Eikino
Server Details
Geolocate photos or video frames and check media for AI generation signs via API key.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
Each tool targets a clearly different capability: AI-generation detection (detect_ai_media), geolocation (locate_media), and account credit balance (get_credits). There is no shared resource or overlapping action space that could cause misselection, and descriptions reinforce the boundaries.
All three names follow a consistent snake_case verb_noun pattern (detect_ai_media, get_credits, locate_media). The verb choice also communicates intent well, so the set reads as a coherent family.
Three tools is a tight, purposeful surface for a narrow forensic-media API — each earns its place. It sits slightly on the thin side (no batch or history operations), but nothing feels redundant.
The core workflows (detect AI generation, geolocate footage, check remaining checks) are covered with no dead ends in the primary flow. Minor gaps exist around retrieving past results, batch submission, or credit usage history, which agents would have to work around.
Available Tools
3 toolsdetect_ai_mediaCheck if video frames or media were AI-generatedAInspect
Analyze 1–6 still frames from a video (or a single image) for signs of AI generation (Sora, Veo, Kling, Runway, Seedance, etc.) vs. real camera footage, returning likelihood (low/medium/high), 0–100 score, summary, AI artifacts and real-footage signs. Uses 1 check.
Inputs: markers, duration, image_url, image_urls, +1 more.
get_creditsCheck remaining Eikino checksARead-onlyIdempotentInspect
Return the number of available AI checks remaining on this Eikino account. Free.
Inputs: no named parameters.
locate_mediaFind where a photo or video was takenAInspect
Estimate where a photo or 1–4 video frames were filmed, returning place name, country, coordinates, confidence, uncertainty radius in km, visual clues and alternatives. Uses 1 check when a location is found; 0 checks if unknown or failed.
Inputs: hint, kind, taken, image_url, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Check whether a video was generated by AI (Sora, Veo, Kling, HeyGen and others).
Verify photos are real camera captures, not AI: C2PA and RAW+JPEG forensics. OAuth or API key.
Locate photos from visual clues and assess location claims with candidates and uncertainty.
YouTube and video analysis, C2PA marking for AI images, lossless EXIF/GPS removal. Pay per call.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables detection of AI-generated content in images, videos, audio, and text via the AI or Not API. Supports media analysis tools for deepfakes, synthetic voices, and AI-written text.21MIT
- AlicenseAqualityBmaintenanceEnables AI agents to analyze images from a URL, local path, or Base64 string and determine whether they are AI-generated, including detection of signatures from Flux, Midjourney, DALL·E, and Stable Diffusion. Also inspects cryptographic C2PA provenance manifests, signing certificate authorities, and camera EXIF metadata without requiring API keys or accounts.266 npmMIT
- FlicenseNot gradedqualityDmaintenanceA local GeoGuessr-for-real-life: reads EXIF GPS and reasons over visual clues using a local uncensored vision-language model + a reasoning model — no cloud, no API keys, nothing uploaded.1-
- AlicenseNot gradedqualityCmaintenanceEnables an agent to determine whether an image is AI-generated, edited, or captured by reading signed C2PA Content Credentials first and falling back to labelled pixel-level forensic heuristics (noise, ELA, spectral, colour, EXIF) only when no manifest exists. Runs fully offline with no API keys or cloud calls, and can report tampering when pixels no longer match a signed hash.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.