Compatible with every major AI agent and IDE
What is the Flipt MCP Server?
Connect your Flipt instance to any AI agent to orchestrate feature management and progressive delivery through natural conversation.
What you can do
- Flag Management — List and inspect feature flags across different namespaces to understand your current feature states
- Targeting & Segments — Retrieve segments and create constraints to define specific user subsets for targeted rollouts
- Rollout Control — List rules and rollouts, and create distributions to manage percentage-based releases and canary deployments
- Variants — Create and manage flag variants to return different values based on evaluation logic
- Auth & Infrastructure — List authentication tokens and namespaces to understand your environment's structure and access levels
How it works
- Subscribe to this server
- Enter your Flipt URL and API Token
- Start managing your feature flags from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps Engineers — quickly audit rollout configurations and namespace partitions without leaving the terminal or IDE
- Product Managers — check the status of feature flags and segments to verify release progress
- Developers — create variants and constraints directly while coding to speed up feature implementation
Built-in capabilities (9)
Create a constraint for a segment
Create a distribution for a rule
Create a new variant for a flag
List flags in a namespace
List all namespaces
List rollouts for a flag
List rules for a flag
List segments in a namespace
List authentication tokens
Why LlamaIndex?
LlamaIndex agents combine Flipt tool responses with indexed documents for comprehensive, grounded answers. Connect 9 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 Flipt tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain Flipt tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query Flipt, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what Flipt tools were called, what data was returned, and how it influenced the final answer
Flipt in LlamaIndex
Flipt and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Flipt 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 | 4,000+ 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 Flipt in LlamaIndex
The Flipt 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 9 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
Flipt for LlamaIndex
Every tool call from LlamaIndex to the Flipt MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I list all feature flags in a specific namespace?
Yes! Use the list_flags tool and provide the namespaceKey (e.g., 'default'). The agent will return all flags configured within that partition.
How do I define a new variant for an existing flag?
You can use the create_variant action. You'll need to specify the namespaceKey, flagKey, and the new variant's key and name.
Is it possible to see the rollout configuration for a specific flag?
Absolutely. Use the list_rollouts tool by providing the target namespaceKey and flagKey to retrieve the current rollout strategy.
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 Flipt 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
Explore More MCP Servers
View all →
Dotloop
10 toolsManage real estate transactions via Dotloop — list loops, manage participants, and oversee documents.

Musixmatch
9 toolsLargest music lyrics database — search tracks, retrieve lyrics, and identify artists via AI.

Telebroad
12 toolsConnect your business phone system with cloud PBX that includes auto-attendant, call queues, and voicemail-to-email transcription.

HTMLCSSToImage
10 toolsGenerate high-quality images and PDFs from HTML/CSS or URLs directly from your AI agent.
