Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Productivity
  4. /
  5. Motif Research MCP
Productivity
Motif Research MCP icon

Motif Research MCP

by sleepycobalt

Motif MCP turns a folder of interview transcripts into cited findings and checks them with a critic loop. It runs inside MCP hosts such as Claude Code, Cursor and Claude Desktop.

Plugin·Contact for pricing

Visit registry.modelcontextprotocol.io(opens in a new tab)

About Motif Research MCP

Key features of Motif Research MCP

  • motif_synthesize builds insights and a report from transcripts, with a run id and cost
  • motif_critique checks insights or a document against the transcripts
  • motif_receipts returns the verbatim turn text behind any cited turn id
  • motif_board produces a FigJam layout and scripts to run through Figma's MCP server
  • motif_runs_get returns run metadata, notes and per-iteration verdicts
  • Progress is streamed as MCP log and progress notifications
  • Failures return MCP tool errors rather than empty successes

Who Motif Research MCP is for

  • UX researchers synthesising interviews
  • Product designers working in agent environments
  • Teams who want findings traced back to quotes
  • Users of Claude Code, Cursor or Claude Desktop

How to use Motif Research MCP

  1. 1

    Step 1: Install with pip install "etot-motif[mcp]", or run it through uvx, and find the absolute path to motif-mcp.

  2. 2

    Step 2: Set ANTHROPIC_API_KEY in the environment or in the server's env config.

  3. 3

    Step 3: Register the server in your host, for example claude mcp add motif -- followed by the path to motif-mcp, or add it to Cursor's or Claude Desktop's MCP config.

  4. 4

    Step 4: Restart the host and check that the motif tools appear.

  5. 5

    Step 5: Ask the agent to synthesise a transcripts folder, then use motif_receipts to verify any citation.

Motif Research MCP FAQ

Does Motif need an API key?

Yes. The server reads ANTHROPIC_API_KEY from the environment or a .env file. In remote mode the key is forwarded with each job and used for that job only.

Where do run logs go?

Installed from PyPI, the server writes run logs to ~/.motif/runs. You can change the location with MOTIF_RUNS_DIR.

Does it write to Figma?

No. motif_board only returns a layout and scripts. The host runs them through Figma's MCP server.

Technical details

Requirements

  • An MCP-compatible client; provider credentials or local runtime dependencies may be required.

Details

Pricing
Contact for pricingFree to use: the code is MIT licensed and the data is CC-BY-NC. You supply your own Anthropic API key. A paid hosted tier is mentioned but not switched on yet.
Type
Plugin
Platforms
  • CLI
  • MCP
Categories
ProductivityAIResearch
Added
Sep 17, 2026
sleepycobalt iconPublishersleepycobalt

Built from public sources

We put this page together from Motif Research MCP’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with Motif Research MCP.

Work at Motif Research MCP? Claim the listing to manage it yourself.

Something wrong here?

Related tools

See more
IMInquisitor MCPInquisitor · Contact for pricingInquisitor is an MCP server and agent skill that makes AI agents solve problems by testing hypotheses instead of retrying blindly. It estimates depth from a cheap first probe and keeps a record of failed ideas.Productivity · Contact for pricingQY Evolution MCP iconQY Evolution MCPQianyuan · Contact for pricingQianYuan is an identity, trust and result-reuse layer for autonomous agents, reachable through an MCP endpoint. Agents publish results they have already produced, and other agents reuse them to save tokens.Productivity · Contact for pricingPerplexity Hybrid Compute iconPerplexity Hybrid ComputePerplexity · Contact for pricingHybrid AI mode that keeps private-file work on a Mac while using cloud models for research and reasoning.Productivity · Contact for pricing