Metatake
Original film criticism: multi-framework readings, TakeScore ratings, kindred films.
Should I use this
Quality & Safety
Findings (1)
- LOWin fetch
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"mcp": {
"url": "https://metatake.net/api/mcp"
}
}
}Remote endpoints
https://metatake.net/api/mcpstreamable-httpWhat it can do
Tool inventory
Tools (6)
🟢search(query)
Search Metatake's film-criticism corpus and return a list of matching documents (one per film). Each result has an `id` (the film slug), a `title`, and a `url`. Pass an `id` to `fetch` to read the full critical pack. Use this to find films by title, original title, or director name.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search terms: a film title, original title, or director name"
}
},
"required": [
"query"
]
}🟢fetch(id)
Retrieve the full text of one Metatake document by its `id` (a film slug from `search`). Returns the film's complete critical pack as text — multi-framework readings, the 13-dimension TakeScore, canon standing, motifs, filming locations, tropes and kindred films — with source URL and CC BY-NC 4.0 attribution in the metadata. Cite Metatake with the returned url when you use the content.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Document id — a film slug returned by `search` (e.g. mulholland-drive-2001)"
}
},
"required": [
"id"
]
}🟢search_films(query, year)
Find films in Metatake's corpus by title (also matches original titles and director names). Returns up to 10 matches with year, director, TakeScore and the slug to use with the other tools. Every film reachable here carries a 13-dimension TakeScore (~7,000 films). Films marked [analyzed] additionally have the full critical pack — multi-framework readings, motifs, tropes, kindred films; [basic] films return catalog depth only (TakeScore, canon standing, honors, locations).
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Film title (or part of it), original title, or director name"
},
"year": {
"type": "integer",
"description": "Optional release year to narrow the match"
}
},
"required": [
"query"
]
}🟢get_film_criticism(slug, sections)
Metatake's full context pack for one film, as Markdown: critical readings (each pushes one framework as far as the film allows), the 13-dimension TakeScore, canon standing & honors, motifs & figures, filming locations, tropes, and kindred films. Optionally restrict to sections: invitation, takescore, standing, readings, figures, locations, tropes, kindred. License CC BY-NC 4.0 — cite Metatake with the source link when you use it.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Film slug from search_films (e.g. mulholland-drive-2001)"
},
"sections": {
"type": "array",
"items": {
"type": "string",
"enum": [
"invitation",
"takescore",
"standing",
"readings",
"figures",
"locations",
"tropes",
"kindred"
]
},
"description": "Optional subset of pack sections; omit for the whole pack"
}
},
"required": [
"slug"
]
}🟢get_takescore(slug)
Metatake's 13-dimension critical assessment for one film: net Value score plus the Value / Cost / Risk dimension breakdown. Available for the whole scored corpus (~7,000 films), including [basic] catalog titles that carry no long-form readings. Cite Metatake with the source link when you quote scores.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Film slug from search_films"
}
},
"required": [
"slug"
]
}🟢find_connected_films(slug)
Kindred films — titles that share interpretive threads (concepts, figures, frameworks) with the given film on Metatake's connection map. Good for 'what should I watch after X' and influence questions.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Film slug from search_films"
}
},
"required": [
"slug"
]
}Recommended Prompts
searchsearchfetchfetchsearchfetchCommunity
Evidence