# ReelRecs (remote · mcp.reelrecs.com)

Find movies and shows for tonight with current trends, mood, taste and streaming options.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.reelrecs.com`: 65/100 (this document), [markdown](https://verifymcp.io/servers/com-reelrecs-reelrecs/mcp.md), [page](https://verifymcp.io/servers/com-reelrecs-reelrecs/mcp)

## Channel facts

- Endpoint: `https://mcp.reelrecs.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.6`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 52/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3508 tokens (~269/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the ReelRecs MCP server?

ReelRecs is a hosted endpoint at https://mcp.reelrecs.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-reelrecs-reelrecs 'https://mcp.reelrecs.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-reelrecs-reelrecs": {
      "url": "https://mcp.reelrecs.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-reelrecs-reelrecs": {
      "type": "http",
      "url": "https://mcp.reelrecs.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-reelrecs-reelrecs]
url = "https://mcp.reelrecs.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-reelrecs-reelrecs": {
      "type": "remote",
      "url": "https://mcp.reelrecs.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-reelrecs-reelrecs --url 'https://mcp.reelrecs.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-reelrecs-reelrecs:
    url: "https://mcp.reelrecs.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-reelrecs-reelrecs": {
      "Transport": "http",
      "Url": "https://mcp.reelrecs.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-reelrecs-reelrecs -t streamable-http -u 'https://mcp.reelrecs.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-reelrecs-reelrecs": {
      "type": "http",
      "url": "https://mcp.reelrecs.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 65, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_charts” rewrote its description, which is the text the model reads
- [security] Tool “get_my_profile” rewrote its description, which is the text the model reads
- [security] Tool “recommend_titles” rewrote its description, which is the text the model reads
- [security] Tool “search_titles” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03

### 2026-11-04 (score 65)

First indexed and scored.

## MCP tools (13)

### `search_titles` (~94 tokens)

Find a movie or show

Find 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, keywords, cast, directors, language, runtime and viewing_experience mood levels with scope and evidence labels. Choices cover viewer-mentioned titles or assistant-chosen mood references.

Input parameters:

- `request` (object, required)

### `recommend_titles` (~198 tokens)

Find what to watch next

Find 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 open-ended or mood-only discovery without reference titles, use get_charts and choose from its viewing_experience context; this avoids relying on optional free-text encoding. Returns up to twelve candidates with ReelRecs Score, descriptions, genres, subgenres, subjects, tags, keywords, cast, directors, runtime, viewing_experience mood levels, reference overlaps and title links. General similarity supplies the neighborhood; intent selects the supporting evidence emphasis. Dislikes adjust comparable affinities; exclusions hide exact titles. The qualities_applied field identifies whether mood text affected ranking; mood context still helps you choose when it is false. Provider filters apply in the requested country; country alone does not filter availability. No account required.

Input parameters:

- `request` (object, required)

### `get_title_peers` (~97 tokens)

Compare similar movies or shows

Find 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 viewing/rating-affinity selection. They do not represent a shared group of raters, and no peer average is calculated. Missing scores are null. Streaming offers are not included.

Input parameters:

- `request` (object, required)

### `get_charts` (~301 tokens)

Find trending movies and TV shows

Find movies or TV shows for tonight or a mood: "What should I watch?", "Netflix tonight", "Something light", "tense but not depressing", "help me figure out what I'm in the mood to watch", or what's popular on streaming. Start here even when an account is connected. Find current candidates first, then use their viewing_experience mood levels, scope and evidence labels alongside title details to choose. No reference title or preference questionnaire is needed. If the viewer is unsure, give concrete picks in two easy directions and let their reaction guide you; mood is an optional follow-up alongside service and movie-versus-show. Returns up to twelve candidates from the latest available U.S. audience charts, with ReelRecs Score, descriptions, genres, subgenres, tags, keywords, subjects, cast, directors, runtime and links. An authorized connection can also add personal Rec Score predictions to these current choices. Streaming-service filtering uses constraints.providers with constraints.country; country alone does not establish availability. Also supports genre, runtime, first-release-year and exclusion filters. Trending and rising measure attention at chart_as_of; popular measures broader audience demand. chart_freshness and chart_age_days distinguish dated discovery snapshots from current rankings. Chart attention is distinct from new releases, and the chart market is distinct from availability country. Provides movie and series discovery, not live sports fixtures or broadcast schedules. No ReelRecs account required.

Input parameters:

- `request` (object, required)

### `get_watch_options` (~136 tokens)

Find where to watch

Find 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 personal access, also returns streaming_preferences.services and matches_saved_service on each offer. Lead with matching included offers; matching rentals and purchases still cost extra. Use saved services without asking the viewer to repeat them. Subscription, free/ad-supported, rental and purchase are separate. An empty or stale result does not prove worldwide unavailability. No ReelRecs account required for public offers.

Input parameters:

- `request` (object, required)

### `get_my_profile` (~94 tokens)

Check my ReelRecs connection

Read account identity and saved streaming-service names when the viewer asks about their account or saved services. This is not a prerequisite for recommendations or help discovering a viewing mood; use public get_charts for those requests. Returns display identity, whether saved taste is available, and streaming_preferences.services, not a taste analysis. get_watch_options also matches offers to these preferences. Requires a connected ReelRecs account. Never exports full history.

### `recommend_for_me` (~194 tokens)

Recommend using my saved taste

Use 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; current chart candidates can include personal predictions too. This tool ranks the wider catalogue by saved taste, positive or disliked reference titles and desired qualities. Returns up to twelve candidates with rich title context, audience ReelRecs Score, personal Your Rec Score predictions and links. Both scores use a ten-point scale; missing predictions are null. Weigh personal fit with the viewing experience and tonight's mood. Excludes watched titles unless rewatch is requested and can use saved streaming services. Saved taste describes lasting preferences; the qualities_applied field identifies whether mood text affected ranking. Requires an authorized ReelRecs account and never accepts an account identifier.

Input parameters:

- `request` (object, required)

### `get_my_ratings` (~188 tokens)

Browse and look up my saved ratings

Use 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 title fragment, kind, highest/lowest/title sort, and next_offset; up to 50 titles per page. For a requested full-history taste analysis, read all pages and use both high and low ratings with the returned descriptions, genres, subgenres and tags. Curate a few picks using that evidence; personal predictions are secondary when requested. Alternatively supply up to ten resolved title_ids to check saved ratings or confirmed absence for those specific titles. Requires ratings:read. Saved ratings, audience scores and personal predictions are distinct. A successful lookup confirms the connection. Cannot read another account or change ratings.

Input parameters:

- `request` (object, required)

### `get_my_bookmarks` (~229 tokens)

Browse my bookmarked movies and shows

Use 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 shows, and next_offset retrieves another page. Start a simple browse with the default page and a short linked list; show remaining fetched titles before fetching more when requested or when it helps choose. matched_count is the total for the applied filters. If a movie/show breakdown is requested, use kind-filtered counts rather than estimating it. Returns saved dates, descriptions, genres, subgenres, tags, runtime, ReelRecs links and audience scores. With personal recommendation permission, also adds Your Rec Score predictions. Keep picks within the returned bookmarks when requested, check watch options, and curate a few fitting choices using available returned title links. Rated or watched titles can still be bookmarked; do not infer history or likes from a save. Requires bookmarks:read permission. Cannot read another account or add/remove saves.

Input parameters:

- `request` (object, required)

### `get_my_watchplus_groups` (~111 tokens)

Find my Watch+ groups

Find 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, then recommend_for_group. Match usernames to distinguish duplicate names; when the same people share several groups, prefer the smallest matching group unless the viewer names one. Proceed directly when the people are clear. Requires watchplus:read permission.

Input parameters:

- `request` (object, required)

### `get_watchplus_context` (~128 tokens)

Understand our Watch+ tastes

Explore 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 relevant saved references, including evidence beyond the overview examples. Helps explain shared appeal, differences, reservations and compromises. Profiles respect existing privacy and blocks. Missing evidence is unknown. Similar saved titles illustrate content overlap; they do not explain the scoring model's causes. Requires watchplus:read; cannot read strangers, pending invitations, private chats or change anything.

Input parameters:

- `request` (object, required)

### `recommend_for_group` (~176 tokens)

Find something we will enjoy together

Choose 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 rich title details, audience ReelRecs Score, separate per-person Rec Score predictions, saved ratings, Watch+ votes and related likes/dislikes. Prioritizes balanced fit and current interest by default; focus=all_titles explores the library. Pass votes lower priority without changing predictions. Excludes known seen titles unless allow_rewatch. Use current mood, positive/disliked references and streaming filters when known; do not demand a questionnaire. Predictions require fresh completed scores; missing coverage never means agreement. Requires watchplus:read and current accepted membership. Privacy and blocks are checked again before returning.

Input parameters:

- `request` (object, required)

### `report_recommendation_feedback` (~177 tokens)

Share recommendation feedback with ReelRecs

Record 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 relevant result request_id and up to five affected title IDs copied from results when available; otherwise omit them. IDs must not be invented. The paraphrase is limited to 300 characters. User statements, actions and uncertain assistant inferences are separate evidence types; inference confidence must be low or medium. Silence or continued use is not evidence of a reaction. Transcripts, identity, credentials and sensitive personal details are outside the report's scope. Reports are unverified observations and cannot change saved ratings or taste. Returns receipt acknowledgement; host approval controls and viewer opt-out apply.

Input parameters:

- `request` (object, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-reelrecs-reelrecs/mcp#diagnostics

## Score history

- 2026-11-05: 65
- 2026-11-04: 65

## Common questions

### What is the ReelRecs MCP server?

ReelRecs is an MCP server listed in the public MCP registry as com.reelrecs/reelrecs. Find movies and shows for tonight with current trends, mood, taste and streaming options. This page covers its hosted endpoint (https://mcp.reelrecs.com/mcp).

### Is the ReelRecs MCP server safe to use?

ReelRecs scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ReelRecs MCP server expose?

ReelRecs exposes 13 tools: search_titles, recommend_titles, get_title_peers, get_charts, get_watch_options, and 8 more. Their descriptions and schemas cost roughly 2,123 tokens of context every time the server is loaded.

### Does the ReelRecs MCP server require authentication?

No. We connected to ReelRecs without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ReelRecs MCP server still maintained?

ReelRecs is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.reelrecs.com/mcp
- Website: https://reelrecs.com/assistants/
- Changelog RSS feed: https://verifymcp.io/servers/com-reelrecs-reelrecs/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-reelrecs-reelrecs/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-reelrecs-reelrecs/mcp