Eversince
Creative agent that plans and executes across image, video, audio, and motion graphics.
Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only
What it can do
- Create Project: Create a new creative project. Provide a natural-language brief describing what to produce. The agent plans, generates, and iterates based on this input. Spends credits.
- List Projects: List projects owned by the authenticated account, most recent first.
- Discover Projects: List studio-created projects that can be adopted for API management.
What data it sees
Do you need an account
No: the server works without sign-in
Creative agent that plans and executes across image, video, audio, and motion graphics. Orchestrates the latest AI models and delivers standalone assets or assembled videos.
Server tool list (33)
Raw names from tools/list. Only developers need these.
| create_project | Create a new creative project. Provide a natural-language brief describing what to produce. The agent plans, generates, and iterates based on this input. Spends credits. |
| list_projects | List projects owned by the authenticated account, most recent first. |
| discover_projects | List studio-created projects that can be adopted for API management. |
| adopt_project | Adopt a studio project for API management (enables programmatic control). |
| get_project | Get current project status, agent message, timeline summary, and result links when available. |
| list_project_assets | List all generated assets (images, videos, audio) for a project. |
| get_project_timeline | Get the full timeline structure of the active variation, including scenes, generations, overlays, and audio tracks. |
| list_project_messages | List the conversation history between the user and the agent for a project. Pagination uses cursor IDs (before/after), not offsets. |
| send_project_message | Send feedback or a follow-up message to the agent. The agent must be in idle state; otherwise a 400 is returned. Requires minimum 10 credits and may spend more if the agent triggers further generation. |
| list_project_variations | List all variations (A/B creative directions) for a project. |
| get_project_memory | Read the agent's working memory for a project (creative notes, plan state, asset ledger). |
| update_project_settings | Update project-level settings (mode, models, craft, title, webhook, expected_output). Timeline operations must go through send_project_message. |
| create_project_share | Create a permanent shareable link for the assembled video. Requires the project to have a rendered output. |
| cancel_project | Cancel the agent run. Already-dispatched generations complete, but the agent stops after them. |
| render_project | Render (or re-render) the active timeline to an assembled video. Spends credits (minimum 10). 4k requires Pro subscription. Rate-limited to 50 renders/day. |
| get_credits_balance | Get the current credits balance for the authenticated account. |
| list_credit_packages | List available credit packages (credits, price, purchase URL). Use when the user needs to top up. |
| list_account_skills | List account-level skills (persistent knowledge applied across all projects). |
| create_account_skill | Teach the agent persistent knowledge (brand guidelines, style rules, workflow preferences). Applied across all projects. |
| get_account_skill | Retrieve a single account-level skill by ID. |
| update_account_skill | Update an account skill — rename, edit instructions, or toggle enabled state. |
| delete_account_skill | Delete an account skill permanently. |
| get_learned_preferences | Read the agent-learned preferences (brand voice, creative patterns) accumulated across projects. |
| update_learned_preferences | Update the agent-learned preferences block and/or toggle enabled state. Provide at least one of content or enabled. |
| list_account_shares | List all public share links for the account with view counts. |
| list_models | List available image and video models with capability flags (supports_multi_shot, supports_reference_images, has_sound, etc.). For voiceover voices, use list_voices. |
| list_voices | List voiceover voices with name, gender, age, accent, style, and description. |
| create_upload | Step 1 of 3 — get a presigned R2 URL. Step 2 (NOT an MCP tool) is a direct HTTP PUT of the file bytes to the returned upload_url, with the returned headers and matching content_type. Step 3 is confirm_upload with the r2_key. Supported types: image (jpeg/png/webp, ≤10MB), video (mp4/webm/mov/avi, ≤500MB), audio (mp3/wav/m4a, ≤50MB). |
| confirm_upload | Step 3 of 3 — finalize after the PUT (step 2) succeeds. Returns an upload_id you can use in the references array of create_project or send_project_message. |
| estimate_cost | Estimate credit costs for planned generation operations before executing. Read-only — no credits consumed. Covers generation costs only (agent reasoning is additional). |
| submit_feedback | Report a bug, suggestion, or question to the Eversince team. Pass project_id to attach the report to a specific project. |
| show_images | Fetch multiple Eversince image assets and return them for inline display as a grid. Use after list_project_assets or when showing multiple variants/options to the user. |
| show_image | Fetch an Eversince image asset and return it for inline display. Use this after get_project or list_project_assets when you want to show the user an image directly in the conversation. Only works with eversince.ai media URLs. |