> For the complete documentation index, see [llms.txt](https://knowledgebase.fabricdata.com/insights/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://knowledgebase.fabricdata.com/insights/origin-insights-mcp/getting-started.md).

# Getting started

**AI-powered access to streaming market intelligence.**

Origin Insights MCP is a **Model Context Protocol** server that connects AI assistants (Claude, ChatGPT, and others) directly to Origin Insights' streaming market data. Instead of navigating dashboards or writing queries, analysts **ask in natural language** and get structured, decision-ready answers.

|                  |                                                                       |
| ---------------- | --------------------------------------------------------------------- |
| **MCP endpoint** | [https://insights.fabric-mcp.link](https://insights.fabric-mcp.link/) |
| **Transport**    | Streamable HTTP (via `mcp-remote` for local clients)                  |
| **Auth**         | Browser sign-in — grant access once, per client                       |
| **Setup guide**  | [download.fabric-mcp.link](https://download.fabric-mcp.link/)         |

### Why use it

* **Multi-domain queries:** availability, demand, prices, and platforms in a single question, with no manual exploration.
* **Decision-ready reports:** turns complex data into actionable answers and visual HTML reports with charts and KPIs.
* **Always up to date:** new capabilities ship proactively — no updates needed on your side.
* **Read-only and catalog-scoped:** every answer is grounded in the Origin Insights catalog; the server never writes back to your systems.

### In this section

* [MCP access](/insights/origin-insights-mcp/mcp-access.md) — connection methods (Claude Web, Desktop installer, manual, Claude Code).
* [Best practices](/insights/origin-insights-mcp/best-practices.md) — sample queries, an example agent session, and how to get the most out of it.

> MCP releases are now centralized in Project docs → Releases — MCP.

### Data domains

The catalog spans **11 data domains**. Every tool below reads from one or more of these.

| Domain           | What it covers                                                                                                       |
| ---------------- | -------------------------------------------------------------------------------------------------------------------- |
| **Content**      | Movie/series/episode metadata (TMDb, IMDb, TVDB, EIDR): cast, genres, synopsis, box office, scores, awards, artwork. |
| **Availability** | Current + historical streaming availability, packages (SVOD/TVOD/AVOD), deep-links, lifecycle, seasons, exclusivity. |
| **Demand**       | Weekly composite demand (piracy, social, IMDb, YouTube, CDB): scores per title/market/week, rankings, genre trends.  |
| **Price**        | TVOD rent/buy pricing per title/platform/quality/currency, with monthly and quarterly history.                       |
| **PPB**          | Subscription plans: tiers, local + USD pricing, streams, devices, downloads, ads, resolution, bundles, promos.       |
| **Supply**       | Content exclusivity at platform-country level, aggregator classification.                                            |
| **Platform**     | Platform registry: status, logos, ownership, category, launch year, ads, cross-country catalog overlap.              |
| **Coming Soon**  | Upcoming releases: expected dates, release type, season/episode counts, genre.                                       |
| **Reports**      | Pre-built HTML reports (OIDL): charts, KPIs, tables aggregating multiple domains.                                    |
| **Intelligence** | Market-level analysis across platforms and countries: snapshots, comparisons, opportunity discovery.                 |
| **Interactive**  | Cross-title and cross-platform comparison tools with server-side HTML reports.                                       |

### Tool catalog

The MCP exposes its capabilities through a small set of **domain tools**. Each tool takes an `action` parameter that selects the specific operation, plus the arguments that operation needs. You don't call actions directly — the assistant picks the tool and action for you from your natural-language question. New actions get added automatically; this list reflects the current state.

#### Titles & metadata — `titles`

Title discovery and metadata: search, browse, profiles, artwork, filmography, box office, and awards.

`find_title` · `browse_titles` · `show_title_profile` · `find_title_artwork` · `show_title_awards` · `rank_titles_by_quality` · `find_filmography` · `find_studio_titles` · `find_frequent_collaborators` · `get_title_external_ids` · `find_industry_awards` · `show_box_office` · `rank_awards_leaders`

#### Availability & catalog — `availability`

Where titles stream — right now and over time — plus catalog-wide browsing, lifecycle, seasons, and CSV/Excel export.

`find_where_to_watch` · `find_streaming_availability` · `find_season_availability` · `track_availability_timeline` · `track_title_across_platforms` · `track_title_lifecycle` · `track_availability_history` · `track_season_platform_changes` · `track_season_distribution` · `measure_title_staying_power` · `measure_season_staying_power` · `measure_availability_duration` · `summarize_platform_coverage` · `summarize_season_coverage` · `measure_global_reach` · `measure_season_global_reach` · `find_whats_streaming` · `find_platform_exclusives` · `find_departing_titles` · `track_catalog_growth` · `track_catalog_evolution` · `measure_global_catalog_size` · `export_whats_streaming_to_csv` · `export_whats_streaming_to_excel`

#### Demand, popularity & rankings — `demand`

Trending titles, demand rankings, global hits, per-title popularity over time, genre momentum, official top-10, and pre-release hype.

`find_trending_titles` · `rank_titles_by_demand` · `find_global_hits` · `measure_title_popularity` · `track_genre_trends` · `find_top_10_charts` · `discover_hyped_titles` · `break_down_demand_scores` · `whats_coming_soon`

#### Platforms & services — `platforms`

The streaming services themselves: list, search, ownership, logos, status/metadata, and cross-country catalog overlap.

`list_streaming_services` · `find_platforms` · `find_platforms_by_owner` · `find_platform_logos` · `check_platform_status` · `compare_platform_across_countries`

#### Pricing — `pricing`

Per-title transactional (TVOD) rent/buy pricing.

`show_title_price` · `track_price_drops` · `break_down_title_price`

#### Subscriptions & plans — `subscriptions`

Subscription (SVOD) plans, bundles, and promotions.

`compare_subscription_plans` · `find_best_plans` · `find_promotional_offers` · `track_plan_prices`

#### Market & competitive intelligence — `market_intelligence`

Platform-vs-platform and country-vs-country analysis, catalog overlap, audience gaps, studio strategy, and hidden-gem licensing shortlists.

`compare_platforms` · `compare_catalog_overlap` · `compare_country_catalogs` · `find_audience_gaps` · `spot_hidden_gems` · `analyze_studio_strategy` · `get_the_quick_pitch` · `generate_market_intelligence_report`

#### Multi-step playbooks — `playbooks`

Composite analyses that run several lookups for you and return a single decision-ready answer.

`compare_titles` · `find_similar_titles` · `calculate_platform_value` · `build_content_calendar` · `build_market_brief` · `build_acquisition_brief` · `evaluate_license_renewal` · `find_underexploited_titles` · `build_content_gap_brief`

#### Reports & outputs

Formatted, visual HTML reports. Each report tool aggregates all of its sections in a single call.

* **Single entity — `reports`:** `generate_title_report` · `generate_country_report` · `generate_platform_report` · `generate_people_report` · `generate_top_titles_report` · `who_watches_this` · `complete_audience_report` · `add_executive_insights`
* **Market-wide — `reports_market`:** `generate_trends_report` · `generate_market_radar` · `generate_box_office_report` · `generate_comingsoon_report` · `generate_release_calendar_report` · `generate_subscription_plans_report` · `generate_bundle_analysis_report` · `generate_promotional_offers_report` · `generate_overlap_report` · `generate_awards_report` · `generate_price_history_report` · `generate_genre_catalog_distribution_report`
* **Generic — `generate_report`:** a configurable report from assembled data, for when no specific report tool fits.

> Reports render in **English** regardless of the query language.

#### Data guide & methodology — `data_guide`

Metadata about the data itself and how the platform works — not the titles in it.

`list_available_data` · `check_data_freshness` · `explain_demand_scores` · `summarize_data_catalog` · `show_partition_keys_guide` · `confirm_title_match` · `ask_knowledge_base`

#### Advanced / raw data — `raw_data`

Direct query access, for bespoke exploration only.

`execute_sql` · `query_raw_data` · `export_full_query_to_csv` · `list_tables` · `get_table_schema`

> `execute_sql` and `query_raw_data` are a **last resort**. Before reaching for them, use the domain tools above — they're optimized, validate parameters, and return cleaner data.

***

<details>

<summary>Related Articles</summary>

* [MCP access](/insights/origin-insights-mcp/mcp-access.md)
* [Best practices](/insights/origin-insights-mcp/best-practices.md)

</details>

> We hope you found this article helpful. If you have a question this article doesn't address, reach out on the [Service Desk](https://fabric.atlassian.net/servicedesk/customer/portal/336).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://knowledgebase.fabricdata.com/insights/origin-insights-mcp/getting-started.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.