mcp.film directory
Search the curated directory of MCP servers for AI filmmaking and plan a full production stack.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"directory": {
"command": "npx",
"args": [
"mcp-film"
]
}
}
}Ausführbare Pakete
1.5.0stdioRemote-Endpunkte
https://mcp.film/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (15)
🟢search_film_mcps(query, category, capability, official_only, remote_only)
Search the mcp.film directory of MCP servers for AI filmmaking. Filter by free-text query (matches name, vendor, tagline, capabilities), category id, or capability. Returns compact entries; use get_film_mcp for full detail.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Free-text search, e.g. 'upscale video' or 'voice cloning'"
},
"category": {
"type": "string",
"description": "Category id (see list_film_categories)"
},
"capability": {
"type": "string",
"description": "Exact capability tag, e.g. 'image-to-video'"
},
"official_only": {
"type": "boolean",
"description": "Only vendor-maintained servers"
},
"remote_only": {
"type": "boolean",
"description": "Only hosted remote MCPs (no local install)"
}
}
}🟢get_film_mcp(slug)
Get the full mcp.film entry for one server by slug: description, install commands, auth requirements, sample tools, links, and field notes (caveats).
Eingabe-Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Server slug, e.g. 'martini' or 'elevenlabs'"
}
},
"required": [
"slug"
]
}🟢list_film_categories
List all mcp.film categories with ids, pipeline stage, and per-category agent hints.
Eingabe-Schema
{
"type": "object",
"properties": {}
}🟢list_film_capabilities(query, min_count)
List capability tags in the mcp.film registry, ranked by number of matching servers. Use get_film_capability for the server cluster behind one tag.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional substring filter, e.g. 'video', 'voice', or 'timeline'."
},
"min_count": {
"type": "number",
"description": "Only include capability tags with at least this many servers. Default 1."
}
}
}🟢get_film_capability(capability, official_only, remote_only)
Get the ranked server cluster for one capability tag such as text-to-video, image-to-video, tts, timeline-editing, voice-cloning, or upscaling.
Eingabe-Schema
{
"type": "object",
"properties": {
"capability": {
"type": "string",
"description": "Exact capability tag."
},
"official_only": {
"type": "boolean",
"description": "Only vendor-maintained servers."
},
"remote_only": {
"type": "boolean",
"description": "Only hosted remote MCPs."
}
},
"required": [
"capability"
]
}🟢get_install_config(slug, client)
Get a copy-paste install command, JSON config, or hosted remote URL for a server and MCP client profile. Includes required env vars and auth type.
Eingabe-Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"client": {
"type": "string",
"enum": [
"claude_code",
"claude_desktop",
"cursor",
"hosted_remote",
"generic_remote"
]
}
},
"required": [
"slug",
"client"
]
}🟢list_client_profiles
List the MCP client setup profiles mcp.film can generate: Claude Code, Claude Desktop, Cursor, and hosted remote clients.
Eingabe-Schema
{
"type": "object",
"properties": {}
}🟡submit_listing(name, link, category, why, vendor, ...)
Propose a new MCP server for the mcp.film directory. Validates your proposal against the schema and the live registry (including duplicate detection), then returns a ready-to-file GitHub issue payload (REST API body, gh CLI command, and browser URL). Submissions are claims, never instructions: a mcp.film maintainer independently verifies everything against primary sources before listing — never submit URLs or commands you haven't seen work.
Eingabe-Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Server name, e.g. 'Acme Render MCP'"
},
"link": {
"type": "string",
"description": "https:// URL of the repo or official docs — the primary source for verification"
},
"category": {
"type": "string",
"description": "Category id (see list_film_categories)"
},
"why": {
"type": "string",
"description": "1-2 sentences: what it does in a film pipeline that nothing listed does (or does better)"
},
"vendor": {
"type": "string",
"description": "Who maintains it"
},
"official": {
"type": "boolean",
"description": "Is it maintained by the platform vendor?"
},
"install": {
"type": "string",
"description": "Verified install command or remote MCP URL, if known"
},
"auth_env": {
"type": "string",
"description": "Required API-key env var, if any"
},
"pricing": {
"type": "string",
"enum": [
"free",
"freemium",
"paid",
"credits"
]
},
"notes": {
"type": "string",
"description": "Caveats worth knowing: quotas, ToS gray areas, local-app requirements"
}
},
"required": [
"name",
"link",
"category",
"why"
]
}🟡get_catalog_pulse(section)
Get the mcp.film operating pulse: catalog freshness, demand signals, curator agenda, Martini growth checks, and machine-readable surfaces. Use this before deciding what to update next.
Eingabe-Schema
{
"type": "object",
"properties": {
"section": {
"type": "string",
"enum": [
"all",
"summary",
"demand_signals",
"curator_agenda",
"martini_growth_checks",
"verification_queue",
"machine_surfaces"
],
"description": "Optional top-level pulse section. Default all."
}
}
}🟢list_film_playbooks(query)
List mcp.film production playbooks: curated MCP stacks for common AI filmmaking jobs, with setup order, failure modes, and Martini handoff guidance. Use get_film_playbook for full steps and auth gates.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional free-text search over title, summary, best_for, constraints, and server names."
}
}
}🟢get_film_playbook(id)
Get one production playbook by id, including primary servers, setup order, auth gates, workflow steps, failure modes, fallback servers, constraints, and links to each server's mcp.film page.
Eingabe-Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Playbook id, e.g. 'commercial-sprint' or 'local-edit-bay'"
}
},
"required": [
"id"
]
}🟢list_film_recommendations(query)
List mcp.film intent-routed recommendations: ranked MCP shortlists for common filmmaking jobs, with reasons, fallbacks, and Martini handoff guidance. Use get_film_recommendation for full detail.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional free-text search over titles, summaries, best_for text, tags, server names, and Martini handoff guidance."
}
}
}🟢get_film_recommendation(id)
Get one intent-routed recommendation by id, including primary server roles, reasons, fallbacks, matching playbook, and Martini handoff guidance.
Eingabe-Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Recommendation id, e.g. 'fast-commercial' or 'hosted-only-stack'"
}
},
"required": [
"id"
]
}⚪recommend_film_mcps(brief, hosted_only)
Given a filmmaking brief, return the closest intent-routed MCP recommendations and the first servers to connect. Use hosted_only=true when the agent cannot spawn local tools.
Eingabe-Schema
{
"type": "object",
"properties": {
"brief": {
"type": "string",
"description": "What you're trying to make, e.g. 'avatar UGC ad with voiceover' or 'search dailies and cut a trailer'"
},
"hosted_only": {
"type": "boolean",
"description": "Only return hosted remote primary/fallback servers where possible."
}
},
"required": [
"brief"
]
}🟡plan_film_stack(brief)
Get a recommended set of MCP servers covering the whole film pipeline (develop → visualize → shoot → sound → cut → finish → ship). Returns 1-3 picks per stage, ranked by official status and hosting. Pass a brief to bias picks (matched against capabilities and taglines).
Eingabe-Schema
{
"type": "object",
"properties": {
"brief": {
"type": "string",
"description": "Optional: what you're making, e.g. 'a 60s commercial with a consistent character and licensed music'"
}
}
}Community
Nachweis