
ReelRecs MCP server
Which MCP servers are ReelRecs's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-11-04
- Registry namecom.reelrecs/reelrecsverified in the MCP registry
The registry name sits under reelrecs.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-04
- Tools13
- Server calls itselfReelRecs
- Server version0.1.0
- Protocol version2025-06-18
On 2026-11-04 the server answered initialize and tools/list without a sign-in. First answer in 311 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 12 of 13 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer320 ms
- Space in an agent's context≈ 8,781 tokensthe definitions of all its tools (13), which an agent carries on every turn
- Tool definitionsB · 85 of 100
- Typed results13 of 13 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 12 of 13
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_titlesFind a movie or TV show from its name, a remembered fragment or a typo. Resolve its exact version before recommendations or availability checks. Returns canonical IDs and rich title context: description, genres, subgenres, tags, subjects…
recommend_titlesFind movies like X, shows to watch after Y, or alternatives when someone liked one title but disliked another. Resolve names with search_titles first, then pass positive and disliked reference IDs plus any desired qualities. For an…
get_title_peersFind optional content references for one resolved movie or show when a comparison is useful. Returns ReelRecs Score out of 10, descriptions, tags, subgenres and links. Candidates are selected from content without audience-score or…
get_chartsStart here for "Netflix tonight", "What should I watch?", "Good shows", "Something light" or what's popular on streaming, including when an account is connected. Find current candidates first, then judge their fit for the viewer's mood…
get_watch_optionsFind where to watch a movie or show, including on the viewer's saved services. Resolve names with search_titles first, then pass up to ten exact IDs. Returns providers, offer types, observation dates and availability freshness. With…
get_my_profileRequires a connected ReelRecs account. Returns display identity, whether saved taste is available, and the viewer's saved streaming-service names in streaming_preferences.services. Use these when the viewer asks about their services…
recommend_for_meUse when the viewer asks to explore their saved taste or the wider library, such as "recommend based on my ratings". For an open-ended "Netflix tonight", "What should I watch?" or mood-only start, use get_charts first even when connected…
get_my_ratingsUse for my ratings, all the movies and shows I rated, understand my taste, what I loved or disliked, and have I rated this title. Omit title_ids to browse the viewer's full rated list, independently of bookmarks. Browse with an optional…
get_my_bookmarksUse for my bookmarks, my watchlist, saved movies or shows, did I save this title, and help me pick from my list. Lists the connected viewer's own saves, newest first; query searches the full list by title fragment, kind filters movies or…
get_my_watchplus_groupsFind the connected viewer's accepted Watch+ groups by group or member name, such as Jenna. Returns current accepted member IDs, display names and app usernames, never emails or pending invitees. Use these IDs for the people watching now…
get_watchplus_contextExplore the selected accepted group members' accessible tastes. Returns liked and less-liked examples and descriptive patterns. Supply up to ten resolved title IDs for each person's predicted rating, saved rating, Watch+ interest/pass and…
recommend_for_groupChoose what the accepted Watch+ members watching together might enjoy tonight. Resolve the group and people with get_my_watchplus_groups first. Returns up to twelve compact candidates for the assistant to curate into two or three, with…
report_recommendation_feedbackRecord a brief quality report about a meaningful acceptance, rejection, correction or concrete problem with ReelRecs results, when permitted by the viewer and host. At most one report per new signal across ReelRecs tools. Accepts the…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"reelrecs": {
"type": "http",
"url": "https://mcp.reelrecs.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http reelrecs https://mcp.reelrecs.com/mcpclaude.ai, ChatGPT and other clients: add https://mcp.reelrecs.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.