TorrentClaw-MCP
Giving AI assistants the ability to search movies and TV shows, find torrents with magnet links, check streaming availability, and explore cast/crew metadata.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
torrentclaw
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
autocompleteGet type-ahead search suggestions for movies and TV shows. Use this to validate or disambiguate a title before calling search_content. Returns up to 8 suggestions with id, title, year, and content type. Much faster than a full search.
get_creditsGet the director and top 10 cast members (with character names) for a movie or TV show. Use when the user asks about actors, cast, director, or 'who is in' a title. Requires content_id from search_content results.
get_popularGet trending movies and TV shows ranked by user click count. Use when the user asks for recommendations, trending titles, or 'what's popular'. Returns a paginated list with title, year, type, ratings, and content_id. Note: results do NOT include torrents — to get torrents for a title, call search_co…
get_recentGet the most recently added movies and TV shows, sorted by addition date. Use when the user asks 'what's new', 'latest additions', or 'recently added'. Returns a paginated list with title, year, type, ratings, date added, and content_id. Note: results do NOT include torrents — to get torrents for a …
get_torrent_urlGet a direct .torrent file download URL from an info_hash. Use when the user specifically wants a .torrent file rather than a magnet link (magnet links are already in search_content results). Returns a single URL the user can open in their browser or torrent client.
get_watch_providersCheck where a movie or TV show is available to stream, rent, or buy (Netflix, Disney+, Amazon Prime, etc.) in a specific country. Requires content_id from search_content results. Note: if you passed country to search_content, streaming info is already in those results — use this tool only for a diff…
submit_scan_requestSubmit a torrent for audio/video quality analysis (codec, tracks, resolution, HDR). Use when the user wants to know the exact media specs of a torrent before downloading. Results are not instant — use get_scan_status to check progress. Rate limited to 5 requests per hour.
get_scan_statusCheck the status of a torrent audio/video scan request. Returns the current scan status (pending, scanning, completed, failed). Use after submit_scan_request.
search_contentSearch for movies and TV shows by title, genre, year, rating, or quality. Returns matching content with metadata (title, year, genres, IMDb/TMDB ratings) and torrent download options (magnet links, quality, seeders, file size). This is the primary tool — use it first when a user asks to find, downlo…
track_interactionTrack a user interaction with a torrent (magnet link click, .torrent download, or hash copy). Use this after presenting a magnet link or torrent URL to the user, to keep popularity stats accurate. Fire-and-forget — does not block.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
TORRENTCLAW_API_KEY_(none)_ Optional API key for authenticated access (higher rate limits)TORRENTCLAW_API_URLTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
10/10 tools missing one or more hints — autocomplete (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_credits (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_popular (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +7 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
Only 0/10 tool handlers declare input schemas (0%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
9/10 tool handlers wrap calls in try/catch (90%)
Wrap each tool handler body in try/catch and return a structured error response.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/torrentclaw/torrentclaw-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check