Server providing Argo CD integration for MCP clients.
Nothing to run from here
GreenPick 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.
99/100
trust score
25
downloads a day
local
runs on your machine
611
downloads in 30d
What it does
Greener, cheaper cloud infra decisions — carbon + cost + latency tradeoffs, in-editor.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user greenpick-mcp '--' uvx greenpick
# 2 — ask your agent for something these tools do
# compare_regions_tri_axis, greener_alternative_to, estimate_workload_carbon and 16 more
GreenPick costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
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 GreenPick 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. Its scan result is on the Security tab — 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. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user greenpick-mcp '--' uvx greenpickReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take GREENPICK_CARBON_SOURCE (Carbon data source: 'auto' (US->EIA, EU->ENTSO-E, Canada->Hydro-Québec/IESO live), 'mock' (offline: typical monthly values from a year of real data), 'eia', 'entsoe', or 'electricitymaps'. Defaults to offline.), EIA_API_KEY (Free US EIA-930 grid data API key (optional; enables live US carbon).), ENTSOE_TOKEN (Free EU ENTSO-E grid data token (optional; enables live EU carbon + day-ahead forecast).), ELECTRICITYMAPS_TOKEN (Electricity Maps API token (optional; used when GREENPICK_CARBON_SOURCE=electricitymaps).), GREENPICK_CACHE_TTL_SECONDS (Cache lifetime for fetched grid data, in seconds.), GREENPICK_LOG_LEVEL (Logging level (DEBUG, INFO, WARNING, ERROR).) if you want to set them.
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
19 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Rank candidate cloud regions by carbon, with cost + latency tradeoffs, and recommend one.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_lat | number | yes | — |
| user_lon | number | yes | — |
| vcpu | number | yes | — |
| ram_gb | number | yes | — |
| est_monthly_egress_gb | number | no | — |
| providers | array | no | — |
| optimize_for | string | no | — |
| max_added_latency_ms | number | no | — |
| baseline_region | string | no | — |
| regions | array | no | — |
You picked current_region — find the greenest region within +max_added_latency_ms, with the carbon/cost/latency delta vs. your current choice. The core 'nudge' tool. Pass regions to limit the search to options you'd actually move to; your current region is always included. Before accepting a…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| current_region | string | yes | — |
| user_lat | number | yes | — |
| user_lon | number | yes | — |
| vcpu | number | yes | — |
| ram_gb | number | yes | — |
| est_monthly_egress_gb | number | no | — |
| max_added_latency_ms | number | no | — |
| providers | array | no | — |
| regions | array | no | — |
Rough kgCO2/month for a workload running in a region. An ESTIMATE (documented power model x grid intensity), not a measurement.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | yes | — |
| vcpu | number | yes | — |
| ram_gb | number | yes | — |
| hours_per_month | number | no | — |
Current grid carbon intensity for a region, with source, timestamp, and data freshness.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | yes | — |
Carbon-aware scheduling: given a region, report its cleanest recent hours so you can time a DEFERRABLE job (nightly ETL, batch, backups, training) when the grid is greenest.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | yes | — |
| top_n | integer | no | — |
| window_hours | integer | no | — |
Suggest a greener SAME-SIZE instance family in the SAME region. The mechanism is performance-per-watt: a newer-generation or ARM (Graviton-class) family does the same work on less energy -> less CO2 at the region's grid intensity. Give your current family (e.g. 'm5', 'n2', 'Dv5') for a savings…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | yes | — |
| vcpu | number | yes | — |
| ram_gb | number | yes | — |
| current_family | string | no | — |
| hours_per_month | number | no | — |
Energy + CO2 of running an LLM INFERENCE workload (serving queries) — the inference-side sibling of estimate_training_carbon. Give the model SIZE CLASS (small | mid | large | frontier_dense | moe, or a param alias like '8b' / '70b' / 'moe'), monthly request volume, and avg OUTPUT tokens per…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| size_class | string | yes | — |
| monthly_requests | number | yes | — |
| avg_output_tokens | integer | no | — |
| region | string | no | — |
| provider | string | no | — |
Right-sizing (the #1 FinOps win) with a carbon twin: if you're over-provisioned, a smaller size cuts BOTH cost and carbon — same work, less waste, no tradeoff. Give the provisioned size (vcpu, ram_gb) and observed CPU utilisation (0..1, e.g. 0.2 for 20%); optionally RAM utilisation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | yes | — |
| vcpu | number | yes | — |
| ram_gb | number | yes | — |
| cpu_utilization | number | yes | — |
| ram_utilization | number | no | — |
| hours_per_month | number | no | — |
Emit paste-in instrumentation so the user's OWN app can report an ESTIMATED carbon metric over time. Consider offering this when the user is building an app/service and wants ongoing visibility into its footprint. GreenPick returns a code snippet (Python in v1) + the power-model coefficients + a…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| language | string | no | — |
| region | string | no | — |
| provider | string | no | — |
| vcpu | number | no | — |
| ram_gb | number | no | — |
Design-time advice for a USER-FACING PLATFORM: should you serve users from ONE region or SEVERAL? Consider calling this when the user is building a web app / dashboard / API that serves end users. Give hubs as where your users are — a list like…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hubs | array | yes | — |
| vcpu | number | no | — |
| ram_gb | number | no | — |
| providers | array | no | — |
Will running compute away from where your DATA lives backfire via egress? Give where compute runs, where the data lives (provider+region), and monthly GB crossing between them.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| compute_provider | string | yes | — |
| compute_region | string | yes | — |
| data_provider | string | yes | — |
| data_region | string | yes | — |
| monthly_cross_boundary_gb | number | yes | — |
| carbon_saving_kg_co2_from_move | number | no | — |
Forward-looking scheduling: which UPCOMING hours will be cleanest? Uses the EU day-ahead wind+solar forecast (ENTSO-E) to rank the greenest hours over the next hours_ahead. This is a RELATIVE ranking (more forecast renewables = cleaner), not an absolute gCO2/kWh forecast.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | yes | — |
| hours_ahead | integer | no | — |
| top_n | integer | no | — |
For a RECURRING job (e.g. a nightly batch you run every day), find the region's cleanest time of day — each hour-of-day averaged across the recent days of data. Returns the cleanest/ dirtiest hour-of-day and the % gap. Honest scope: a DAILY pattern over the few days of free data, NOT a 7-day…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | — |
| region | string | yes | — |
Carbon of a GPU training run, with greener WHERE (region) and WHEN (hours) guidance.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| gpu | string | yes | — |
| gpu_count | integer | yes | — |
| gpu_hours | number | yes | — |
| region | string | no | — |
| provider | string | no | — |
| utilization | number | no | — |
| top_n_regions | integer | no | — |
GreenPick's assumptions and what it explicitly does NOT claim. Read this before trusting a number.
Takes no parameters.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install GreenPick or to call it, 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: —
ATrust score 99 / 100
Release 0.6.3 · scanned 8 Nov 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 score100
Client score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest2a33cddd14e517598800b54bb8cb06a1213ece74cda456af1cd6ca6cc3257841
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (19 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| compare_regions_tri_axis | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| greener_alternative_to | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| estimate_workload_carbon | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| region_carbon_now | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cleanest_hours_to_run | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| greener_instance_family | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| estimate_inference_carbon | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| rightsizing_check | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| offhours_check | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| greenest_regions_on_average | no tags | |
| carbon_metric_scaffold | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| serving_pattern_advice | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| data_locality_egress_check | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| migration_payoff | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| region_move_justification | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| carbon_forecast | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cleanest_time_of_day | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| estimate_training_carbon | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| explain_methodology_and_limits | no tags |
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 digest2a33cddd14e51759
Scanned2026-11-08
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.6.3. Pin a release below and the command asks for exactly that one.
0.6.3
7 Nov 2026
latestNo release note was published with this version.
0.6.2
5 Nov 2026
No release note was published with this version.
0.6.1
3 Nov 2026
No release note was published with this version.
0.5.2
3 Nov 2026
No release note was published with this version.
0.4.2
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish GreenPick can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.