Experimental package — This module provides a set of MCP tools to retrieve information from GitHub
Free
Nothing to run from here
Earth Agent is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
MCP Server for Earth Agent - exposes Google Earth Engine tools to AI assistants like Claude Code, Cursor, and Zed
Quickstart
# 1 — run it from where its publisher ships it
npx -y earth-agent-mcp
# 2 — ask your agent something
> MCP Server for Earth Agent - exposes Google Earth Engine tools to AI assistants like Claude Code, Cursor, and Zed
Earth Agent is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
WYAll 1 server
wybert1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Earth Agent as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add earth-agent-mcp -- npx -y earth-agent-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
17 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Get current weather for a location. Returns temperature, conditions, humidity, wind speed, etc. Useful when the user asks about weather conditions for a study area.
Takes no parameters.
Example callreturns →
Get current date and time. Returns the current date and time, optionally in a specific timezone. Useful for timestamping operations or understanding when data was collected.
Takes no parameters.
Example callreturns →
Wait for a specified number of seconds. Use this when you need to wait for: - Code execution to complete - Map layers to render - Data to load Maximum wait time is 60 seconds.
Takes no parameters.
Example callreturns →
Read the current code from the Google Earth Engine Code Editor. Returns the full content of the code editor, which can be used to understand the current state before making edits.
Takes no parameters.
Example callreturns →
Edit code in the GEE editor using old_string/new_string replacement. This tool finds the exact old_string in the editor and replaces it with new_string. The old_string must match exactly (including whitespace and indentation). Use this for targeted edits to existing code.
Takes no parameters.
Example callreturns →
Overwrite the entire Google Earth Engine Code Editor with new code. This replaces ALL content in the editor. Use this when: - Starting fresh with new code - The existing code is not relevant - Major rewrites are needed WARNING: This will delete all existing code in the editor!
Takes no parameters.
Example callreturns →
Undo the last code edit in the Google Earth Engine editor. Use this to revert the most recent change if something went wrong.
Takes no parameters.
Example callreturns →
Execute the current code in the Google Earth Engine Code Editor. This clicks the
Takes no parameters.
Example callreturns →
Take a screenshot of the Google Earth Engine interface. Returns a screenshot image showing the current state of the GEE Code Editor, including the map, console, and any visualizations. Useful for: - Seeing map layer results - Checking chart visualizations - Debugging visual issues
Takes no parameters.
Example callreturns →
Get an accessibility snapshot of the Google Earth Engine page. Returns a YAML representation of the DOM accessibility tree, showing interactive elements with their reference IDs. Useful for: - Understanding page structure - Finding elements to click - Debugging UI interactions
Takes no parameters.
Example callreturns →
Read the output from the Google Earth Engine console. Returns the current console output, including: - Print statements from code execution - Error messages - Task status messages Use this after running code to check results.
Takes no parameters.
Example callreturns →
Get the current map position and bounds in Google Earth Engine. Returns: - Center coordinates (latitude, longitude) - Zoom level - Visible bounds
Takes no parameters.
Example callreturns →
Read the Inspector panel output in Google Earth Engine. Returns data from the Inspector panel, including: - Pixel values at clicked locations - Layer information - Band values for image layers
Takes no parameters.
Example callreturns →
Clear the Google Earth Engine map, inspector, and console. Resets the environment by: - Clearing map layers - Clearing inspector data - Clearing console output Use this to start fresh or clean up between operations.
Takes no parameters.
Example callreturns →
Search Google Earth Engine documentation and datasets. Search types: -
Takes no parameters.
Example callreturns →
Click an element in the GEE interface by its reference ID. Use gee_snapshot first to find element reference IDs, then use this tool to interact with buttons, links, and other clickable elements.
Takes no parameters.
Example callreturns →
Click at a specific screen position in the GEE interface. Useful for clicking on map locations or elements without reference IDs.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Earth Agent costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
BTrust score 87 / 100
Release 1.3.0 · scanned 25 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score94
Client score87
Findings1 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest55e9c9216d9339b5be4fa995425afaa48bf62bc8389b4b9726947c17098e4ea7
Score vectorthreat 94 → client 87
| Term | Level | What it prices | Points |
|---|---|---|---|
| −6.3 | |||
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest55e9c9216d9339b5
Scanned2026-08-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 1.3.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
1.3.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Earth Agent in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.