Optimal's MCP (Model Context Protocol) server lets Claude securely pull your research data straight out of Optimal, so you can ask natural-language questions and dive deeper into your research.
These steps are written for Claude. The same Optimal MCP server also works with other MCP-compatible AI assistants, including Cursor, ChatGPT, Microsoft Copilot, Gemini, and other custom MCPs.
Requirements
Claude
Free, Pro, Max, Team, or Enterprise plan. Free plans are limited to one custom connector.
Optimal
An active Optimal account, with access to the workspace(s)/studies you want Claude to read from.
MCP enabled for your Optimal workspace. If you do not have access, please get in touch with your admin to enable MCP under the Features tab.
Who can connect
Claude Free, Pro, or Max plans: any individual user can add the Claude connector themselves. You do not need to be an admin.
Claude Team or Enterprise plans: an Owner or Primary Owner must add the Claude connector once at the organization level (Organization Settings > Connectors). After that, each user can connect Claude with their own Optimal account.
Connect Claude to Optimal
Open Connectors settings.
Claude Free, Pro, or Max Users:
Go to Customize (or Settings) in Claude > Connectors.Claude Team & Enterprise Owners:
Go to Organization Settings in Claude > Connectors.
Add a custom connector. Click the "+" button and choose Add custom connector.
Enter Optimal's MCP server details.
Name: Optimal
Server URL:
https://app.optimalworkshop.com/mcp
Click Add. No OAuth Client ID/Secret is required. Leave Advanced settings blank.
Authenticate. Claude will prompt you to sign in to Optimal. Log in with your normal Optimal credentials and approve access. Claude only sees the workspaces/studies your account already has permission to view.
Enable it in a conversation (optional). Connectors are generally available by default once added, but if you don't see Optimal in a given conversation, click the "+" in the chat box, choose Connectors, and toggle Optimal on for that conversation.
Note that MCP is evolving rapidly, so this guidance may change. Please refer to the latest documentation from Claude for any updates.
What can Claude read?
Claude can only read your Optimal data. It can't create, edit, or delete anything in Optimal, and it only sees what your own user login already has access to.
Study setup & metadata — study configuration and metadata (names, methodology, dates, etc.); tags, observations, and notes added by your team
Participant results — task results, success/completion metrics, and clickmaps/paths for prototype & usability tests; aggregated survey response distributions for structured questions (radio, checkbox, rating, etc.). Open-text/free-form survey answers are not currently surfaced through the MCP.
Recordings & transcripts — session and transcript counts for interview studies. Raw recordings and playback (video/audio) are not retrieved directly — what's exposed is derived from them (counts, AI analysis), not the recording files themselves.
AI-generated outputs — AI-generated study summaries, plus categorized insights such as themes, pain points, opportunities, sentiment, behaviours, and mental models, each with source/citation counts; task-, section-, and study-level analysis
Example prompts
These are just a few examples to get you started. You're not limited to this phrasing or these topics. Ask Claude in your own words; it can handle a much wider range of questions across your Optimal data.
"What were the biggest usability issues across our last five prototype tests?"
"Summarize participant feedback for our onboarding flow."
"What themes emerged from our customer interviews this quarter?"
"Compare findings between our March and June studies."
Things to know
Access mirrors your Optimal permissions. Claude can only retrieve data from workspaces/studies you can already see.
Claude connects to Optimal's MCP server from Anthropic's cloud, not your local device. No local install or firewall changes are typically needed.
Questions? Please get in touch with our team or share your feedback via our feedback and features request form.