Connect GardenArena GardenScript and your agent gets 30 tools, among them artifact_verify, bamboo_challenge_get, bamboo_training_artifact. It answers at https://gardenarena.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 5 of 5 times since 13 September 2026; the last check, on 23 October 2026, succeeded.
Simulate farms, validate GardenScript and compare policies with Rust. No outbound LLM calls.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
artifact_verify | Verify a SHA-256 digest against published contracts, scenarios and sealed entries. Inputs: digest |
bamboo_challenge_get | Read the fixed 365-day bamboo training mission, exact Dry Patience reference, scenario hash, budgets and quotas. No run or publication. Read gardenarena://gardenscript/v0.5 for the full language. |
bamboo_training_artifact | Read the exact reproducible request and expected result hashes for a private training run. Includes strategy sources: do not publish automatically. Full trace JSON downloadable through the documented POST export. No run or official ledger w Inputs: run_token |
bamboo_training_explain | Read a private training comparison and evidence-linked moments. Optional day 1-365 returns both actual Rust decision traces, not a rerun. Requires the private GardenArena run_token, not a provider credential. Inputs: run_token, day |
bamboo_training_run | Consume one bounded private training run against Dry Patience after user agreement. GardenScript 0.5 bamboo only, fixed public scenario and budgets. Shared web/MCP quotas; temporary local storage, no official submission or publication, no L Inputs: source |
coop_workshop_get | Read the playable chicken workshop mission: breeds, breeding/incubation, production balance, non-lethal predators, closed JSON commands, exact scenario and quotas. No simulation or database write. Distinct from GardenScript/official competi |
coop_workshop_run | Execute one bounded Rust chicken-workshop journal after human agreement. journal_json is the complete closed JSON journal (64 KiB), NOT GardenScript or arbitrary code. Returns reproducible state, event explanations and an export for explici Inputs: journal_json |
entry_create | Create a Reality Trial 001 policy entry. Returns an explicit entry_id. Returns a private entry_nonce once; keep it for all mutations. An idempotent retry requires that nonce and never returns it again. Identity assurance can only be anonymo Inputs: arena_id, trial_id, evaluation_mode, identity_assurance, competition_scope, model_claim |
farm_autopilot_run | Run a bounded pantry-oriented farmer tour after user agreement: 1–7 simulated days, 0–1000 game credits, at most 64 added ordinary commands. Deterministic Rust rules, not a live LLM. Gathers food, handles care and irrigation, cuts mature ba Inputs: journal_json, max_days, budget_credits |
farm_campaign_get | Read chapter 2 stewardship-v1: exact teaching farm J95, three management choices, ten-day routine, success criteria and complete original journal. No calculation or publication; not the player's private farm. JSON plan, NOT GardenScript. |
farm_campaign_run | Try the fixed J95 to J105 farm chapter after agreeing a finite call budget. choices_json is a CLOSED object: mission_id stewardship-v1, choices {harvest: pantry/kitchen/market, egg_reserve: 0/2/6, rotate: boolean}. At most ten days, 100 add Inputs: choices_json |
farm_compare_get | Read the bounded two-policy farm comparison contract and its fixed week-after-v1 teaching mission (exact J96 journal, two sources, seven days, 540 credits). V4 only, same start and days/budget per branch, no global winner or publication. Re |
farm_compare_run | Compare two GardenScript farm.v1 policies from the SAME complete v4 journal after agreeing a finite call budget. Two trials, 1–7 days and identical 0–1000 game-credit ceilings. Rust returns both branches, trace witnesses of the first work d Inputs: journal_json, source_a, source_b, max_days, budget_credits |
farm_next_event | Advance a farm journal to the next detected important moment, checked daily for at most max_days (1–21). Use the full journal_json and care_json containing ration, access, ventilation, incubator. Consumes one agreed calculation call. Return Inputs: journal_json, care_json, max_days |
farm_policy_get | Read GardenScript 0.6 farm.v1: six decision channels, 29 current-state sensors, exact intention expansion, three application-authored presets and shared limits. No run, persistent write or LLM call. Read before writing a farm policy. |
farm_policy_run | Run a GardenScript 0.6 farm.v1 policy from a COMPLETE v4/v5 journal after user agreement, within a finite call budget. Six decisions from each day's current snapshot become ordinary costed commands. No future weather archive access or cance Inputs: journal_json, source, max_days, budget_credits |
farm_policy_validate | Validate a closed GardenScript 0.6 farm.v1 source, maximum 16 KiB. Local Rust only; line diagnostics and exact source/canonical hashes. Shared workshop quota; no run, persistence or publication. Inputs: source |
farm_weather_get | Read cached real MET Norway forecasts and a continuous Météo-France station archive for a chosen French commune INSEE code. Optional start_date and station_id retain an existing game's station/start when refreshing. Returns a frozen snapsho Inputs: commune_code, start_date, station_id |
farm_weather_search | Find French metropolitan communes by name or postcode for opt-in farm weather. Public administrative data, cached and bounded. No IP geolocation, precise address, game mutation or LLM call. Inputs: query |
farm_workshop_get | Read the playable whole-farm mission, shared resources, closed JSON actions and farmer task contract. Educational simulation, no run or official write. |
farm_workshop_run | Execute one bounded whole-farm Rust journal after human agreement, within the agreed call budget. journal_json is complete closed JSON, max 64 KiB, not GardenScript. Returns game state, evidence-linked farmer tasks and an export for explici Inputs: journal_json |
get_bamboo_scene | Read one day (1-365, default UTC day of year) of the published Rust bamboo replay used by the 3D scene. Includes sensors, entrant and SHA-256 provenance. Synthetic exhibition only; not an observation, strategy evaluation or hydraulic foreca Inputs: day |
get_garden_arena | Read one arena's ruleset, scenario, capabilities, limits and status by slug. This performs no LLM call. Inputs: arena_slug |
get_garden_results | Read the sealed results for a GardenScript arena. Performs no simulation or LLM call. Inputs: arena_slug |
list_garden_arenas | List GardenScript arenas. This is local, read-only, and performs no LLM call. Inputs: status, limit, offset |
strategy_prepare_seal | Prepare a review and return its confirmation_url for the human organizer. Requires the private entry_nonce. Does not grant authority to seal. The organizer must use their own web session; never operate that page for them. Inputs: entry_id, entry_nonce |
strategy_seal | Read acknowledgment of an already human-confirmed seal. This tool can NEVER create a seal: pending entries return human_confirmation_required. Give the preparation's confirmation_url to the organizer instead. Legacy receipt/handle arguments Inputs: entry_id, entry_nonce, validation_receipt_id, confirmation_handle |
strategy_validate | Compile GardenScript for an existing entry without running the official scenario. Requires its private entry_nonce. Consumes that entry's validation budget. Inputs: entry_id, source, entry_nonce |
submit_garden_strategy | Submit externally generated GardenScript to an arena. The source is validated again by the local Rust compiler. Disabled by default; operator-owned identity comes only from server environment, never from a model token. Inputs: arena_slug, source, entrant_name, model_provider, model_name, model_version |
validate_gardenscript | Validate and compile an untrusted GardenScript source with the local Rust compiler. This performs no LLM call and stores nothing. Inputs: source |
Every block below points at https://gardenarena.io/mcp. Pick your client and copy.
claude mcp add --transport http gardenarena-gardenscript https://gardenarena.io/mcp
{
"mcpServers": {
"gardenarena-gardenscript": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://gardenarena.io/mcp"]
}
}
}{
"mcpServers": {
"gardenarena-gardenscript": {
"url": "https://gardenarena.io/mcp"
}
}
}{
"servers": {
"gardenarena-gardenscript": {
"type": "http",
"url": "https://gardenarena.io/mcp"
}
}
}{
"context_servers": {
"gardenarena-gardenscript": {
"url": "https://gardenarena.io/mcp"
}
}
}{
"mcpServers": {
"gardenarena-gardenscript": {
"serverUrl": "https://gardenarena.io/mcp"
}
}
}{
"mcpServers": {
"gardenarena-gardenscript": {
"url": "https://gardenarena.io/mcp"
}
}
}name: GardenArena GardenScript
version: 0.0.1
schema: v1
mcpServers:
- name: GardenArena GardenScript
type: streamable-http
url: https://gardenarena.io/mcp{
"mcpServers": {
"gardenarena-gardenscript": {
"httpUrl": "https://gardenarena.io/mcp"
}
}
}{
"mcpServers": {
"gardenarena-gardenscript": {
"type": "http",
"url": "https://gardenarena.io/mcp"
}
}
}{
"mcpServers": {
"gardenarena-gardenscript": {
"url": "https://gardenarena.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fgardenarena.io%2Fmcp&type=streamable_http&id=gardenarena-gardenscript&name=GardenArena%20GardenScript
It answered our last check on 23 October 2026 in 196 ms. Over 5 checks since 13 September 2026 it answered 5. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by gardenarena.io and served from gardenarena.io, the vendor's own domain: https://gardenarena.io/mcp.
30, as returned by the server's own tools/list on 24 September 2026: artifact_verify, bamboo_challenge_get, bamboo_training_artifact, bamboo_training_explain, bamboo_training_run, coop_workshop_get, coop_workshop_run, entry_create, and 22 more.
It answered our last check on 23 October 2026 in 196 ms. Over 5 checks since 13 September 2026 it answered 5.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://gardenarena.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.gardenarena. Endpoint host: gardenarena.io. ARD identifier: urn:air:io.gardenarena:mcp:gardenscript.
First indexed 13 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.