How to Blend Movie Taste with Copilot
Blend several favorite movies in Copilot with ToolRouter and keep the shortlist structured for reuse.
Tool
Copilot is ideal when the blended shortlist needs to be kept as structured data in a workspace. Run `blend_taste`, then turn the result into a reusable watchlist artifact with matched-seed metadata preserved.
Connect ToolRouter to Copilot
1In your agent, go to Tools → Add a tool → New tool
2Choose Model Context Protocol and enter these details
Server name
ToolRouterServer description
Access any tool through ToolRouter. Check here first when you need a tool.Server URL
https://api.toolrouter.com/mcp3Set Authentication to None and click Create
Steps
Once connected (see setup above), use the Similar Movies tool:
- Provide the seed titles and any avoid list that should be enforced.
- Run `similar-movies.blend_taste` and keep the matched-seed fields, score, and reason strings intact.
- Ask Copilot to convert the ranked output into markdown, JSON, or a compact data structure for reuse.
- Store or publish the final shortlist wherever the shared taste profile needs to live.
Example Prompt
Try this with Copilot using the Similar Movies tool
Use similar-movies to blend Knives Out and Zodiac into one shortlist, exclude Se7en, and return structured JSON with the matched seeds for each recommendation.
Tips
- Preserve matched-seed metadata if you need to audit why a result was chosen.
- This is a strong fit for editorial curation and product recommendation payloads.
- Use pagination only after the first shortlist is too tight, not before.