# Bitmovin Observability MCP

> Query and analyse your data from Bitmovin Observability

- name: com.bitmovin.mcp.analytics/analytics-mcp
- version: 0.0.1
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 82/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.bitmovin.mcp.analytics%2Fanalytics-mcp
- tools: https://api.protogrid.dev/v1/servers/com.bitmovin.mcp.analytics%2Fanalytics-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "analytics-mcp": {
      "type": "http",
      "url": "https://analytics.mcp.bitmovin.com",
      "headers": {
        "x-api-key": "${X_API_KEY}"
      }
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-75d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 82/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 3 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 11 of 11 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: queryTotal (idempotentHint); analyzeImpression (idempotentHint); getAvailableMetrics (idempotentHint); …
- pass `tools.token_cost`: about 4,435 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 11, about 4,435 tokens to load them all
- tool set hash: 7cddb3d7e5e9746796a385b68ffe1b88
- badge: [![protogrid quality](https://protogrid.dev/badge/com.bitmovin.mcp.analytics/analytics-mcp.svg)](https://protogrid.dev/servers/com.bitmovin.mcp.analytics/analytics-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://analytics.mcp.bitmovin.com (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (11)

- `analyzeImpression`: Deep-dive analysis of a SINGLE playback session identified by a specific impressionId: static properties, aggregated metrics, state-transition timeline, and an AI-powered interpretation of session quality. Use for detailed single-session troubleshooting. REQUIRES an impressionId. Do NOT use this for license-wide metrics, totals, trends, or any time-range ('last week', start/end) analysis — this tool does not accept start/end. For metrics over a time period use the 'query' tool; for breakdowns by category use 'queryGroupBy'.
- `fetchImpressions`: List the impression ids (individual playback session ids) for a license over a time range, optionally narrowed by filters. Returns the ids themselves — NOT counts, totals, or trends. Use this to enumerate sessions before drilling into specific ones with `getImpressionOverview` or `analyzeImpression`. Typical uses: 'give me impression ids from yesterday', 'list sessions on Safari that errored last week', 'sample sessions from country US'. Every matching session is eligible (including failed/setup sessions), not only successful plays. Results are capped (default 100, max 200); if truncated, narrow the timeframe/filters or raise `limit`. A licenseKey is required, and `peekAllLicenses` lists the available ones; `searchFilters` resolves the filter attributes and operators used by the optional `filters` input. For metric counts/trends over a period use `query` / `queryTotal`; for category breakdowns use `queryGroupBy`.
- `getAvailableFilters`: List the full catalog of filter attributes with their supported operators. Prefer searchFilters to resolve a single attribute; use this only when you need every filter.
- `getAvailableMetrics`: List the full catalog of metrics with their supported aggregation methods. Prefer searchMetrics to resolve a single keyword; use this only when you need every metric.
- `getImpressionOverview`: Inspect a SINGLE playback session identified by a specific impressionId. Returns that one session's static properties (device, location, player) and its aggregated metrics (total played time, buffering, video quality). REQUIRES an impressionId. Do NOT use this for license-wide metrics, totals, trends, or any time-range ('last week', start/end) analysis — this tool does not accept start/end. For metrics over a time period use the 'query' tool; for breakdowns by category use 'queryGroupBy'.
- `peekAllLicenses`: View a summary of all available licenses with their recent play counts and percentage distribution. Use this to understand what licenses exist and their relative usage. When a user asks about licenses by ranking (e.g., 'biggest', 'most active', 'first'), use this to identify which license matches that criteria before querying.
- `query`: Query a metric over a time range (start/end) for a license as a TIME SERIES — always renders a chart. Use this for trends and license-wide analytics over a period (e.g. 'last week', 'last 30 days', 'yesterday'). Bucket size is chosen automatically from start/end; there is no interval field to set. For a single aggregated number (one total/average over the whole period, NO chart), use the separate `queryTotal` tool instead. Queries resolve against API metric keywords, which can differ from a metric's common name — 'plays', for example, is 'impression_id'. The 'searchMetrics' tool resolves a keyword cheaply; 'getAvailableMetrics' returns the full catalog. Every query needs a licenseKey; `peekAllLicenses` lists the ones available. AD ANALYTICS: ad metrics use 'ad_'-prefixed keywords and are queried against a separate ads dataset. The ad completion funnel is: 'ad_quartile_1' (first quartile / 25%) -> 'ad_midpoint' (50%) -> 'ad_quartile_3' (third quartile / 75%) -> 'ad_completions'. Other ad metrics: 'ad_impressions', 'ad_starts', 'ad_clicks', 'ad_skips', 'ad_startup_time', 'ad_error_percentage', 'ad_error_sessions', 'ad_time_played', 'ad_play_percentage', 'ad_unique_users'. Ad data is present on some licenses and not others; `peekAllLicenses` output shows which. A query covers a single license, so an ad question resolves against one license at a time. With an ad metric, filters and groupBy take the AD-specific attributes from 'searchFilters' / 'getAvailableFilters' (e.g. 'AD_SYSTEM', 'AD_POSITION', 'ADVERTISER_NAME'); playback attributes and ad attributes are not interchangeable. OPTIONAL 3) Use the 'searchFilters' tool to find filter attributes/operators (or 'getAvailableFilters' for the full list).
- `queryGroupBy`: query metric grouped by categories. Queries resolve against API metric keywords, which can differ from a metric's common name — 'plays', for example, is 'impression_id'. The 'searchMetrics' tool resolves a keyword cheaply; 'getAvailableMetrics' returns the full catalog. Every query needs a licenseKey; `peekAllLicenses` lists the ones available. AD ANALYTICS: ad metrics use 'ad_'-prefixed keywords and are queried against a separate ads dataset. The ad completion funnel is: 'ad_quartile_1' (first quartile / 25%) -> 'ad_midpoint' (50%) -> 'ad_quartile_3' (third quartile / 75%) -> 'ad_completions'. Other ad metrics: 'ad_impressions', 'ad_starts', 'ad_clicks', 'ad_skips', 'ad_startup_time', 'ad_error_percentage', 'ad_error_sessions', 'ad_time_played', 'ad_play_percentage', 'ad_unique_users'. Ad data is present on some licenses and not others; `peekAllLicenses` output shows which. A query covers a single license, so an ad question resolves against one license at a time. With an ad metric, filters and groupBy take the AD-specific attributes from 'searchFilters' / 'getAvailableFilters' (e.g. 'AD_SYSTEM', 'AD_POSITION', 'ADVERTISER_NAME'); playback attributes and ad attributes are not interchangeable. The groupBy attribute is an exact API attribute name, and common guesses are often wrong: 'OPERATING_SYSTEM' is invalid where 'OPERATINGSYSTEM' is correct, and an unrecognised attribute fails with a validation error. The 'searchFilters' tool resolves an attribute name; 'getAvailableFilters' returns the full catalog. Results grouped by ERROR_CODE carry occurrence counts but not error semantics, which are Bitmovin-specific and documented in the live Bitmovin documentation served by the docs MCP tool (typically `general_docs_ask_bitmovin_docs`). That tool resolves one numeric error code per call and returns nothing usable for a question naming several codes at once.
- `queryTotal`: Get an aggregated value (one number) for a metric over a time range — no chart, no time bucketing. Can fetch SEVERAL metrics in one call: pass an array to `metric` to get one value per metric (e.g. the ad completion funnel), instead of calling this tool repeatedly. Use ONLY when the user asks for totals/averages/median/p95 over a whole period (e.g. 'total plays last month', 'average startup time yesterday', 'p95 rebuffer last week', 'the ad funnel counts last week'). For trends or any 'how did X change over time' / 'show last week' question, use the `query` tool instead — it always renders a chart. Queries resolve against API metric keywords, which can differ from a metric's common name — 'plays', for example, is 'impression_id'. The 'searchMetrics' tool resolves a keyword cheaply; 'getAvailableMetrics' returns the full catalog. Every query needs a licenseKey; `peekAllLicenses` lists the ones available. AD ANALYTICS: ad metrics use 'ad_'-prefixed keywords and are queried against a separate ads dataset. The ad completion funnel is: 'ad_quartile_1' (first quartile / 25%) -> 'ad_midpoint' (50%) -> 'ad_quartile_3' (third quartile / 75%) -> 'ad_completions'. Other ad metrics: 'ad_impressions', 'ad_starts', 'ad_clicks', 'ad_skips', 'ad_startup_time', 'ad_error_percentage', 'ad_error_sessions', 'ad_time_played', 'ad_play_percentage', 'ad_unique_users'. Ad data is present on some licenses and not others; `peekAllLicenses` output shows which. A query covers a single license, so an ad question resolves against one license at a time. With an ad metric, filters and groupBy take the AD-specific attributes from 'searchFilters' / 'getAvailableFilters' (e.g. 'AD_SYSTEM', 'AD_POSITION', 'ADVERTISER_NAME'); playback attributes and ad attributes are not interchangeable.
- `searchFilters`: Find the exact filter/group-by attribute keyword for a topic or question (e.g. 'browser', 'device type', 'content tier'). Preferred way to resolve an attribute; use 'licenseKey' to resolve custom namings of attributes; use getAvailableFilters only to list the full static catalog.
- `searchMetrics`: Find the exact metric keyword for a topic or question (e.g. 'buffering', 'how many errors'). Preferred way to resolve a metric keyword; use getAvailableMetrics only to list the full catalog.