GreenlandAI
REMOTE · MCP.GREENLANDAI.AI
The physical world as queryable data: companies, deposits, infrastructure, projects and commodities.
Available components
Last scanned (18 hours ago)
Scores higher than 74% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Maps and Location
Recent critical change
Authorization (18 Oct 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (market_provide). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 7580 tokens (~151/item across 50 items; 50 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 51 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Nov 26 +1
- Stability: fail → pass ▲ security
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93.
- 10 Nov 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 90.
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 3 Nov 26 +1
- Tool “wallet_transfer” rewrote its description, which is the text the model reads security
- Server version: 0.8.0+7b64a4a → 0.8.0+531f321 functional
- 31 Oct 26 0
- Server version: 0.7.1+6725419 → 0.8.0+7b64a4a functional
- 30 Oct 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “balance_proof” rewrote its description, which is the text the model reads security
- Tool “billing_attempts” rewrote its description, which is the text the model reads security
- Tool “billing_quote” rewrote its description, which is the text the model reads security
- Tool “bridge_proof” rewrote its description, which is the text the model reads security
- Tool “company” rewrote its description, which is the text the model reads security
- Tool “company_search” rewrote its description, which is the text the model reads security
- Tool “contribute_receipts” rewrote its description, which is the text the model reads security
- Tool “contribute_relations” rewrote its description, which is the text the model reads security
- Tool “contribute_stats” rewrote its description, which is the text the model reads security
- Tool “contribute_submissions” rewrote its description, which is the text the model reads security
- Tool “deposit” rewrote its description, which is the text the model reads security
- Tool “deposits” rewrote its description, which is the text the model reads security
- Tool “entity_change” rewrote its description, which is the text the model reads security
- Tool “entity_history” rewrote its description, which is the text the model reads security
- Tool “entity_state” rewrote its description, which is the text the model reads security
- Tool “funding_prepare” rewrote its description, which is the text the model reads security
- Tool “funding_status” rewrote its description, which is the text the model reads security
- Tool “joules_balance” rewrote its description, which is the text the model reads security
- Tool “joules_deficit” rewrote its description, which is the text the model reads security
- Tool “ledger_verify” rewrote its description, which is the text the model reads security
- Tool “look_at” rewrote its description, which is the text the model reads security
- Tool “look_from” rewrote its description, which is the text the model reads security
- Tool “look_through” rewrote its description, which is the text the model reads security
- Tool “map_viewport” rewrote its description, which is the text the model reads security
- Tool “market_accept” rewrote its description, which is the text the model reads security
- Tool “market_listings” rewrote its description, which is the text the model reads security
- Tool “market_match” rewrote its description, which is the text the model reads security
- Tool “market_provide” rewrote its description, which is the text the model reads security
- Tool “market_quote” rewrote its description, which is the text the model reads security
- Tool “market_request” rewrote its description, which is the text the model reads security
- Tool “market_request_rematch” rewrote its description, which is the text the model reads security
- Tool “market_request_rematch_withdraw” rewrote its description, which is the text the model reads security
- Tool “nearby” rewrote its description, which is the text the model reads security
- Tool “oracle_assess” rewrote its description, which is the text the model reads security
- Tool “oracle_assignments” rewrote its description, which is the text the model reads security
- Tool “oracle_deregister” rewrote its description, which is the text the model reads security
- Tool “oracle_register” rewrote its description, which is the text the model reads security
- Tool “place_index” rewrote its description, which is the text the model reads security
- Tool “receipts_me” rewrote its description, which is the text the model reads security
- Tool “relationships” rewrote its description, which is the text the model reads security
- Tool “signals” rewrote its description, which is the text the model reads security
- Tool “site_reconstruction” rewrote its description, which is the text the model reads security
- Tool “trade_settlement” rewrote its description, which is the text the model reads security
- Tool “transparency_latest” rewrote its description, which is the text the model reads security
- Tool “verify_proof” rewrote its description, which is the text the model reads security
- Tool “wallet_transfer” rewrote its description, which is the text the model reads security
- Schema quality: 406 → 151 ▲ functional
- Schema quality: excellent → good functional
- Server version: 0.5.30+8404506 → 0.7.1+6725419 functional
- New tool “company_profile” functional
- New tool “deposit_brief” functional
- New tool “job_status” functional
- New tool “tool_guide” functional
- “company_search” added an optional parameter “fields” cosmetic
- “deposits” added an optional parameter “fields” cosmetic
- “entity_change” added an optional parameter “start” cosmetic
- “look_from” added an optional parameter “fields” cosmetic
- “map_viewport” added an optional parameter “fields” cosmetic
- “nearby” added an optional parameter “fields” cosmetic
- “place_index” added an optional parameter “fields” cosmetic
- “relationships” added an optional parameter “fields” cosmetic
- “billing_quote” reworded the description of “lat” cosmetic
- “billing_quote” reworded the description of “path” cosmetic
- “company” reworded the description of “id” cosmetic
- “contribute_relations” reworded the description of “relations” cosmetic
- “deposits” reworded the description of “commodity” cosmetic
- “joules_balance” reworded the description of “wallet_id” cosmetic
- “look_from” reworded the description of “entity_type” cosmetic
- “relationships” reworded the description of “as_of” cosmetic
- “relationships” reworded the description of “entity” cosmetic
- “relationships” reworded the description of “relation_type” cosmetic
- “site_reconstruction” reworded the description of “include_model” cosmetic
- 28 Oct 26 0
- Tool “map_viewport” rewrote its description, which is the text the model reads security
- Server version: 0.5.29+600f3db → 0.5.30+8404506 functional
- New tool “signals” functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://mcp.greenlandai.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=greenlandai.ai | CN=YE2,O=Let's Encrypt,C=US | 1 Nov 2026 | 30 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 5152f18edb7c28b5cb0e083edaab3588beb |
| SANs: *.greenlandai.ai, greenlandai.ai | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.greenlandai.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814 | 8 | Verified |
| greenlandai.ai. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'none'; frame-ancestors 'none'; |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.greenlandai.ai/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.greenlandai.ai/mcp | HTTPS enforced | 301 | https://mcp.greenlandai.ai/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
balance_proof ~66
Inclusion proof for YOUR wallet balance in the latest hourly transparency attestation: leaf hash, Merkle path, root, the anchoring BSV txid ("pending" until the batch is broadcast) and how to verify it. No arguments: the wallet is the one your credential owns.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
billing_attempts ~105
YOUR OWN charge record, attempt by attempt (your own wallet, from your credential): each attempt's status (pending, completed, settled_zero, failed, refunded …), reserved vs settled joules, and the attempt_id to match a call's `metering.attempt_id`. Paged with limit and offset.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | – | – | Maximum rows to return. 1-200. Default 50. |
| offset | – | – | Rows to skip, for paging. Default 0. |
| Name | Type | Req | Description |
|---|---|---|---|
| count | – | – | – |
| items | – | – | – |
| note | – | – | – |
| statuses | – | – | – |
| wallet_id | – | – | – |
No examples provided.
billing_quote ~243
The exact price of a metered call for YOU, before you make it — free. `path` = the API path the tool hits (e.g. /api/v1/relationships, with hops). Fund `joules_all_in`, the true debit. The quote says when it is a maximum and when an empty answer is free.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | – | – | site.reconstruction date, YYYY-MM-DD. |
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. Alternative to lat/lng for a site. |
| hops | – | – | Graph depth for a relationships path (an agent key up to 10). |
| id | – | – | Entity id (with entity_type) for a site. |
| lat | – | – | Latitude in decimal degrees, -90 to 90 (WGS84). |
| lng | – | – | Longitude in decimal degrees, -180 to 180 (WGS84). |
| path | string | yes | The API path the call would hit, e.g. "/api/v1/relationships", "/api/v1/look.from", "/api/v1/companies/{id}" … |
| radius_m | – | – | site.reconstruction square half-side in metres. |
| Name | Type | Req | Description |
|---|---|---|---|
| billed_hops | – | – | – |
| hops | – | – | – |
| joules | – | – | – |
| joules_all_in | – | – | – |
| joules_with_receipt | – | – | – |
| joules_with_receipt_all_in | – | – | – |
| partial_refund_note | – | – | – |
| path | – | – | – |
| peg | – | – | – |
| pricing_model | – | – | – |
| pricing_tier | – | – | – |
| query_type | – | – | – |
| quote_is_maximum | – | – | – |
| rail_fee_joules | – | – | – |
| rate_per_hop | – | – | – |
| receipt | – | – | – |
| receipt_offer | – | – | – |
| refund_on_empty | – | – | – |
| tier | – | – | – |
| usd | – | – | – |
No examples provided.
bridge_proof ~60
Inclusion proofs for YOUR Bridge Ledger rows (contribution and fee events): per-row leaf hash, Merkle path, bridge_root and the anchoring BSV txid ("pending" until the hourly batch is broadcast). No arguments: scoped to your credential.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
company ~104
One company's record by id: the company, the deposits and infrastructure it operates, its relationships with tier and provenance, and `merged` when the id moved. Have only a name? Call `company_search` first. An unknown id is a 404. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| id | – | yes | The GreenlandAI company id: a whole number (known_companies.id, e.g. "4334"). |
Structured output declared, but exposes no named fields.
No examples provided.
company_profile ~136
company + relationships + entity_history for one company in ONE call, billed exactly as the three would be, with one charged_joules total. Lean by default; include_raw for everything. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| hops | integer | – | Relationship depth, 1-10. Default 1. |
| id | – | yes | The company id (from company_search, a pin or a relationship row). |
| include_raw | boolean | – | Return every part whole. Default false. |
Structured output declared, but exposes no named fields.
No examples provided.
company_search ~202
Find companies by name, sector or country, to get the id that `company`, `relationships` and the entity tools take. Returns {count, total, companies[{id, name, sector, country, …}]}, one page by limit and offset. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| country | – | – | Country as an ISO code or a name; USA, US and United States find the same companies. |
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| limit | integer | – | Maximum rows to return. Up to 100. Default 50. |
| offset | integer | – | Rows to skip, for paging. Default 0. |
| search | – | – | Part of the company's name (case-insensitive substring match), e.g. "rio tinto". |
| sector | – | – | Exact sector name (case-insensitive), e.g. "mining". |
Structured output declared, but exposes no named fields.
No examples provided.
contribute_receipts ~85
Your OWN append-only contribution receipts, each with its canonical claim hash (claim_sha256), so you can check the door holds what you sent. Send your enabled gai_ key as X-API-Key. Paged.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum rows to return. Default 50. |
| offset | integer | – | Rows to skip, for paging. Default 0. |
Structured output declared, but exposes no named fields.
No examples provided.
contribute_relations ~99
Submit evidenced graph relationships to the contributor door (TEN programme). Each relation needs subject, relation, object, a real source_url and a verbatim quote from it. Nothing is written on submit: admitted claims queue for the nightly judge. Send your enabled gai_ key as X-API-Key.
| Name | Type | Req | Description |
|---|---|---|---|
| entities | – | – | New entities proposed alongside a relation that references them; never accepted on their own. |
| relations | array | yes | The relationships to submit. |
Structured output declared, but exposes no named fields.
No examples provided.
contribute_stats ~48
Your OWN contributor standing: submitted, accepted and rejected totals, acceptance rate, pending review and standing (good, warning, suspended, revoked). Send your enabled gai_ key as X-API-Key.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
contribute_submissions ~82
Your OWN per-item submission outcomes: pending_review, accepted or rejected, with the judge's reason verbatim and what was promoted. Send your enabled gai_ key as X-API-Key. Paged.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum rows to return. Default 50. |
| offset | integer | – | Rows to skip, for paging. Default 0. |
Structured output declared, but exposes no named fields.
No examples provided.
deposit ~89
One resource deposit by id: its record, `commodities[]` ({name, role, group}) and operators. Pair with `deposits(commodity=…)` to find ids. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| id | – | yes | The deposit's numeric id (from `deposits`, a pin, or a relationship row). |
Structured output declared, but exposes no named fields.
No examples provided.
deposit_brief ~136
deposit + relationships + entity_history for one deposit in ONE call, billed exactly as the three would be, with one charged_joules total. Lean by default; include_raw for everything. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| hops | integer | – | Relationship depth, 1-10. Default 1. |
| id | – | yes | The deposit id (from deposits, a pin or a relationship row). |
| include_raw | boolean | – | Return every part whole. Default false. |
Structured output declared, but exposes no named fields.
No examples provided.
deposits ~252
Search resource deposits by commodity, resource_type, country, status, owner_country, max_port_km or name. `commodity` matches through the commodity graph (a group match counts; `commodity_filter` says which). Returns {count, total, deposits[]}, paged. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| commodity | – | – | A commodity name, e.g. "neodymium". |
| country | – | – | Country as an ISO code or a name. |
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| limit | integer | – | Maximum rows to return. Up to 100. Default 50. |
| max_port_km | – | – | Only deposits within this many km of a port. |
| offset | integer | – | Rows to skip, for paging. Default 0. |
| owner_country | – | – | Country of the deposit's owners (their home states), ISO code or name. |
| resource_type | – | – | The deposit's primary resource label (exact, case-insensitive). |
| search | – | – | Part of the deposit's name (substring). |
| status | – | – | Deposit status, e.g. operating, development, exploration. |
Structured output declared, but exposes no named fields.
No examples provided.
entity_change ~347
The structured change at one site between two dates (t0, t1): per class (water, ice, canopy, pad, stockpile) the area changed, what optical and radar each saw, and a confidence. Read `height_class` first: only repeat_surface supports a volume change. Slow (about 15–60 s): start=true answers at once with a job_id for job_status. Agent keys only. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. With id; or pass lat + lng. |
| id | – | – | The entity's numeric id (with entity_type). |
| lat | – | – | Latitude in decimal degrees, -90 to 90 (WGS84). |
| lng | – | – | Longitude in decimal degrees, -180 to 180 (WGS84). |
| max_cloud | number | – | Maximum cloud cover of a scene, 0-100 percent. Default 40. |
| radius_m | – | – | Footprint radius in metres, 50-2500, overriding the site's held footprint (else a 500 m circle). |
| same_season | boolean | – | For spans of 300+ days, take the t0 frame at t1's day of year. Default true. |
| start | boolean | – | true: answer at once with a job_id (the same reservation, settled when the measurement is done) |
| t0 | string | yes | The earlier date, YYYY-MM-DD, on or after 1984-03-16. Required. |
| t1 | – | – | The later date, YYYY-MM-DD. Default today. |
Structured output declared, but exposes no named fields.
No examples provided.
entity_history ~107
The cheap index of one entity's dates: imagery scene dates (no images), our record's versions since record time began, and a short newest-first `what_changed` list, each item marked world time or our time. Agent keys. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_type | string | yes | Entity kind: deposit | infrastructure | company | project. Required. |
| id | – | yes | The entity's numeric id. Required. |
Structured output declared, but exposes no named fields.
No examples provided.
entity_state ~176
One packet for one entity at a date (as_of): the entity as we held it then, the pins held by then, its relationships valid then, and the satellite still for that date. Charged for the parts delivered. Agent keys only. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | – | – | The date of the packet, YYYY-MM-DD. Default today. |
| entity_type | string | yes | Entity kind: deposit | infrastructure | company | project. Required. |
| id | – | yes | The entity's numeric id. Required. |
| max_cloud | number | – | Maximum cloud cover of a scene, 0-100 percent. For the still. Default 20. |
| radius_km | number | – | Radius for the nearby pins, in km. Default 25. |
Structured output declared, but exposes no named fields.
No examples provided.
funding_prepare ~84
The in-band funding step for a joule shortfall: your own USDC-on-Base deposit address and the live minimum, read from the running system. It moves no money; track the deposit with `funding_status`.
| Name | Type | Req | Description |
|---|---|---|---|
| needed | integer | – | The joules you are short (the shortfall from joules_deficit or a 402). Default 0. |
| Name | Type | Req | Description |
|---|---|---|---|
| in_band_agent_funding_live | – | – | – |
| needed | – | – | – |
| note | – | – | – |
| routes | – | – | – |
| wallet_id | – | – | – |
No examples provided.
funding_status ~51
YOUR OWN USDC-on-Base deposit state: credited, or held (below the minimum, above the maximum, or waiting for platform funding) — nothing is lost while held. From your credential, no arguments.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| deposits | – | – | – |
| held_below_min_total_usdc | – | – | – |
| minimum_usdc | – | – | – |
| needed_to_credit_usdc | – | – | – |
| note | – | – | – |
| scanner_cursor_block | – | – | – |
| usdc_live | – | – | – |
No examples provided.
job_status ~67
An entity_change job started with start=true: running, done (with the answer and how its reservation settled) or failed (released). Free. Only the paying wallet can read it.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | The job_id an entity_change(start=true) call returned (a UUID). |
Structured output declared, but exposes no named fields.
No examples provided.
joules_balance ~73
Your own wallet balance, free. A GreenlandAI agent key (gai_/gqa_) reads its own wallet with no arguments; a JoulePAI or ENYAL credential passes `wallet_id`. The graph meter debits this same wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| wallet_id | – | – | Wallet id (UUID) to read |
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | – | – | – |
| agent_name | – | – | – |
| balance | – | – | – |
| balance_joules | – | – | – |
| handle | – | – | – |
| id | – | – | – |
| owner_type | – | – | – |
| verification_status | – | – | – |
| wallet_id | – | – | – |
No examples provided.
joules_deficit ~112
Can you afford the next call? Give a planned `cost`; returns {needed, have, shortfall, tool_to_call_next}. Free. Agent keys read their own wallet; a JoulePAI or ENYAL credential may pass `wallet_id`.
| Name | Type | Req | Description |
|---|---|---|---|
| cost | integer | yes | The joules the next call will cost (its joules_all_in from billing_quote). |
| wallet_id | – | – | Wallet to read (UUID); omit to use your own. Not used with a GreenlandAI agent key. |
| Name | Type | Req | Description |
|---|---|---|---|
| have | – | – | – |
| needed | – | – | – |
| shortfall | – | – | – |
| tool_to_call_next | – | – | – |
No examples provided.
ledger_verify ~37
Recent public ledger anchors with their on-chain transaction ids and the exact credit supply at each anchor — public, no auth. Independently checkable.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| anchors | – | – | – |
| chain_semantics | – | – | – |
| coverage | – | – | – |
| eras | – | – | – |
| hash_format | – | – | – |
| total | – | – | – |
No examples provided.
look_at ~230
A satellite still of a place: the newest Sentinel-2 archive image on or before `as_of`, by lat/lng or entity_type + id. Returns the JPEG plus provenance (`observed_at` is the scene's date). A cloudy or missing scene is `available:false` and costs nothing. Agent keys only. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | – | – | Newest scene on or before this date, YYYY-MM-DD. Default: the newest scene. |
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. With `id`, anchors the still on that entity. |
| id | – | – | Entity id to anchor on (with entity_type). |
| lat | – | – | Latitude in decimal degrees, -90 to 90 (WGS84). Use with lng, or pose on an entity instead. |
| lng | – | – | Longitude in decimal degrees, -180 to 180 (WGS84). |
| max_cloud | number | – | Maximum cloud cover of a scene, 0-100 percent. Default 20. |
Structured output declared, but exposes no named fields.
No examples provided.
look_from ~242
Map pins near a point (lat/lng + radius_km). `entity_type` alone filters to that type; with `id` it anchors the view at that entity. Each pin carries its `source_tier` provenance. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| energy | boolean | – | Include energy-fleet infrastructure (power plants and grid assets). Default false. |
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. |
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| id | – | – | Entity id to anchor the pose on (with entity_type). |
| include_country_centroids | boolean | – | Also return country-centre placeholder pins (entities known only by country). Default false. |
| lat | – | – | Latitude in decimal degrees, -90 to 90 (WGS84). Use with lng, or pose on an entity instead. |
| lng | – | – | Longitude in decimal degrees, -180 to 180 (WGS84). |
| radius_km | number | – | Search radius around the pose, in km. Default 100. |
Structured output declared, but exposes no named fields.
No examples provided.
look_through ~256
An ordered stack of dated Sentinel-2 stills of one site from t0 to t1, one per window (max_frames, default 6), each with its own scene date. A window with no clear scene is an explicit empty frame, not charged. Agent keys only. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. |
| id | – | – | Entity id to anchor on (with entity_type). |
| lat | – | – | Latitude in decimal degrees, -90 to 90 (WGS84). |
| lng | – | – | Longitude in decimal degrees, -180 to 180 (WGS84). |
| max_cloud | number | – | Maximum cloud cover of a scene, 0-100 percent. Default 20. |
| max_frames | integer | – | How many equal windows to cut the range into, 1-12; one still per window. Default 6. |
| t0 | string | yes | Start of the date range, YYYY-MM-DD, on or after 2015-06-23. Required. |
| t1 | – | – | End of the date range, YYYY-MM-DD. Default today. |
Structured output declared, but exposes no named fields.
No examples provided.
map_viewport ~214
Everything inside a bounding box (min_lat, min_lng, max_lat, max_lng): the true count per type for the whole box plus a capped sample of pins. Agent keys only. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| energy | boolean | – | Include energy-fleet infrastructure and projects. Default false. |
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. Default all four. |
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| include_country_centroids | boolean | – | Also return country-centre placeholder pins (entities known only by country). Default false. |
| max_lat | – | – | North edge of the bounding box (latitude). |
| max_lng | – | – | East edge of the bounding box (longitude). |
| min_lat | – | – | South edge of the bounding box (latitude). Send all four edges together. |
| min_lng | – | – | West edge of the bounding box (longitude). |
Structured output declared, but exposes no named fields.
No examples provided.
market_accept ~84
Accept a delivery on a match (POST /match/{id}/accept) — releases escrow to the provider. You must be the buyer party; the backend enforces it.
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | – | – | Your own opaque key: the same key accepts once, never twice. |
| match_id | string | yes | The marketplace match id (UUID). You must be its buyer. |
Structured output declared, but exposes no named fields.
No examples provided.
market_listings ~180
Browse the RAREEAI marketplace: kind="providers" (listings, filterable and sorted) or "oracles". Paged.
| Name | Type | Req | Description |
|---|---|---|---|
| active | boolean | – | Only active listings. Default true. |
| frontier | – | – | Listings in this frontier only (providers). |
| kind | string | – | "providers" (marketplace listings) or "oracles". Default providers. |
| limit | integer | – | Maximum rows to return. Up to 200. Default 50. |
| offset | integer | – | Rows to skip, for paging. Default 0. |
| oracle_verified | – | – | Only providers that opted in to oracle verification (true) or did not (false). |
| resource_type | – | – | Listings of this resource type only (providers). |
| sort | string | – | Sort order, e.g. price_asc (default) or price_desc. |
Structured output declared, but exposes no named fields.
No examples provided.
market_match ~65
Read one marketplace match you are a party to: its escrow_terms, fee and timeout fields, dispute window and dispute state. For the settlement legs use `trade_settlement`.
| Name | Type | Req | Description |
|---|---|---|---|
| match_id | string | yes | The marketplace match id (UUID). You must be a party to it. |
Structured output declared, but exposes no named fields.
No examples provided.
market_provide ~80
Create or update a marketplace listing (verified account, marketplace:write). Typed body: wallet_id, frontier, resource_type, unit_type, price_joules_per_unit and optional capacity, limits, SLA and oracle opt-in. A first-time registration carries a one-time fee.
| Name | Type | Req | Description |
|---|---|---|---|
| body | – | yes | The listing; each field is described in its schema. |
Structured output declared, but exposes no named fields.
No examples provided.
market_quote ~74
Read one marketplace REQUEST you own, by id: its terms, status and units matched, plus the generic `escrow_terms`. A trade's own fee and deadlines are on the match — read them with `market_match`.
| Name | Type | Req | Description |
|---|---|---|---|
| request_id | string | yes | The marketplace REQUEST id (UUID) you posted with `market_request`. |
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | – | – | – |
| contract_escrow | – | – | – |
| created_at | – | – | – |
| escrow_terms | – | – | – |
| expires_at | – | – | – |
| frontier | – | – | – |
| id | – | – | – |
| max_price_per_unit | – | – | – |
| priority | – | – | – |
| privacy_mode | – | – | – |
| rematch_max_price_per_unit | – | – | – |
| rematch_max_total_joules | – | – | – |
| rematch_until | – | – | – |
| requirements | – | – | – |
| resource_type | – | – | – |
| speed | – | – | – |
| status | – | – | – |
| target_provider_id | – | – | – |
| unit_type | – | – | – |
| units_matched | – | – | – |
| units_needed | – | – | – |
| wallet_id | – | – | – |
No examples provided.
market_request ~81
Post a marketplace BUY request (verified account, marketplace:write): wallet_id, frontier, resource_type, unit_type, units_needed, max_price_per_unit and options. Escrow is debited on match. A physical trade must carry `physical_claim` (the site and dates).
| Name | Type | Req | Description |
|---|---|---|---|
| body | – | yes | The buy request; each field is described in its schema. |
Structured output declared, but exposes no named fields.
No examples provided.
market_request_rematch ~65
Match one of YOUR open requests now. Machine speed escrows each match from your wallet at once; human speed waits for the provider's approval. A 409 when the request is no longer open.
| Name | Type | Req | Description |
|---|---|---|---|
| request_id | string | yes | Your open marketplace REQUEST id (UUID). |
Structured output declared, but exposes no named fields.
No examples provided.
market_request_rematch_withdraw ~61
Withdraw a request's automatic re-matching consent now (DELETE /api/v1/marketplace/request/{id}/rematch). Matches already escrowed stay as they are.
| Name | Type | Req | Description |
|---|---|---|---|
| request_id | string | yes | Your marketplace REQUEST id (UUID). |
Structured output declared, but exposes no named fields.
No examples provided.
nearby ~204
Entities near a location: lat + lng, radius_km, an optional entity_type, limit. Each carries `source_tier`. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. Optional filter; default all four. |
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| include_country_centroids | boolean | – | Also return country-centre placeholder pins (entities known only by country). Default false. |
| lat | number | yes | Latitude in decimal degrees, -90 to 90 (WGS84). Required. |
| limit | integer | – | Maximum rows to return. Up to 100. Default 20. |
| lng | number | yes | Longitude in decimal degrees, -180 to 180 (WGS84). Required. |
| radius_km | number | – | Search radius in km. Default 100. |
Structured output declared, but exposes no named fields.
No examples provided.
oracle_assess ~100
Post your verdict on a delivery you were assigned: verdict (valid or invalid), quality_score 0-100, notes, an optional execution_trace. A low score opens a dispute. A 409 means the match has moved on — do not retry; read the match.
| Name | Type | Req | Description |
|---|---|---|---|
| body | – | yes | Your verdict; each field is described in its schema. |
| match_id | string | yes | The marketplace match id (UUID). One you are assigned to assess. |
Structured output declared, but exposes no named fields.
No examples provided.
oracle_assignments ~72
List YOUR oracle assignments: each delivery to assess, with its match_id, deadline, the fee earned and your verdict if already given. Optional status filter and limit.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum rows to return. 1-200. Default 50. |
| status | – | – | Only assignments in this status. |
Structured output declared, but exposes no named fields.
No examples provided.
oracle_deregister ~63
Deregister as an oracle and get your stake back from escrow (less anything slashed). `wallet_id` is required. Fails while you have pending assessments.
| Name | Type | Req | Description |
|---|---|---|---|
| wallet_id | string | yes | Your oracle wallet's UUID (the one that holds the stake). |
Structured output declared, but exposes no named fields.
No examples provided.
oracle_register ~81
Register as a RAREEAI oracle by staking joules (invite-only at launch; a wallet not yet invited is told how to apply). Body: wallet_id, specialisations (1–7 from a fixed list) and stake_amount. The stake is returned when you deregister.
| Name | Type | Req | Description |
|---|---|---|---|
| body | – | yes | The registration; each field is described in its schema. |
Structured output declared, but exposes no named fields.
No examples provided.
place_index ~329
What exists at a place, and when: dated stills, source quotes and measurements within radius_km of lat/lng or of an entity's site, newest first. Each row carries valid_on (world time) and recorded_at (our time). Filter by dates and kinds; paged. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. With id, centres on that entity's site. |
| entity_types | – | – | Comma list of entity kinds to include (deposit, infrastructure, company, project). |
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| from_date | – | – | Only rows valid on or after this date, YYYY-MM-DD. |
| id | – | – | The entity's numeric id (with entity_type). |
| kinds | – | – | Comma list of row kinds: still, quote, verdict, match, measurement. |
| lat | – | – | Latitude in decimal degrees, -90 to 90 (WGS84). With lng; or name an entity. |
| limit | integer | – | Maximum rows to return. 1-500. Default 100. |
| lng | – | – | Longitude in decimal degrees, -180 to 180 (WGS84). |
| offset | integer | – | Rows to skip, for paging. Default 0. |
| radius_km | number | – | Radius in km, up to 50. Default 2. |
| to_date | – | – | Only rows valid on or before this date, YYYY-MM-DD. |
Structured output declared, but exposes no named fields.
No examples provided.
receipts_me ~39
Receipts for your key: whether THIS key is opted in to a receipt with each paid graph answer, and how its owner turns them on. Free.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | – | – | – |
| caller | – | – | – |
| receipt_offer | – | – | – |
| what_a_receipt_is | – | – | – |
No examples provided.
relationships ~312
Labelled relationship edges (owns, operates, supplies …) around ONE entity, with tier and provenance: start from entity_type + entity_id (or a name in `entity`), walk `hops` deep, filter by relation_type. `as_of` answers for a past date. An ambiguous name fails uncharged and lists the candidates. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | – | – | Answer for a past date: YYYY-MM-DD or a UTC datetime. |
| entity | – | – | Start entity by NAME: an exact (case-insensitive) match, else a name that contains it. |
| entity_id | – | – | The start entity's numeric id (with entity_type) — the unambiguous way to name it. |
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. Pins the start node with entity_id. |
| fields | – | – | Only these keys in each row (plus id). Omit for all. |
| hops | integer | – | Traversal depth, 1-10 (agent keys). Default 1. The billing unit: priced per hop. |
| limit | integer | – | Maximum edges to return, up to 100. Default 50. |
| offset | integer | – | Rows to skip, for paging. Default 0. |
| relation_type | – | – | Only edges with this relation label, e.g. OPERATES, CONTAINS, MEMBER_OF. |
| search | – | – | Free-text filter over edge text. |
Structured output declared, but exposes no named fields.
No examples provided.
signals ~143
The live signal cards: compiled, provenance-carrying observations (lead_lag, network, signature) with severity and the entities they name. Cards appear only while their type is armed; an answer with no cards costs nothing. Observations, not advice. Agent keys only. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| country | – | – | Two-letter ISO country code (e.g. DE); cards about entities in that country. |
| kind | – | – | One signal family: lead_lag | network | signature. Default all three. |
| limit | integer | – | Cards per answer, 1-50. Default 20. |
Structured output declared, but exposes no named fields.
No examples provided.
site_reconstruction ~253
A dated, georeferenced 3D model of a site (entity_type + id, or lat + lng) with measurements: extent, elevation, slope, pits and heaps with volumes. The tier (lidar_2m or dem_30m) is decided before any charge. Slow (about 15–60 s). Agent keys only. Metered: see CHARGING in the server instructions; quote first with `billing_quote`.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | – | – | Pick the lidar collection and texture nearest this date, YYYY-MM-DD. |
| entity_type | – | – | Entity kind: deposit | infrastructure | company | project. With id; or pass lat + lng. |
| id | – | – | The entity's numeric id (with entity_type). |
| include_model | boolean | – | Also return the binary glTF model as model_glb_base64 (a lidar model is about 5 MB as base64). |
| lat | – | – | Latitude in decimal degrees, -90 to 90 (WGS84). |
| lng | – | – | Longitude in decimal degrees, -180 to 180 (WGS84). |
| radius_m | – | – | Half the square's side, in metres, 100-1000. Default 300. |
Structured output declared, but exposes no named fields.
No examples provided.
tool_guide ~83
The full guide for one tool, free and not metered: its complete description (edge cases, every rule, examples), every parameter's full description and the fields it returns. Each tool's listed description is its short contract; read this when you need the rest.
| Name | Type | Req | Description |
|---|---|---|---|
| tool | string | yes | A tool name from tools/list, e.g. relationships. |
Structured output declared, but exposes no named fields.
No examples provided.
trade_settlement ~88
YOUR OWN trade's settlement, as buyer or seller: every leg (payout, fees, refunds) with its role, amount, ledger status and on-chain anchor state, plus the escrow contract's legs when there is one. A 404 means you were not a party.
| Name | Type | Req | Description |
|---|---|---|---|
| match_id | string | yes | The marketplace match id (UUID). You must have been its buyer or seller. |
| Name | Type | Req | Description |
|---|---|---|---|
| all_anchored | – | – | – |
| contract | – | – | – |
| dispute | – | – | – |
| leg_count | – | – | – |
| legs | – | – | – |
| match_id | – | – | – |
| settled | – | – | – |
| your_role | – | – | – |
No examples provided.
transparency_latest ~64
The latest hourly public transparency attestation: a Merkle root over every wallet balance, the verified total supply and the Bridge Ledger root, with the anchoring BSV txid ("pending" until broadcast; `last_anchored` names the newest anchored one). No auth.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| algorithm_version | – | – | – |
| anchoring | – | – | – |
| bridge_root | – | – | – |
| bridge_rows | – | – | – |
| bsv_txid | – | – | – |
| fees | – | – | – |
| last_anchored | – | – | – |
| merkle_root | – | – | – |
| settlement_leaves | – | – | – |
| settlement_root | – | – | – |
| state_root | – | – | – |
| supply_verified | – | – | – |
| timestamp | – | – | – |
| total_supply | – | – | – |
| tx_count | – | – | – |
| volume | – | – | – |
| wallet_count | – | – | – |
No examples provided.
verify_proof ~111
Look up one identifier (a chunk, proof, match or transfer id, or a BSV txid) in ENYAL's public verify lookup; its verdict fields come back unchanged. Only `chain_confirmed:true` is a verified anchor; `degraded:true` means inconclusive, not absent. No auth.
| Name | Type | Req | Description |
|---|---|---|---|
| identifier | string | yes | The id to look up: a chunk_id, proof_id, match_id or transfer id (UUID), or a BSV transaction id (64 hex). |
| Name | Type | Req | Description |
|---|---|---|---|
| chain_confirmed | – | – | – |
| chain_status | – | – | – |
| count | – | – | – |
| degraded | – | – | – |
| found | – | – | – |
| identifier | – | – | – |
| note | – | – | – |
| recorded | – | – | – |
| results | – | – | – |
| unavailable_sources | – | – | – |
No examples provided.
wallet_transfer ~103
A direct wallet-to-wallet transfer (wallet:transfer scope). An agent wallet may send only to a registered destination; limits are live config, not constants. Typed body: from_wallet_id, to_wallet_id or to_handle, amount and options. A transfer fee is charged to the sender. privacy_mode: only 'transparent' (or omit it) — the other modes are temporarily unavailable and refused.
| Name | Type | Req | Description |
|---|---|---|---|
| body | – | yes | The transfer; each field is described in its schema. |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the GreenlandAI MCP server?
GreenlandAI is a hosted endpoint at https://mcp.greenlandai.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.greenlandai.ai
claude mcp add --transport http ai-greenlandai-greenlandai 'https://mcp.greenlandai.ai/mcp'
What is the GreenlandAI MCP server?
GreenlandAI is an MCP server listed in the public MCP registry as ai.greenlandai/greenlandai. The physical world as queryable data: companies, deposits, infrastructure, projects and commodities. This page covers its hosted endpoint (https://mcp.greenlandai.ai/mcp).
Is the GreenlandAI MCP server safe to use?
GreenlandAI scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the GreenlandAI MCP server expose?
GreenlandAI exposes 50 tools: look_from, signals, relationships, nearby, map_viewport, and 45 more. Their descriptions and schemas cost roughly 6,438 tokens of context every time the server is loaded.
Does the GreenlandAI MCP server require authentication?
No. We connected to GreenlandAI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the GreenlandAI MCP server still maintained?
GreenlandAI is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the GreenlandAI MCP server?
VerifyMCP ran 13 checks on GreenlandAI, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.