Index / MCP servers / eYKON Intelligence

eYKON Intelligence MCP server

eYKON Intelligence is a remote MCP server that gives an AI agent 24 tools, among them expand_actor_network, query_agent_reports, query_aircraft. It answers at https://eykon.ai/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.

Status
Answering
Tools
24
Official
yes, served from eykon.ai
Reliability
6 of 6 checks
Response time
101 ms
Transport
streamable HTTP
Last checked
19 October 2026

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

Description as the publisher wrote it.

The 24 tools eYKON Intelligence offers

ToolWhat it does
expand_actor_networkWalk the fleet kinship graph from a seed entity. Returns the nodes and edges within N hops.
Inputs: entity_id, hops
query_agent_reportsRetrieve recent intelligence reports generated by eYKON Sub-Agents. Returns structured reports with severity, narrative, and entity references.
Inputs: domain, severity, hours
query_aircraftQuery ADS-B aircraft positions within a geographic area.
Inputs: lat_min, lat_max, lon_min, lon_max, altitude_min, altitude_max
query_airportsQuery 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. Ea
Inputs: lat_min, lat_max, lon_min, lon_max, iso_country, include_minor
query_calibrationeYKON'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 uns
Inputs: feature, track, window_days
query_conflictsQuery armed-conflict events (GDELT-backed, with ACLED fallback when licensed) by region / date / event type / actor.
Inputs: country, lat_min, lat_max, lon_min, lon_max, days
query_convergencesRecent convergence_events (anomaly-of-anomalies) with synthesis and contributing anomaly IDs.
Inputs: hours
query_dark_contact_eventsDark-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:
Inputs: status, limit
query_entitiesSearch the entities registry (vessels, operators, owners, flags, ports, refineries, mines).
Inputs: q, entity_type, limit
query_minesQuery 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 / Pr
Inputs: lat_min, lat_max, lon_min, lon_max, commodity, dev_stat
query_nightlightsQuery 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 baselin
Inputs: mode, event_type, facility_type, country, facility_name, days
query_pipelinesQuery 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 st
Inputs: lat_min, lat_max, lon_min, lon_max, fuel, status
query_portsQuery 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
Inputs: lat_min, lat_max, lon_min, lon_max, harbor_size, limit
query_posture_scoresMost recent posture_scores rows per theatre. Returns composite + 5-domain sub-scores.
Inputs: theatre_slug, limit
query_power_plantsQuery 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 r
Inputs: lat_min, lat_max, lon_min, lon_max, fuel, status
query_precursor_matchesNearest precursor_library entries for the given theatre, by cosine similarity.
Inputs: theatre_slug, top_k, event_type
query_refineriesQuery 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
Inputs: lat_min, lat_max, lon_min, lon_max, country, limit
query_regime_shiftsActive regime shifts (30d-vs-60d test) with p-values and effect sizes.
Inputs: region
query_shadow_fleet_leadsRanked 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 def
Inputs: commodity, min_score, limit
query_thermal_anomaliesQuery 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 ("therma
Inputs: mode, facility_type, country, facility_name, days, min_detections
query_vesselsQuery AIS vessel positions within a geographic area and time window. Returns vessel name, MMSI, type, position, speed, heading, destination.
Inputs: lat_min, lat_max, lon_min, lon_max, hours
query_weatherQuery current weather conditions for a specific location (Open-Meteo).
Inputs: latitude, longitude
run_chokepoint_scenarioRun 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.
Inputs: chokepoint, closure_type, duration_days, diversion_lag_hours, assumptions
run_sanctions_wargameRun a sanctions propagation scenario.
Inputs: sanctioning_bodies, preset, target_entities, depth

Add eYKON Intelligence to your AI client

Every block below points at https://eykon.ai/api/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http eykon-intelligence https://eykon.ai/api/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "eykon-intelligence": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://eykon.ai/api/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "eykon-intelligence": {
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "eykon-intelligence": {
      "type": "http",
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "eykon-intelligence": {
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "eykon-intelligence": {
      "serverUrl": "https://eykon.ai/api/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "eykon-intelligence": {
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: eYKON Intelligence
version: 0.0.1
schema: v1
mcpServers:
  - name: eYKON Intelligence
    type: streamable-http
    url: https://eykon.ai/api/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "eykon-intelligence": {
      "httpUrl": "https://eykon.ai/api/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "eykon-intelligence": {
      "type": "http",
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "eykon-intelligence": {
      "url": "https://eykon.ai/api/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Feykon.ai%2Fapi%2Fmcp&type=streamable_http&id=eykon-intelligence&name=eYKON%20Intelligence

Is eYKON Intelligence up right now?

It answered our last check on 19 October 2026 in 101 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to eYKON Intelligence

Questions about eYKON Intelligence

Is there an official eYKON Intelligence MCP server?

Yes. It is published by eykon.ai and served from eykon.ai, the vendor's own domain: https://eykon.ai/api/mcp.

How many tools does eYKON Intelligence have?

24, as returned by the server's own tools/list on 10 September 2026: expand_actor_network, query_agent_reports, query_aircraft, query_airports, query_calibration, query_conflicts, query_convergences, query_dark_contact_events, and 16 more.

Is eYKON Intelligence down?

It answered our last check on 19 October 2026 in 101 ms. Over 6 checks since 10 September 2026 it answered 6.

How do I add eYKON Intelligence to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://eykon.ai/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does eYKON Intelligence need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: ai.eykon. Endpoint host: eykon.ai. ARD identifier: urn:air:ai.eykon:mcp:intelligence. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.