Bring Customer Feedback
to LlamaIndex
Learn how to connect Refiner to LlamaIndex and start using 8 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Refiner MCP Server?
Connect your Refiner customer feedback account to any AI agent and simplify how you collect in-product insights, manage user segments, and monitor survey performance through natural conversation.
What you can do
- Survey Oversight — List all in-app, email, and link surveys and retrieve detailed status and response counts.
- Response Analysis — Query survey submissions with technical filters like UUIDs and date ranges to identify trends.
- Identity & Targeting — Identify users and upsert technical traits to ensure surveys reach the right audience.
- Event-Driven Feedback — Track high-fidelity user actions programmatically to trigger perfectly timed micro-surveys via AI.
- Segment Intelligence — List and query defined user segments to understand your audience distribution.
- Operational Monitoring — Check API health and verify account configurations directly from the agent.
How it works
1. Subscribe to this server
2. Enter your Refiner API Key (found in your project settings)
3. Start managing your feedback ecosystem from Claude, Cursor, or any MCP client
Who is this for?
- Product Managers — quickly check survey results and user sentiment via simple AI commands.
- Growth & Marketing — automate event tracking and verify segment metadata directly from the workspace.
- Customer Success — monitor individual user feedback and verify identity traits via the AI assistant.
Built-in capabilities (8)
Check API Status
Get contact details
Identify or update user
List product contacts
List survey responses
List user segments
List feedback surveys
Track user event
Why LlamaIndex?
LlamaIndex agents combine Refiner tool responses with indexed documents for comprehensive, grounded answers. Connect 8 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- —
Data-first architecture: LlamaIndex agents combine Refiner tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain Refiner tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query Refiner, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what Refiner tools were called, what data was returned, and how it influenced the final answer
Refiner in LlamaIndex
Refiner and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Refiner to LlamaIndex through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Refiner in LlamaIndex
The Refiner MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 8 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LlamaIndex only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Refiner for LlamaIndex
Every tool call from LlamaIndex to the Refiner MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check the responses for a specific survey via AI?
Yes! Use the list_refiner_responses tool and provide the Survey UUID. Your agent will retrieve the latest submissions, which you can then ask the AI to summarize or filter by date.
How do I identify a user and add custom traits using the agent?
Use the identify_refiner_user action. Provide the User ID or Email and a JSON string of traits (e.g., '{"plan":"pro"}'). This helps you target surveys based on specific user metadata.
Is it possible to track a custom event to trigger a survey via AI?
Absolutely. Use the track_refiner_event tool. Provide the event name and the user's ID/Email. When this event is logged, Refiner will trigger any surveys you have configured for that specific action.
How does LlamaIndex connect to MCP servers?
Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.
Can I combine MCP tools with vector stores?
Yes. LlamaIndex agents can query Refiner tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
Does LlamaIndex support async MCP calls?
Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.
BasicMCPClient not found
Install: pip install llama-index-tools-mcp