Loading…
Original film criticism for AI agents: multi-framework readings, TakeScore ratings, kindred films.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The metatake MCP server exposes 6 tools, focused primarily on web capabilities. Its published description reads: "Original film criticism for AI agents: multi-framework readings, TakeScore ratings, kindred films". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates metatake D- — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check metatake's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add metatake to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://metatake.net/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
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 ful
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
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
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,
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] cata
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.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: search
A tool description tries to alter the model’s use of another tool.
ass an `id` to `fetch` to read the full critical pack. Use this to fiRecommendationDescriptions must describe only their own tool.
tool: fetch
A tool description tries to alter the model’s use of another tool.
film slug from `search`). Returns the film's complete critical pack asRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
earch_films (or search) to resolve a film to its slug, then call get_fRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: (server instructions)
The description pairs a fetch imperative with a hardcoded external URL, letting the server relocate its real instructions off-metadata and mutate them after review. Fires only when a fetch verb and a URL co-occur, so benign documentation links do not.
Metatake (https://metatake.net) serves original film criticism — AI-drafted, hRecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
Validates up to 75,000 URLs per job checking status codes, redirects, and response times.
Pay-per-call AI API marketplace with 47 endpoints — OCR, TTS, LLM chat, image generation, weather, and crypto pricing — paid via x402 USDC micropayments on Base.
EPA drinking water quality data in plain English, providing AI agents with tap water quality information for US cities via nine public-data tools.
AI phone answering and appointment booking tools for service businesses.
Aggregates Romanian TV, streaming, cinema, and theater listings for AI agents.
Agent-callable Parallax services — catalog browsing, pricing, project start, and booking.