OCEI v2.2 Orbital Compute & Arbitrage Oracle
REMOTE · ORBITCOMPUTE.AI
Attested orbital AI compute physics, NOAA space-weather & $/MTok arbitrage oracle (OCEI v2.2).
Available components
Last scanned (18 hours ago)
Scores higher than 44% of remote servers
Reachable. Last reached 21 Nov 2026.
Category AI and Machine Learning
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 Security46
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS check failed: the endpoint is reachable over plaintext HTTP. See how to fix → View diagnostics → Fail
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- 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 Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1108 tokens (~277/item across 4 items; 4 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 Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
- Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (12)
- TLS certificate
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
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.
- 21 Nov 26 +5
- Tool “compute_arbitrage_dispatch” rewrote its description, which is the text the model reads security
- Tool “evaluate_orbital_compute_regime” rewrote its description, which is the text the model reads security
- Tool “solve_optimal_workload_allocation” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- Tool coverage: 0% → 100% ▲ functional
- Schema quality: fair → good functional
- Server version: 2.2.0 → 2.3.0 functional
- New tool “get_ocei_history_and_live_grids” functional
- “compute_arbitrage_dispatch” added an optional parameter “grid_hub” cosmetic
- “evaluate_orbital_compute_regime” added an optional parameter “annual_attrition_pct” cosmetic
- “evaluate_orbital_compute_regime” added an optional parameter “comm_intensity_bits_per_flop” cosmetic
- “evaluate_orbital_compute_regime” added an optional parameter “earth_capex_factor” cosmetic
- “evaluate_orbital_compute_regime” added an optional parameter “grid_hub” cosmetic
- “evaluate_orbital_compute_regime” added an optional parameter “launch_vehicle” cosmetic
- “solve_optimal_workload_allocation” added an optional parameter “comm_intensity_bits_per_flop” cosmetic
- “solve_optimal_workload_allocation” added an optional parameter “grid_hub” cosmetic
- “compute_arbitrage_dispatch” reworded the description of “grid_price_usd_mwh” cosmetic
- “compute_arbitrage_dispatch” reworded the description of “hw” cosmetic
- “compute_arbitrage_dispatch” reworded the description of “power_mw” cosmetic
- “compute_arbitrage_dispatch” reworded the description of “storm_mode” cosmetic
- “evaluate_orbital_compute_regime” reworded the description of “altitude_km” cosmetic
- “evaluate_orbital_compute_regime” reworded the description of “beta_deg” cosmetic
- “evaluate_orbital_compute_regime” reworded the description of “grid_price_usd_mwh” cosmetic
- “evaluate_orbital_compute_regime” reworded the description of “hw” cosmetic
- “evaluate_orbital_compute_regime” reworded the description of “loop_temp_c” cosmetic
- “evaluate_orbital_compute_regime” reworded the description of “power_mw” cosmetic
- “evaluate_orbital_compute_regime” reworded the description of “storm_mode” cosmetic
- “solve_optimal_workload_allocation” reworded the description of “grid_price_usd_mwh” cosmetic
- “solve_optimal_workload_allocation” reworded the description of “max_latency_ms” cosmetic
- “solve_optimal_workload_allocation” reworded the description of “storm_mode” cosmetic
- “solve_optimal_workload_allocation” reworded the description of “workload_type” cosmetic
- “compute_arbitrage_dispatch” made “grid_price_usd_mwh” optional cosmetic
- 20 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Nov 26 0
- Stability: unverified → 0.03 ▲ functional
- 13 Nov 26 51
First indexed and scored.
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://orbitcompute.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=orbitcompute.ai | CN=WE1,O=Google Trust Services,C=US | 10 Nov 2026 | 8 Feb 2027 | ECDSA 256 | ECDSA-SHA256 | cc4dae6b8d1dc15913a046ebc807b7be |
| SANs: orbitcompute.ai, api.orbitcompute.ai, *.api.orbitcompute.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of orbitcompute.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814 | 8 | Verified |
| orbitcompute.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 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://orbitcompute.ai/mcp | Verified | 200 | |
| http (plaintext) | http://orbitcompute.ai/mcp | Served over HTTP | 200 |
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 →
compute_arbitrage_dispatch ~242
Fast binary go/no-go economic dispatch decision comparing a single terrestrial electricity price or live hub (ERCOT, PJM, EPEX) against the orbital breakeven threshold ($/MWh). Returns exact dispatch_signal (ORBIT_PRIMARY, HYBRID_SPLIT, TERRESTRIAL_PRIMARY), dispatch_directive, breakeven threshold, and $/MTok spread. Use ONLY for binary grid-vs-orbit switching; use solve_optimal_workload_allocation for 3-shell percentage splits.
| Name | Type | Req | Description |
|---|---|---|---|
| grid_hub | string | – | Live wholesale electricity hub to evaluate when grid_price_usd_mwh is omitted. |
| grid_price_usd_mwh | number | – | Explicit local spot electricity price in USD/MWh (supports negative wind/solar spot prices). If omitted, uses grid_hub. |
| hw | string | – | Hardware stack profile determining $/MTok and breakeven $/MWh. |
| power_mw | number | – | Cluster scale in MW used to size launch/bus overhead and breakeven threshold. |
| storm_mode | string | – | Space-weather mode for pre-emptive storm failover triggers. |
No output schema declared.
No examples provided.
evaluate_orbital_compute_regime ~493
Full physics, 5-year TCO, and credit-underwriting audit for an orbital AI cluster. Use this tool for deep thermodynamic, radiation, Turyshev communication-intensity (bits/J), attrition stress (3.5%/9.0%), $/W payback, and 4-pillar OCEI v2.3 scoring. Do NOT use for fast binary electricity dispatch (use compute_arbitrage_dispatch) or multi-shell percentage routing (use solve_optimal_workload_allocation).
| Name | Type | Req | Description |
|---|---|---|---|
| altitude_km | number | – | Orbital altitude in km (320=VLEO, 650=Dawn-Dusk SSO, 1500=MEO). |
| annual_attrition_pct | number | – | Annual unrepairable hardware attrition rate in percent (0=raw baseline, 3.5=burn-in screened, 9.0=unscreened stress). |
| beta_deg | number | – | Solar beta angle in degrees (75-90 yields zero eclipse at 650 km). |
| comm_intensity_bits_per_flop | number | – | Workload I/O intensity in bits/FLOP (1e-8=text/reasoning, 2e-6=rich multimodal) for Turyshev Gamma downlink checks. |
| earth_capex_factor | number | – | Terrestrial civil/substation CapEx multiplier (1.0=Tier-IV utility, 0.6=vertically integrated self-build). |
| grid_hub | string | – | Select live D1 wholesale electricity hub (ercot=Texas, pjm=Virginia, epex=Europe) or canonical $115/MWh baseline. |
| grid_price_usd_mwh | number | – | Custom terrestrial grid tariff in USD/MWh (overrides grid_hub if provided). |
| hw | string | – | Orbital AI hardware stack profile. |
| launch_vehicle | string | – | Heavy-lift launch vehicle mass and price model. |
| loop_temp_c | number | – | Radiator coolant loop temperature in Celsius (80C optimal for commercial silicon; 95C for Terafab 370K). |
| power_mw | number | – | Target cluster electrical capacity in megawatts (1 to 100,000 MW). |
| storm_mode | string | – | Space weather telemetry source: live NOAA/GOES streams or deterministic G0/G3/G5 stress profile. |
No output schema declared.
No examples provided.
get_ocei_history_and_live_grids ~125
Retrieves empirical Cloudflare D1 time-series snapshots of OCEI-Spot, true 60-minute settlement TWAP, rolling 30-day covenant availability, and all 3 live wholesale spot electricity hubs (ERCOT Texas, PJM Virginia, EPEX Europe). Use this tool for historical trend comparison, SLA/insurance covenant auditing, or live electricity price lookup.
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | Lookback window in hours (1 to 720 hours / 30 days). |
| limit | number | – | Maximum number of D1 snapshot rows to return. |
No output schema declared.
No examples provided.
solve_optimal_workload_allocation ~248
Multi-shell percentage constraint solver for cluster schedulers (SkyPilot, Kubernetes, SOOS). Outputs exact percentage splits across 650 km Dawn-Dusk SSO, 320 km self-cleaning VLEO Edge, and Terrestrial Spot Grids based on workload latency SLA, Turyshev downlink intensity (bits/FLOP), space weather, and electricity price. Returns optimal_split_pct and blended $/1M token cost.
| Name | Type | Req | Description |
|---|---|---|---|
| comm_intensity_bits_per_flop | number | – | Turyshev I/O intensity (bits/FLOP); automatically shifts downlink-bound multimodal workloads to Earth. |
| grid_hub | string | – | Live wholesale electricity hub (ercot, pjm, epex) or $115/MWh baseline. |
| grid_price_usd_mwh | number | – | Spot grid price in USD/MWh; if omitted, uses grid_hub. |
| max_latency_ms | number | – | Maximum acceptable one-way network latency in ms (<=6 ms prioritizes 320 km VLEO). |
| storm_mode | string | – | Space weather regime. |
| workload_type | string | – | AI workload class controlling latency sensitivity and batchability. |
No output schema declared.
No examples provided.
How do I install the OCEI v2.2 Orbital Compute & Arbitrage Oracle MCP server?
OCEI v2.2 Orbital Compute & Arbitrage Oracle is a hosted endpoint at https://orbitcompute.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 · orbitcompute.ai
claude mcp add --transport http mr-didi-mcp-ocei-oracle 'https://orbitcompute.ai/mcp'
What is the OCEI v2.2 Orbital Compute & Arbitrage Oracle MCP server?
OCEI v2.2 Orbital Compute & Arbitrage Oracle is an MCP server listed in the public MCP registry as io.github.Mr-Didi/mcp-ocei-oracle. Attested orbital AI compute physics, NOAA space-weather & $/MTok arbitrage oracle (OCEI v2.2). This page covers its hosted endpoint (https://orbitcompute.ai/mcp).
Is the OCEI v2.2 Orbital Compute & Arbitrage Oracle MCP server safe to use?
OCEI v2.2 Orbital Compute & Arbitrage Oracle scores 59 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 OCEI v2.2 Orbital Compute & Arbitrage Oracle MCP server expose?
OCEI v2.2 Orbital Compute & Arbitrage Oracle exposes 4 tools: evaluate_orbital_compute_regime, compute_arbitrage_dispatch, solve_optimal_workload_allocation, get_ocei_history_and_live_grids. Their descriptions and schemas cost roughly 1,108 tokens of context every time the server is loaded.
Does the OCEI v2.2 Orbital Compute & Arbitrage Oracle MCP server require authentication?
No. We connected to OCEI v2.2 Orbital Compute & Arbitrage Oracle without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the OCEI v2.2 Orbital Compute & Arbitrage Oracle MCP server still maintained?
OCEI v2.2 Orbital Compute & Arbitrage Oracle 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 OCEI v2.2 Orbital Compute & Arbitrage Oracle MCP server?
VerifyMCP ran 12 checks on OCEI v2.2 Orbital Compute & Arbitrage Oracle, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about OCEI v2.2 Orbital Compute & Arbitrage Oracle: Authorization. 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.