{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_9c965df4vyra","handle":"gemini-media-mcp","url":"https://wellknown.network/agents/gemini-media-mcp","links":{"self":"https://wellknown.network/agents/gemini-media-mcp/record.json","html":"https://wellknown.network/agents/gemini-media-mcp","markdown":"https://wellknown.network/agents/gemini-media-mcp/record.md","api":"https://wellknown.network/api/v1/agents/gemini-media-mcp","status":"https://wellknown.network/api/v1/agents/gemini-media-mcp/status","claim":"https://wellknown.network/agents/gemini-media-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/gemini-media-mcp/claim.json","badge":"https://wellknown.network/agents/gemini-media-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/gemini-media-mcp/history","tools":"https://wellknown.network/api/v1/agents/gemini-media-mcp/tools"},"ard":{"identifier":"urn:air::server:gemini-media-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"gemini-media-mcp","summary":"Plan, generate, compose, and edit images and video with Gemini image models, Veo 3.1, and Gemini Omni, with a cost estimate before every call and an optional Gemini 4 Argon director that checks each take against your notes","description":"# Gemini Media MCP\n\nPlan, generate, compose, and edit images and video with Gemini image models, Veo 3.1, and Gemini Omni, with a cost estimate before every call and an optional Gemini 4 Argon director that checks each take against your notes.\n\n## What it does\n\n- **Plan:** `plan_generation` ranks tool and model options for an intent with costs, and generates nothing.\n- **Generate:** images with Gemini, video with Veo 3.1, fast video with Omni.\n- **Compose:** storyboards, multi-beat reels, transitions between stills, bridges between clips.\n- **Edit and extend:** conversational video edits, seamless scene extension, loop and extend.\n- **Direct:** optional `director_notes` have Gemini 4 Argon turn your notes into checks, review each take, and retake on a clear fail.\n- **Cost-aware:** any call runs `dry_run` for a quote; real runs report metered cost and its pricing source.\n\n## Quick start\n\n```bash\nuvx gemini-media-mcp setup\n```\n\nThe `setup` wizard walks you through the whole onboarding flow end-to-end:\n\n1. Pick a credential mode: **Gemini API** (images + Omni video, easier to set up) or **Vertex AI** (images + Veo and Omni video, adds GCS output and Vertex-only features).\n2. Enter your API key, or your Google Cloud project plus a service account JSON (file path or inline paste).\n3. Choose where generated media should be written (defaults to `~/gemini-media`).\n4. Optionally set a `VIDEO_GCS_BUCKET` for large video output, and auto-populate `GCS_ALLOWED_BUCKETS`.\n5. Validate your credentials with a live check (constructs a Google GenAI client and lists models to confirm the key/credentials actually authenticate). Validation failures are non-fatal — you can continue anyway.\n6. Print a ready-to-paste Claude Desktop JSON block. On macOS, the wizard can also merge the block directly into `~/Library/Application Support/Claude/claude_desktop_config.json` (existing servers are preserved and the prior file is backed up to `.bak`).\n\nFor scripted use, all prompts can be supplied …","publisher":null,"homepage":"https://github.com/CxOAGI/gemini-media-mcp","repository":"https://github.com/CxOAGI/gemini-media-mcp","version":"0.1.13","license":"Apache License\n                                   Version 2.0, …","protocols":["mcp"],"tags":["argon","gemini","gemini-omni","image-generation","mcp","model-context-protocol","veo","vertex-ai","video-generation"],"pricing":null,"endpoints":[{"url":"pypi:gemini-media-mcp","type":"package_pypi","auth":null,"probeable":false,"listed":true}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"commerce.pricing","name":"Pricing & Quotes","confidence":1,"provenance":"derived"},{"slug":"media.image-generation","name":"Image Generation","confidence":1,"provenance":"declared"},{"slug":"media.video-generation","name":"Video Generation","confidence":1,"provenance":"declared"}],"categories":["commerce","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"gemini-media-mcp","registry":"pypi","observedAt":"2026-11-09T05:25:01.911Z","publishedAt":"2026-10-28T20:33:24.384043Z","latestVersion":"0.1.13"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"gemini-media-mcp","url":"https://pypi.org/project/gemini-media-mcp/","firstSeenAt":"2026-09-09T16:23:31.429Z","fetchedAt":"2026-11-09T05:24:03.609Z","normalizedAt":"2026-11-09T05:24:03.609Z"}]},"firstSeenAt":"2026-09-09T16:23:31.429Z","updatedAt":"2026-11-09T05:25:01.911Z"}