# levea-mcp-server Open-source MCP client for Levea autonomous AI video editor — natural-language video editing (viral clips, captions, vertical reframe, chroma key, audio cleanup, motion tracking, B-roll, voiceover, music, cloud MP4 export) for Claude Desktop, Claude Code, - **Type:** MCP server - **Trust:** 60/100 (B), scored on the package rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 0.5.3 - **Author:** brajendrak00068 - **License:** MIT - **npm:** levea-mcp-server - **Source:** https://github.com/brajendrak00068/agentic-ai-video-production - **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport) ## Trust 60/100 (B), scored on the package rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: not run - Obfuscation scan: not run - Evidence age: 0 days ## Security scan - **Status:** clean - **Scanned:** 2026-10-11T20:13:32.150Z - **Version scanned:** 0.5.3 - **CVEs:** none found by OSV at scan time ## Tools 25 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `autonomous_edit` — PRIMARY EDIT TOOL. Run a natural-language video edit end-to-end. The backend agent plans, executes, verifies, and exports. Accepts anything from a one-liner ("g - `autonomous_edit_streaming` — Same as autonomous_edit but consumes the SSE event stream from the backend. Returns the final terminal result; per-step events (status, thinking, tool_call, too - `queue_edit` — Fire-and-forget async path. Returns immediately with a `taskId`. Use when the edit may exceed the MCP request timeout (long viral-clip generation, multi-format - `check_job_status` — Poll an export / async job by jobId (numeric). Supports wait:true to block until terminal. - `check_task_status` — Poll a queued edit task by taskId (returned by queue_edit). Separate from job_id (exports). - `get_active_task` — For a given project, return the currently-running edit task (if any). Useful for reconnecting MCP clients. - `list_caption_templates` — List the user's caption templates (builtin + saved). Returns slugs, display names, and style summaries. - `apply_caption_template` — Apply a caption template to a scene synchronously (without going through autonomous_edit). - `save_caption_template` — Save a new caption template definition the user can re-apply later. - `save_current_caption_template` — Snapshot the caption styling currently applied to a project / scene as a reusable template. - `delete_caption_template` — Delete a user-saved caption template by id. - `list_brand_kits` — List the user's brand profiles (palette, fonts, logo, voice, gradeBias). Returns ids you pass to autonomous_edit's brandId / projectBrandId. - `get_brand_kit` — Fetch one brand profile by id. - `create_brand_kit` — Create a brand profile. Fields: name, palette {primary,secondary,accent,neutral,extras[]}, fonts {primary,secondary}, gradeBias (warm/cool/neutral/vivid/muted), - `update_brand_kit` — Update an existing brand profile by id. Body has the same shape as create_brand_kit. - `delete_brand_kit` — Delete a brand profile. - `list_projects` — List the user's projects. - `get_project` — Fetch one project by id. - `create_project` — Create a new project. Optional initial brandId. - `delete_project` — Delete a project. - `asset_upload_url` — Get a signed upload URL for a local file (so users do not have to host video / image / audio elsewhere before passing video_url to autonomous_edit). Body: { fil - `list_assets` — List the user's uploaded assets. Optional projectId filter. - `delete_asset` — Delete an asset by file name (the path returned by asset_upload_url). - `transcribe_asset` — Force transcription of an existing asset. Returns transcript words + timing. - `editor_health` — Connectivity diagnostic against LEVEA_API_URL. Unauthenticated. ## Install **Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for. **Cautions** (coverage gaps and advisories — never blocking) - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"levea-mcp-server\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"levea-mcp-server\"\n ],\n \"env\": {\n \"LEVEA_API_KEY\": \"\"\n }\n }\n }\n}" ``` **Credentials it will ask for** (names only — Forge never holds a value): - `LEVEA_API_KEY` — Levea API Key (required) Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one. - This entry needs 1 credential (1 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset. ## Blast radius Extensive blast radius — deletes data; holds an api key. - Floor 58, ceiling 58 (tier: extensive) - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/levea-mcp-server - Install plan: https://forgeregistry.com/api/v1/packages/levea-mcp-server/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/levea-mcp-server - HTML page: https://forgeregistry.com/registry/levea-mcp-server - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.