How to Use the Convex MCP in LlamaIndex

Q: Is it possible to run custom Convex actions from LlamaIndex?

Absolutely. Your agent can call runaction to run complex server-side tasks whenever a search query requires external processing.

Q: How do slash paths work with the function tool?

You call runfunction and pass the path using a slash instead of a colon. This matches standard HTTP routing and keeps your backend clean.

Index your Convex database records directly into LlamaIndex vector stores using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convex MCP to LlamaIndex

Create your Vinkius account to connect Convex 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 Convex with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Convex MCP Server data for semantic search

Stop querying your database with rigid filters. By running `run_query`, your agent pulls fresh table rows and immediately indexes them into a vector store for fast similarity search. This bridges the gap between static documents and live transactional data. Your search queries now yield results grounded in actual, real-time backend state.

Executing mutations based on retrieved context

Your agent can make smart database writes after searching your index. It uses `run_mutation` to insert or update records once it finds the relevant context. This setup prevents duplicate entries and outdated information. The agent checks the current index first, reasons about the gap, and writes the fix.

Triggering remote backend actions

Sometimes searching and writing data isn't enough to solve a user query. Running `run_action` allows your agent to run complex, multi-step backend code directly on your servers. You can target specific endpoints using `run_function` with standard slash-path syntax. This keeps your local agent lightweight while offloading processing to the cloud.

Setup guide

Set up Convex 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 Convex 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 Convex tools.",
)
response = await agent.run("List recent Convex 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 Convex. 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 Convex 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 Convex MCP in LlamaIndex

Initialize the Convex MCP client with your Vinkius endpoint and convert the tools. You can then run `run_query` to fetch records and load them directly into your index pipeline.

Yes, your agent can make decisions based on retrieved context. It then uses `run_mutation` to update your backend tables with the new information.

Absolutely. Your agent can call `run_action` to run complex server-side tasks whenever a search query requires external processing.

You call `run_function` and pass the path using a slash instead of a colon. This matches standard HTTP routing and keeps your backend clean.

Your database rows and schema definitions are processed in an ephemeral sandbox. Vinkius operates under a zero-trust model, meaning your raw data is never cached or stored.

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