How to Use the MintMCP MCP in LlamaIndex

Q: How does MintMCP enforce data access policies in LlamaIndex?

The gateway uses mintmcpgettoolpolicy to fetch the SOC2 governance parameters for any tool LlamaIndex tries to run on the MCP. If the user query lacks the right RBAC permissions, the gateway blocks the action before execution.

Q: Can LlamaIndex audit its tool executions via MintMCP?

Yes, mintmcpfetchauditlogs dumps systematic telemetries of all tool executions triggered by your LlamaIndex agent. You can index these logs back into LlamaIndex to let users query past execution history.

Q: How does a LlamaIndex app discover approved tools using MintMCP?

Call mintmcplistavailabletools to audit the approved tools inside your virtual server. This ensures your LlamaIndex client only indexes and presents tools that have passed local security compliance.

Q: What happens when an active session is revoked?

When mintmcprevokeaccesstoken is called, the gateway immediately cuts the active OAuth flow. Any subsequent tool execution attempt by your LlamaIndex agent will be blocked instantly by the MCP gateway.

Build secure, knowledge-augmented LlamaIndex applications with the MintMCP gateway.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MintMCP MCP to LlamaIndex

Create your Vinkius account to connect MintMCP to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup MintMCP with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index secure virtual servers into LlamaIndex

`mintmcp_list_virtual_servers` exposes your isolated tool environments so LlamaIndex can map them to specific knowledge indices. You query this tool to discover which functional groups are active before building your query engines. This lets you build multi-tenant RAG pipelines. Your indexing code reads the server structures, ensuring users only search and retrieve tool outputs from virtual servers they are explicitly allowed to access.

Guardrail live API data before indexing

`mintmcp_eval_guardrail` filters sensitive data out of tool execution outputs before LlamaIndex writes them to your vector database. It checks parameter strings and API responses for PII, preventing leaks in your searchable knowledge base. This keeps your vector store clean and compliant. You run this check on every live tool execution, so your indexed data remains free of high-risk credentials or personal info across the MCP connection.

Retrieve configuration schemas for indexing

`mintmcp_get_virtual_server` extracts the exact configuration patterns of a specific virtual server schema. Your LlamaIndex application uses this schema data to understand the context of the tools it is querying. By indexing these configurations, your agent can ground its answers in your actual infrastructure layout. It prevents hallucinations by providing the exact schema layout to your MCP Server client.

Setup guide

Set up MintMCP MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all MintMCP MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to MintMCP tools.",
)
response = await agent.run("List recent MintMCP data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by MintMCP. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect MintMCP now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about MintMCP MCP in LlamaIndex

The gateway uses `mintmcp_get_tool_policy` to fetch the SOC2 governance parameters for any tool LlamaIndex tries to run on the MCP. If the user query lacks the right RBAC permissions, the gateway blocks the action before execution.

Yes, `mintmcp_fetch_audit_logs` dumps systematic telemetries of all tool executions triggered by your LlamaIndex agent. You can index these logs back into LlamaIndex to let users query past execution history.

Call `mintmcp_list_available_tools` to audit the approved tools inside your virtual server. This ensures your LlamaIndex client only indexes and presents tools that have passed local security compliance.

When `mintmcp_revoke_access_token` is called, the gateway immediately cuts the active OAuth flow. Any subsequent tool execution attempt by your LlamaIndex agent will be blocked instantly by the MCP gateway.

The gateway never stores parameter strings or access tokens. All data processed via `mintmcp_run_tool_action` is held in memory inside an ephemeral sandbox and wiped clean the millisecond the execution finishes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript