
    license
    C
    quality
    C
    maintenance
    MCP server for the Geopera geospatial data platform that enables AI agents to discover imagery, place and manage orders, and run analytics using the same API as other Geopera clients.
    100
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ShafHaider007/eo-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server