SentientUI MCP server
Commit Nov 2, 2026Allows AI agents to access experiment data, manage UI variants, and analyze conversion performance directly from your development environment.
Also known as SentientUI/mcp
- Stars
- 1
- Tools
- 35
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 2, 2026
- License
- MIT
What is SentientUI MCP?
SentientUI allows AI agents to access experiment data, manage UI variants, and analyze conversion performance directly from your development environment. It exposes 35 tools, such as list_projects, create_project, get_project_stats.
Summary generated from the project's README
About SentientUI MCP server
Developers using Claude Code, Cursor, or Copilot can connect their AI assistants directly to SentientUI experiment data to manage UI variants and analyze performance. By providing a project-specific server key via environment variables or using an OAuth sign-in through a hosted endpoint, the server enables agents to interact with live experiment metrics and management actions from within the development environment.
The server provides a wide range of tools for data retrieval and project management. It allows agents to list projects, check ingestion health with get_project_stats, and examine component performance through get_variant_performance. It also supports creating and managing both code-native and no-code variants, enabling agents to pause, resume, or retire specific versions of a component based on real-time data.
Beyond simple metric viewing, the server facilitates advanced optimization tasks. Agents can use get_variant_brief to receive evidence-driven instructions for writing new code-native variants or use get_funnel_report to analyze step-by-step drop-off in conversion funnels. This integration turns an AI assistant into an active participant in the experimentation lifecycle, capable of interpreting insights and suggesting data-backed changes.
What you can do with it
- 1Optimize UI components with dataAsk your AI assistant to pull a performance brief and write a new code-native variant based on measured findings.
- 2Monitor experiment health and guardrailsCheck if any specific variants have been automatically paused by safety guardrails.
- 3Analyze conversion funnel drop-offRequest a detailed report on where users are dropping off within a multi-step conversion funnel.
- 4Manage no-code text variantsInstruct the agent to create a new text-only variant as a draft within the SentientUI dashboard.
Written from the project's README. Every use case is checked against a quote from it.
SentientUI MCP tools 35
Detected from the READMElist_projectscreate_projectget_project_statsadd_originlist_componentsget_variant_performanceget_variant_briefget_test_briefcreate_variantupdate_variantdelete_variant_draftpause_variant
Show all 35 toolsShow fewer tools
resume_variantretire_variantrestore_variantget_goal_funnellist_goalsdefine_goallist_funnelsget_funnel_reportlist_guardrail_eventsget_persona_breakdownget_stage_breakdownget_layout_statsget_insightsrefresh_insightsget_cell_matrixget_cell_detailgenerate_celllist_cell_reviewsreview_cellget_agent_trafficget_traffic_breakdownget_agent_legibilityget_integration_guide
Configuration
SENTIENTUI_API_KEY
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablesentientui/mcp is public and reachablegithub.com/sentientui/mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-02github.com/sentientui/mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model35 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub@sentientui/mcp
MCP server for SentientUI — gives AI agents in Claude Code, Cursor, and Copilot direct access to your experiment data and management actions.
Quick start
Prefer no key? You can skip local install entirely and connect your assistant to the hosted endpoint by URL with an OAuth sign-in — this is the only way to use SentientUI from web/app assistants (claude.ai, ChatGPT):
https://api.sentient-ui.com/mcpClaude Code:
claude mcp add --transport http sentientui https://api.sentient-ui.com/mcp. For stdio-only clients:npx mcp-remote https://api.sentient-ui.com/mcp. The rest of this README covers the local, key-based install below.
1. Get a server key
Dashboard → Project → Settings → API key → Server key → Generate, and copy it right away — it is shown only once. Available on every plan, including Free. A server key belongs to one project: it can read and change only that project, and generating a new one revokes the previous key (except keys held by a connected Shopify store).
2. Add to your AI assistant
Claude Code — one command:
claude mcp add sentientui -e SENTIENTUI_API_KEY=sk_your_key_here -- npx -y @sentientui/mcp
Or check a project-scoped .mcp.json into your repo:
{
"mcpServers": {
"sentientui": {
"command": "npx",
"args": ["-y", "@sentientui/mcp"],
"env": {
"SENTIENTUI_API_KEY": "sk_your_key_here"
}
}
}
}
Cursor — ~/.cursor/mcp.json:
{
"mcpServers": {
"sentientui": {
"command": "npx",
"args": ["-y", "@sentientui/mcp"],
"env": {
"SENTIENTUI_API_KEY": "sk_your_key_here"
}
}
}
}
VS Code + Copilot — .vscode/mcp.json:
{
"servers": {
"sentientui": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@sentientui/mcp"],
"env": {
"SENTIENTUI_API_KEY": "sk_your_key_here"
}
}
}
}
3. Restart your IDE. The server connects at startup.
Demo mode
No account? Run without an API key:
npx @sentientui/mcp
A demo token is provisioned automatically — 10 calls/month, read-only (write tools require an account with an sk_ key or an OAuth sign-in), no sign-up required. It points at an empty sandbox project with no fixture data, so the read tools return empty results: it shows the tool surface, not a populated example. The token is cached in ~/.config/sentientui/mcp-anon.json.
Tools
| Tool | Access | What it does |
|---|---|---|
list_projects |
read | List the projects this credential can see (an sk_ key sees only its own project) |
create_project |
write | Create a project and return its pk_ public key (account login only — not an sk_ key or demo token) |
get_project_stats |
read | Ingestion health: status, 24h events and People (with how many are being analysed or automated), and calls to the /v1/agent API (agentCalls — not MCP tool calls) |
add_origin |
write | Allow-list a site origin so the SDK's events from it are accepted (idempotent) |
list_components |
read | Adaptive components with variant counts and impressions |
get_variant_performance |
read | Per-(component, variant) rates with their n and the server's evidence verdict vs the baseline (range 7d/30d/90d/all or from/to; default 7d; the verdict judges the windowed rate, with all-time reliability reported separately) |
get_variant_brief |
read | Evidence-driven brief for writing a new code-native variant: per-arm rates with n and evidence verdicts, audience, measured findings, an evidence state (with a best-practice fallback while nothing is decided), and step-by-step code instructions |
get_test_brief |
read | Ready-to-paste test code (RTL, mock server, Playwright/Cypress) that forces one of a component's real variants |
create_variant |
write | Create a no-code managed text variant as a draft — fallback for text-only variants without a code change |
update_variant |
write | Edit a managed variant's name or text, or activate a draft (status: active — it starts serving) / move it back to draft |
delete_variant_draft |
write | Delete a managed variant that is still a draft |
pause_variant |
write | Pause a variant so no new traffic is assigned to it (undo with resume_variant) |
resume_variant |
write | Resume a paused variant — manual or guardrail pause |
retire_variant |
write | Retire (archive) an active variant (undo with restore_variant; a promoted variant must be unpromoted first) |
restore_variant |
write | Bring a retired variant back to active (does not unpause it) |
get_goal_funnel |
read | Per-goal conversion summary (windowed; default 30d) with descriptive all-time per-variant rates — not a step funnel (use get_funnel_report for drop-off); the id is kept for compatibility |
list_goals |
read | Defined goals (id, role, event, status), including ones with no conversions yet |
define_goal |
write | Create a new goal (secondary or guardrail). Create-only: refuses an existing goal id and never sets or changes the primary goal |
list_funnels |
read | Defined multi-step funnels |
get_funnel_report |
read | Step-by-step funnel drop-off |
list_guardrail_events |
read | Every variant currently paused by a guardrail (pass days to see only pauses from the last N days) |
get_persona_breakdown |
read | Visitor clusters with session counts and reliability (all retained sessions) |
get_stage_breakdown |
read | E-commerce funnel stages: stage mix, arrival channel x stage, stage moves between visits, tested holdout lift per first-visit context and channel (all-time), and versions per context (windowed, observational) |
get_layout_stats |
read | Per-persona section order with bandit pulls and reward (cumulative state) |
get_insights |
read | Ranked measured findings with their sample (low samples flagged), plus AI narrations marked unmeasured |
refresh_insights |
write | Regenerate AI insights — needs Starter or higher and an editor/admin role (a paid model call); advisor recommendations are Growth+ |
get_cell_matrix |
read | The "Who sees what" matrix of generated versions per visitor type and region |
get_cell_detail |
read | One cell's generated version, why it was written, and how it performs |
generate_cell |
write | Queue AI generation for one cell — publishes automatically, or waits for approval when review mode is on (Free includes 5 generations/month) |
list_cell_reviews |
read | Generated versions waiting for approval (review mode) |
review_cell |
write | Approve (publish) or reject one generated version waiting for review |
get_agent_traffic |
read | Which AI crawlers, automated browser sessions and agent API callers read the site (windowed; paid plans) |
get_traffic_breakdown |
read | Where traffic came from: People vs visitors we couldn't confirm vs automated (7 groups, windowed) |
get_agent_legibility |
read | Whether the pages agents read are machine-legible, with fixes (paid plans) |
get_integration_guide |
read | SDK setup guide (static — same for every project) |
Write tools ask first. Every write tool changes what real visitors see or what the project accepts, so an assistant should confirm with you before calling one. The common ones are reversible:
pause_variant→resume_variant,retire_variant→restore_variant,update_variantstatus: active→status: draft.Generated versions. An
<Adaptive id="…">that wraps your original as children (novariants) registers as a personalizable region once it is mounted and deployed. Its versions per visitor type are written in SentientUI — inspect and fill them withget_cell_matrix,get_cell_detail, andgenerate_cell— with no code change or redeploy. When the project has review mode on, a generated version waits inlist_cell_reviewsuntilreview_cellapproves it.Code-native vs no-code variants. Variants you declare in your app (
<Adaptive variants={{…}}>) register automatically the first time the SDK requests an assignment after you deploy — they go live immediately and need nocreate_variantcall. Usecreate_variantonly for no-code variants whose content is stored in SentientUI and rendered without a code change; these start as drafts — activate one withupdate_variant(status: active) or from the dashboard.Optimizing a component? Call
get_variant_brieffirst. It returns each variant's rate with its sample and the server's evidence verdict, the audience, measured findings, and an evidence-state assessment — then your AI assistant writes a new on-brand variant directly into your code (which auto-registers on deploy). While nothing is decided, the brief falls back to best-practice priors for your project's context type so the assistant still makes a sensible change.
Example prompts
- "What projects do I have?"
- "Show me the CVR trends for the hero banner this week"
- "Are any variants paused by the guardrail right now?"
- "What do the AI insights say about what changed this week?"
- "Refresh insights for project X"
- "Optimize my hero CTA — pull the brief and add a new variant in the code"
- "Create a new variant called 'short-copy' for the pricing CTA"
Configuration
| Environment variable | Default | Description |
|---|---|---|
SENTIENTUI_API_KEY |
— | Your sk_... server key. Required (or demo mode activates). |
SENTIENTUI_API_URL |
https://api.sentient-ui.com |
Override for staging or a custom API endpoint. |
Auth model
The server key you provide is passed as a Bearer token on every call to the SentientUI management API. It is scoped to one project: list_projects returns only that project, and calls naming any other project are refused. To work across several projects, connect by URL with an OAuth sign-in instead. Keys are never logged or stored by the MCP package; they exist only in the process environment.
Server keys start with sk_ (not pk_). Public keys (pk_) are for the browser SDKs (React, core, the script-tag snippet) and will be rejected by the management API.
AI agent context
AGENTS.md (included in this package) gives your AI assistant deeper context about SentientUI concepts, tool ordering, and common pitfalls. Wire it up once and it applies to every conversation.
| Assistant | How to use |
|---|---|
| Claude Code | Append to your project's CLAUDE.md (or ~/.claude/CLAUDE.md for every project) |
| Cursor | Copy to .cursor/rules/sentientui.mdc |
| GitHub Copilot | Append to .github/copilot-instructions.md |
| Other | Paste into your assistant's system prompt |
Requirements
- Node.js 18+
- A SentientUI account (or use demo mode)
SentientUI MCP questions
What tools does SentientUI MCP provide?
It exposes 35 tools, including list_projects, create_project, get_project_stats, add_origin, list_components.
How do I connect to SentientUI from web-based assistants like Claude.ai or ChatGPT?
You can connect by using the hosted endpoint URL with an OAuth sign-in.
Do write tools require confirmation?
Yes, write tools that change real visitor experiences or project settings will prompt the assistant to ask for your confirmation first.