Compatible with every major AI agent and IDE
What is the ngrok MCP Server?
Connect your ngrok account to any AI agent and take full control of your ingress infrastructure through natural conversation.
What you can do
- Endpoints & Edges — List all active public URLs (ephemeral, edge, or cloud) and inspect HTTPS edges for advanced routing configurations
- Security & Access — Audit IP policies and restrictions applied to your dashboard, API, or agents to ensure secure access
- Domain Management — Retrieve all custom domains reserved for your applications directly from the ngrok cloud
- Credential Management — List API keys used for authentication and manage secure vaults for sensitive values
- Infrastructure Visibility — Get a bird's-eye view of your entire tunneling setup without leaving your terminal or chat interface
How it works
- Subscribe to this server
- Enter your ngrok API Key
- Start managing your tunnels and security from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps Engineers — quickly audit active endpoints and security policies across the organization
- Backend Developers — check reserved domains and HTTPS edge configurations during local development
- Security Teams — monitor IP restrictions and vault usage to maintain compliance and secure access
Built-in capabilities (7)
List ngrok API keys
List ngrok endpoints
List ngrok HTTPS edges
List ngrok IP policies
List ngrok IP restrictions
List ngrok reserved domains
List ngrok vaults
Why LlamaIndex?
LlamaIndex agents combine ngrok tool responses with indexed documents for comprehensive, grounded answers. Connect 7 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 ngrok tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain ngrok tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query ngrok, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what ngrok tools were called, what data was returned, and how it influenced the final answer
ngrok in LlamaIndex
ngrok and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect ngrok 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 ngrok in LlamaIndex
The ngrok 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 7 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
ngrok for LlamaIndex
Every tool call from LlamaIndex to the ngrok MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I see all my active public URLs currently served by ngrok?
Yes! Use the list_endpoints tool to retrieve all public URLs, whether they are ephemeral, edge-based, or cloud endpoints.
How do I check which custom domains I have reserved?
Simply ask the agent to run the list_reserved_domains action. It will return a list of all custom domains configured in your ngrok account.
Is it possible to audit my IP security policies?
Yes. You can use list_ip_policies and list_ip_restrictions to review the access control rules applied to your infrastructure.
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 ngrok 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 →
ChannelAdvisor (Rithum)
8 toolsManage multi-channel commerce via ChannelAdvisor — track products, inventory, and orders across global marketplaces directly from any AI agent.

ContactOut
7 toolsFind personal emails and direct phone numbers for professionals on LinkedIn to build targeted outreach lists that convert.

SeaTable
11 toolsBuild collaborative databases with spreadsheet simplicity and relational power for project management, CRM, and asset tracking.

Instamojo
10 toolsManage payments, refunds, and payouts via Instamojo API.
