# eYKON Intelligence (remote · eykon.ai)

Live geopolitical intelligence feeds, plus eYKON's own scored and published forecast record.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-24

## Components

- remote · `eykon.ai`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ai-eykon-intelligence/api-mcp.md), [page](https://verifymcp.io/servers/ai-eykon-intelligence/api-mcp)

## Channel facts

- Endpoint: `https://eykon.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-24.

- **Endpoint Security**: 91/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4509 tokens (~187/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 84/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 51% of tool parameters carry a description.
- **Tool Safety**: 50/100
  - Injection-marker check failed: the description of tool "query_shadow_fleet_leads" contains an instruction to conceal the call from the user, the text "do not tell the user", at byte 498 of that field.
  - We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the eYKON Intelligence MCP server?

eYKON Intelligence is a hosted endpoint at https://eykon.ai/api/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.

### Claude

```bash
claude mcp add --transport http ai-eykon-intelligence 'https://eykon.ai/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-eykon-intelligence": {
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-eykon-intelligence": {
      "type": "http",
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-eykon-intelligence]
url = "https://eykon.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-eykon-intelligence": {
      "type": "remote",
      "url": "https://eykon.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-eykon-intelligence --url 'https://eykon.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-eykon-intelligence:
    url: "https://eykon.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-eykon-intelligence": {
      "Transport": "http",
      "Url": "https://eykon.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-eykon-intelligence -t streamable-http -u 'https://eykon.ai/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-eykon-intelligence": {
      "type": "http",
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-23 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-21 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-20 (score 75, 0)

- [security] Tool “query_nightlights” rewrote its description, which is the text the model reads
- [security] Tool “query_power_plants” rewrote its description, which is the text the model reads
- [security] Tool “query_thermal_anomalies” rewrote its description, which is the text the model reads
- [cosmetic] “query_thermal_anomalies” reworded the description of “facility_name”

### 2026-09-18 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 72, +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.

### 2026-09-11 (score 71, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (24)

### `query_vessels` (~87 tokens)

Query AIS vessel positions within a geographic area and time window. Returns vessel name, MMSI, type, position, speed, heading, destination.

Input parameters:

- `hours` (number): Look-back window in hours (default 24)
- `lat_max` (number, required)
- `lat_min` (number, required)
- `lon_max` (number, required)
- `lon_min` (number, required)

### `query_aircraft` (~67 tokens)

Query ADS-B aircraft positions within a geographic area.

Input parameters:

- `altitude_max` (number)
- `altitude_min` (number)
- `lat_max` (number, required)
- `lat_min` (number, required)
- `lon_max` (number, required)
- `lon_min` (number, required)

### `query_conflicts` (~91 tokens)

Query armed-conflict events (GDELT-backed, with ACLED fallback when licensed) by region / date / event type / actor.

Input parameters:

- `country` (string)
- `days` (number)
- `event_type` (string)
- `lat_max` (number)
- `lat_min` (number)
- `lon_max` (number)
- `lon_min` (number)

### `query_refineries` (~178 tokens)

Query oil refineries from OpenStreetMap (canonical refinery tags only — petroleum_refinery, oil_refinery, refinery). ~700 facilities globally, each with name, operator, product, capacity (when tagged), country, city. Use for questions like "refineries in Saudi Arabia", "oil refining capacity on the Gulf Coast", "European refineries near Russian crude pipelines". Pass country to slice (ISO2 code or country name).

Input parameters:

- `country` (string): ISO 3166-1 alpha-2 (e.g. "SA") or country-name substring (e.g. "Saudi"). Filter optional.
- `lat_max` (number, required)
- `lat_min` (number, required)
- `limit` (number): Default 50, max 500.
- `lon_max` (number, required)
- `lon_min` (number, required)

### `query_mines` (~330 tokens)

Query mineral deposits from the USGS Mineral Resources Data System (MRDS — public-domain US Government, ~304k records globally, archival snapshot frozen at 2011). Each row carries site name, development status (Producer / Past Producer / Prospect / Occurrence / Plant), commodities (commod1/2/3 + commodities array), country, state, deposit type. Default returns only Producer / Past Producer / Plant rows with a known commod1 (significant sites); pass include_minor=true for prospects and occurrences. Use for questions like "lithium mines in Chile", "rare-earth deposits worldwide", "active copper producers in Peru". Pass commodity to filter on the commodities[] array (case-sensitive, e.g. "Copper", "Lithium", "Rare Earths").

Input parameters:

- `commodity` (string): Commodity name to match in the commodities array (e.g. "Copper", "Lithium", "Gold", "Rare Earths", "Uranium"). Case-sensitive.
- `country` (string): ISO 3166-1 alpha-2 (e.g. "CL") or country-name substring. Filter optional.
- `dev_stat` (string): Producer | Past Producer | Prospect | Occurrence | Plant | Unknown. Filter optional.
- `include_minor` (boolean): If true, drops the default significant-sites filter and returns prospects/occurrences too.
- `lat_max` (number, required)
- `lat_min` (number, required)
- `limit` (number): Default 50, max 500.
- `lon_max` (number, required)
- `lon_min` (number, required)

### `query_power_plants` (~332 tokens)

Query unit-level power plants from the Global Energy Monitor — Global Integrated Power Tracker (GIPT). ~127k operating units worldwide spanning coal, oil/gas, nuclear, geothermal, bioenergy, utility-scale solar, wind, and hydropower. Each row carries plant name, fuel type, capacity (MW), status, start year, country, owner. Use for questions like "nuclear plants in France above 1 GW", "coal capacity in India", "operating bioenergy plants in Brazil". Pass include_minor=true to bypass the operating-only filter (e.g. to include proposed/retired). Pass fuel to slice to a single fuel_type. The registry is a bulk-loaded snapshot: every result carries `snapshot` (load date, age in days, refresh interval); when snapshot.is_stale is true, a snapshot_note says so — state the load date and never describe a unit's status as current.

Input parameters:

- `fuel` (string): utility-scale solar | wind | hydropower | geothermal | bioenergy | nuclear | coal | oil/gas
- `include_minor` (boolean): If true, drops the default operating-only filter and capacity floor.
- `lat_max` (number, required)
- `lat_min` (number, required)
- `limit` (number): Default 50, max 500.
- `lon_max` (number, required)
- `lon_min` (number, required)
- `min_capacity_mw` (number): Minimum capacity in MW
- `status` (string): operating (default) | construction | proposed | retired | cancelled | shelved | mothballed

### `query_pipelines` (~316 tokens)

Query gas pipelines (GEM GGIT), oil/NGL pipelines (GEM GOIT), and LNG terminals (GEM GGIT) in one call. Returns a mixed list — each row has infra_subtype=pipeline_gas|pipeline_oil|lng_terminal so you can disambiguate. Pipeline rows carry start/end country, length, capacity (bcm/y for gas, BOEd or raw bpd for oil), status, owner, route accuracy. LNG terminals carry facility_type=import|export, capacity in mtpa, country. Use for questions like "Russian gas pipelines into Europe", "LNG export terminals in Qatar", "Trans-Alaska oil pipeline status", "Keystone XL". Pass fuel=gas or fuel=oil to slice to one type. Pass include_minor=true to bypass the operating-only default.

Input parameters:

- `facility_type` (string): For LNG terminals only: import | export.
- `fuel` (string): "gas" (returns gas pipelines + LNG terminals) | "oil" (returns oil pipelines only). Omit to return all three.
- `include_minor` (boolean): If true, drops the default operating-only filter.
- `lat_max` (number, required)
- `lat_min` (number, required)
- `limit` (number): Default 50, max 500.
- `lon_max` (number, required)
- `lon_min` (number, required)
- `status` (string): operating (default) | construction | proposed | retired | cancelled | shelved | mothballed

### `query_airports` (~204 tokens)

Query airports from OurAirports. Default returns the ~7,500 commercially-significant airports (large airports + medium airports with scheduled service); pass include_minor=true for the full ~85k including small airfields, heliports, etc. Each row carries name, type, IATA/ICAO codes, country, municipality, elevation, scheduled_service. Use for questions like "airports near recent conflict events", "ICAO code for Heathrow", "all scheduled-service airports in Ukraine".

Input parameters:

- `include_minor` (boolean): If true, returns all 85k airports including heliports, small airfields, closed.
- `iso_country` (string): Two-letter ISO country code (e.g. "FR", "US"). Filter optional.
- `lat_max` (number, required)
- `lat_min` (number, required)
- `limit` (number): Default 50, max 500.
- `lon_max` (number, required)
- `lon_min` (number, required)

### `query_ports` (~165 tokens)

Query commercial seaports from the NGA World Port Index (~3,800 ports worldwide). Each row carries port name, country, harbor size (Large/Medium/Small/Very Small), harbor type, shelter rating, channel depth in metres, repair facilities. Use for questions like "ports near Bab-el-Mandeb", "deepwater ports in West Africa", "all large harbors in the Mediterranean". Pass harbor_size to slice to a single tier.

Input parameters:

- `harbor_size` (string): Large | Medium | Small | Very Small. Filter optional.
- `lat_max` (number, required)
- `lat_min` (number, required)
- `limit` (number): Default 50, max 500.
- `lon_max` (number, required)
- `lon_min` (number, required)

### `query_weather` (~36 tokens)

Query current weather conditions for a specific location (Open-Meteo).

Input parameters:

- `latitude` (number, required)
- `longitude` (number, required)

### `query_thermal_anomalies` (~710 tokens)

Query NASA FIRMS satellite thermal anomalies (VIIRS 375m + MODIS 1km, near-real-time, ~3h latency). Two modes. mode="facilities" (default) reads the pre-aggregated per-facility-per-day rollup — use it for facility-centric questions ("thermal anomalies at Russian refineries this week", "which Gulf refineries lit up", "anything at the Kirishi refinery"). Filter by country, facility_type (refinery | power_plant), facility_name, days. Returns per facility: total detections, max FRP (fire radiative power, MW), nearest detection distance in km, and the monitoring radius used. mode="raw" reads individual detections inside a lat/lon box — use it for geographic questions not anchored to a monitored facility. CRITICAL INTERPRETATION RULES — a FIRMS detection is a SATELLITE HOT PIXEL, nothing more. It is NOT a confirmed fire, NOT a strike, NOT an outage. Most detections at oil and gas infrastructure are ROUTINE GAS FLARES that burn every single day. Attributing a detection to a strike, an attack, an explosion or a production halt is INFERENCE and must be labelled as inference, corroborated with other sources (conflict events, agent reports, news), and never stated as fact. Equally, ABSENCE OF DETECTION DOES NOT MEAN ABSENCE OF FIRE — cloud cover, smoke, and satellite overpass timing routinely hide real fires. Every response carries a `coverage` block: ingest is REGIONAL — 8 boxes (Russia / Ukraine, Arabian Gulf, Europe, East Asia, South Asia, Southeast Asia, North America (east), North America (west)), not global — so facilities outside those boxes report zero detections because they are NOT WATCHED, not because nothing burned. Always read `coverage` before characterising a zero result, and tell the user which of the two it is.

Input parameters:

- `country` (string): facilities mode: country-name substring (e.g. "Russia", "Saudi", "Ukraine"). Names are full English, NOT ISO codes. Filter optional.
- `days` (number): Look-back window in days ending today (default 7, max 30). Note the archive is shallow — check coverage.days_with_data.
- `facility_name` (string): facilities mode: facility-name substring (e.g. "Kirishi", "Ras Tanura"). Filter optional.
- `facility_type` (string): facilities mode: refinery | power_plant. Filter optional.
- `lat_max` (number): raw mode: required.
- `lat_min` (number): raw mode: required.
- `limit` (number): Default 50, max 500.
- `lon_max` (number): raw mode: required.
- `lon_min` (number): raw mode: required.
- `min_detections` (number): facilities mode: minimum total detections over the window (default 1, i.e. only facilities that registered something). Pass 0 to include quiet facilities and see what was watched-but-silent.
- `min_frp` (number): raw mode: minimum fire radiative power in MW. Higher FRP = more energetic hot pixel, but still not a fire type.
- `mode` (string): "facilities" (default, pre-aggregated per monitored facility) | "raw" (individual detections in a bounding box).

### `query_nightlights` (~662 tokens)

Query NASA Black Marble night-lights (VIIRS VNP46A2, ~500 m): moonlight/atmosphere-corrected nighttime radiance sampled nightly at every FIRMS-watched facility, plus significance events judged against each facility's OWN clear-night baseline. Two modes. mode="events" (default) reads SITE-LEVEL significance events — went_dark_lights (a habitually-lit facility dark across several consecutive CLEAR nights: the outage signal), surge (materially brighter than its own norm), first_light (a reliably-dark facility lights up). Use it for "which power stations went dark last week", "unusual lighting activity in Kuwait". mode="radiance" reads the per-facility nightly radiance rollup — use it for baseline questions ("how bright is Bandar Abbas at night", "clear-night trend at Az Zour"). CRITICAL INTERPRETATION RULES — RADIANCE IS NOT POWER STATE. A dark pixel is not a confirmed outage: cloud, snow, moon geometry and the ~500 m footprint all hide light, so went_dark_lights requires SUSTAINED absence across multiple confidently-CLEAR nights and is still an inference, never a verdict. Judgements use confident_clear observations ONLY (cloud scatters city light back at the sensor — cloudy readings average ~100x brighter and would fake both surges and collapses). ABSENCE OF A ROW IS ABSENCE OF A LOOK, never darkness. Counts are per PHYSICAL SITE, not per registry row (one plant = many generating-unit rows at identical coordinates). LATENCY: NASA publishes VNP46A2 in stages, typically ~1-2 WEEKS behind — every response carries a coverage block with newest_night and lag_days; answers describe that week, NOT last night, and you must say so. Thermal (FIRMS) and night-lights measure DIFFERENT PHYSICS — infrared heat vs visible emitted light — but they are NOT independent sensors: both are NASA VIIRS-family, and the same clouds and overpass timing blind both. Agreement between them (e.g. a FIRMS went_dark and a went_dark_lights at the same facility) is stronger evidence than either alone,…

Input parameters:

- `country` (string): Country-name substring (e.g. "Kuwait", "Saudi"). NOTE: attribution is dense for power plants but sparse for refineries — prefer facility_name for refineries.
- `days` (number): Look-back window in days ENDING AT THE NEWEST DATA NIGHT (not today — see coverage.lag_days). Default 14, max 60.
- `event_type` (string): events mode: went_dark_lights | surge | first_light. Filter optional.
- `facility_name` (string): Facility/site-name substring (e.g. "Az Zour", "Bandar Abbas"). Filter optional.
- `facility_type` (string): radiance mode: refinery | power_plant. Filter optional.
- `limit` (number): Default 50, max 500.
- `mode` (string): "events" (default, site-level significance) | "radiance" (per-facility nightly rollup).

### `query_agent_reports` (~88 tokens)

Retrieve recent intelligence reports generated by eYKON Sub-Agents. Returns structured reports with severity, narrative, and entity references.

Input parameters:

- `domain` (string): air_traffic, maritime, conflict_security, energy_infrastructure, satellite_imagery
- `hours` (number): Look-back hours (default 48)
- `severity` (string): low | medium | high | critical (minimum)

### `query_posture_scores` (~43 tokens)

Most recent posture_scores rows per theatre. Returns composite + 5-domain sub-scores.

Input parameters:

- `limit` (number)
- `theatre_slug` (string)

### `query_convergences` (~42 tokens)

Recent convergence_events (anomaly-of-anomalies) with synthesis and contributing anomaly IDs.

Input parameters:

- `hours` (number): Look-back hours (default 24)

### `query_shadow_fleet_leads` (~228 tokens)

Ranked shadow-fleet vessel leads, scored from silence relative to the OWN observed reporting cadence of each vessel (14-day baseline), vanished-under-way, and flag-of-convenience. Vessels without a cadence baseline yet are unscored, not defaulted. Each lead carries silence_hours = hours since its last AIS fix, measured against the data clock. NOTE: the commodity argument is accepted but NOT applied — vessel type is known for under 1% of the tracked fleet, so all values return the same list; do not tell the user results were filtered by commodity. Coverage IS gated: vessels last seen in a coverage box that has itself been silent >12h are VOID, never ranked; the response carries per-box coverage state (live/stale/dead) you should relay when a corridor the user asks about is dark.

Input parameters:

- `commodity` (string): oil | lng | grain — ACCEPTED BUT NOT APPLIED, see the tool description
- `limit` (number)
- `min_score` (number): Minimum composite score (default 0.4)

### `query_dark_contact_events` (~204 tokens)

Dark-contact EVENTS from the Shadow Fleet board — resolvable observations with a lifecycle, not a leads snapshot. An event opens when a vessel goes silent >=12x its OWN 14-day cadence inside a live coverage box, and resolves within 72 h as: reappeared (a newer fix arrived — positive, feed-wide observation), still_dark (NOT RE-OBSERVED by our coverage — a statement about the instrument, never proof the transponder was off; say "not re-observed", never "confirmed dark"), or void (the coverage box died mid-event; neither a hit nor a miss). Response carries per-box coverage state and open/24h resolution tallies. Use this for "what went dark / what came back" questions; use query_shadow_fleet_leads for the current ranked list.

Input parameters:

- `limit` (number): Max events (default 50)
- `status` (string): open | resolved | void (omit for all)

### `query_calibration` (~244 tokens)

eYKON's own forecast record: Brier and log-loss per TRACK over a window. Three tracks never blend — house (eYKON's own published forecasts), machine (sensor observables) and creator. Each is returned separately with resolved, scored and unscored counts; "scored" is the real n. Unscored rows are excluded, never counted as zero. There is deliberately no combined figure.

Input parameters:

- `feature` (string): posture_shift | conflict_escalation | trade_flow | energy_stress
- `track` (string): house | machine | creator. Omit to get every track, reported separately.
- `window_days` (number): 7 | 30 | 90 (default 90). 90 is the shortest window where the house track carries evidence — n=42 at 90d against 12 at 30d and 6 at 7d — and skill is measured against the track's own base rate INSIDE…

### `query_precursor_matches` (~62 tokens)

Nearest precursor_library entries for the given theatre, by cosine similarity.

Input parameters:

- `event_type` (string)
- `theatre_slug` (string, required): One of the six theatres eYKON computes posture for.
- `top_k` (number): Default 3

### `run_chokepoint_scenario` (~123 tokens)

Run a chokepoint closure scenario (same model as the Chokepoint Simulator). Returns a computed projection; nothing is persisted on this path. A MODEL, not an observation.

Input parameters:

- `assumptions` (object)
- `chokepoint` (string, required): hormuz | bab-el-mandeb | malacca | bosphorus | suez | panama
- `closure_type` (string, required): partial_50 | full | transit_tax_30
- `diversion_lag_hours` (number)
- `duration_days` (number, required)

### `run_sanctions_wargame` (~59 tokens)

Run a sanctions propagation scenario.

Input parameters:

- `depth` (number): 1 | 2 | 3
- `preset` (string, required)
- `sanctioning_bodies` (array, required)
- `target_entities` (array, required)

### `query_regime_shifts` (~42 tokens)

Active regime shifts (30d-vs-60d test) with p-values and effect sizes.

Input parameters:

- `region` (string): Theatre slug or label

### `query_entities` (~52 tokens)

Search the entities registry (vessels, operators, owners, flags, ports, refineries, mines).

Input parameters:

- `entity_type` (string)
- `limit` (number)
- `q` (string, required)

### `expand_actor_network` (~56 tokens)

Walk the fleet kinship graph from a seed entity. Returns the nodes and edges within N hops.

Input parameters:

- `entity_id` (string, required)
- `hops` (number): 1 | 2 | 3 (default 2)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-eykon-intelligence/api-mcp#diagnostics

## Score history

- 2026-09-24: 77
- 2026-09-23: 77
- 2026-09-22: 76
- 2026-09-21: 76
- 2026-09-20: 75
- 2026-09-19: 75
- 2026-09-18: 75
- 2026-09-17: 74
- 2026-09-16: 74
- 2026-09-15: 73
- 2026-09-14: 73
- 2026-09-13: 72
- 2026-09-12: 72
- 2026-09-11: 71
- 2026-09-10: 71

## Common questions

### What is the eYKON Intelligence MCP server?

eYKON Intelligence is an MCP server listed in the public MCP registry as ai.eykon/intelligence. Live geopolitical intelligence feeds, plus eYKON's own scored and published forecast record. This page covers its hosted endpoint (https://eykon.ai/api/mcp).

### Is the eYKON Intelligence MCP server safe to use?

eYKON Intelligence scores 77 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 eYKON Intelligence MCP server expose?

eYKON Intelligence exposes 24 tools: query_vessels, query_aircraft, query_conflicts, query_refineries, query_mines, and 19 more. Their descriptions and schemas cost roughly 4,421 tokens of context every time the server is loaded.

### Does the eYKON Intelligence MCP server require authentication?

Yes. eYKON Intelligence asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the eYKON Intelligence MCP server still maintained?

eYKON Intelligence is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://eykon.ai/api/mcp
- Website: https://eykon.ai/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-eykon-intelligence/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-eykon-intelligence/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-eykon-intelligence/api-mcp