A remote geospatial AI server that lets an assistant fetch Sentinel-2 satellite tiles, run flood classification, query weather, and check agent trust and audit-
What you can do
Fetch the least-cloudy Sentinel-2 tile for an H3 cell, with signed band URLs and cached metadata. Run flood classification on a fetched tile and get class, flood percentage and confidence. Query wind, precipitation and temperature for an H3 cell at a timestamp. Look up an agent's trust tier and score, verify its breadcrumb chain, roll pending breadcrumbs into a sealed epoch, and produce an EU AI Act compliance report. Embedding generation is listed but not yet implemented.
When to use it
Useful when an assistant needs satellite imagery or flood-risk signals for a specific location, atmospheric conditions for an H3 cell, or governance checks such as trust scores, audit-chain verification and compliance reporting for an agent.
Requirements
A remote streamable HTTP endpoint; no package, environment variable or header is declared. No authentication is declared. Network access to the endpoint and its upstream services (Microsoft Planetary Computer, Open-Meteo, a RunPod endpoint) is needed.
Before you install
The weather tool writes to Spatial Memory and drops a signed audit breadcrumb, and the epoch-roll tool seals pending breadcrumbs, so calls change stored state. Tile data is sent to a third-party RunPod endpoint for classification. Compliance and trust results should not be treated as certification on their own.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.geiant%2Fmcp-perception/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Fetch the least-cloudy Sentinel-2 L2A tile covering a given H3 cell from Microsoft Planetary Computer. Returns signed COG band URLs for all 6 Prithvi/Clay spectral bands (B02 Blue, B03 Green, B04 Red, B8A NIR, B11 SWIR1, B12 SWIR2), plus tile metadata. The tile is cached in memory for subsequent perception_classify or perception_embed calls.
Run Prithvi-EO-2.0-300M-TL-Sen1Floods11 flood classification on a Sentinel-2 tile previously fetched by perception_fetch_tile. Sends the 6-band chip to a RunPod endpoint and returns: dominant_class, flood_pixel_pct, confidence, class_counts, and the full perception_chain. The perception chain is written to Spatial Memory and a signed audit breadcrumb is dropped to the agent trail.
[Sub-phase 4.2 — NOT YET IMPLEMENTED] Will generate Clay v1.5 embeddings.
Parameterstile_idrequired
perception_weather
Query atmospheric conditions for an H3 cell at a given timestamp from Open-Meteo ERA5. Returns wind, precipitation, temperature. Writes to Spatial Memory and drops a signed audit breadcrumb.
Get the current TierGate trust tier and score for an agent. Tiers: provisioned (0%) → observed (25%) → trusted (60%) → certified (85%) → sovereign (99%). Omit agent_pk to query the server's own agent.
Parametersagent_pk
gns_verify_chain
Verify the cryptographic integrity of an agent's breadcrumb chain. Returns { is_valid, block_count, issues[] } plus epoch Merkle roots. A valid chain proves no audit records have been tampered with.
Parametersagent_pk
gns_roll_epoch
Roll all pending breadcrumbs into a new sealed epoch with a Merkle root. Returns { epoch_index, merkle_root, block_count, epoch_hash }. Call this at the end of a session to produce a tamper-evident compliance snapshot.
Takes no parameters.
gns_get_compliance_report
Get Compliance Report
Returns a full EU AI Act compliance report for a GNS agent, including trust score, chain verification, Merkle epoch proofs, delegation certificate, and regulatory status.
ParametersagentHandle
Version history
1
v0.3.3LatestSep 16, 2026
Score
75%
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.