How to Use the Convex MCP in Pydantic AI

Q: How do I set up the Convex toolset in Pydantic AI?

You initialize the MCPToolset with your Vinkius HTTP endpoint URL. This unified setup registers these MCP tools directly with your Pydantic AI agent, enabling instant type-safe queries.

Run type-safe Convex queries and mutations validated at runtime with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Convex to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Convex Queries with Pydantic AI

The `run_query` tool fetches data from Convex and passes it to your Pydantic AI agent via this MCP tool. Instead of accepting unchecked JSON, the framework validates the query response against your target Python types at runtime. If your database returns an unexpected field or a missing value, Pydantic AI raises a validation error immediately. You catch bad data before it corrupts your agent's decision-making loop.

Validate Convex Mutations at Runtime

The `run_mutation` tool executes state writes to your database after verifying the arguments. Pydantic AI ensures that the arguments your model generates match your Convex schema perfectly before sending the write. This prevents silent database corruption. If the model hallucinates a field, the validation layer blocks the call on this MCP connection, forcing the agent to correct its own mistake.

Execute Actions Safely

The `run_action` tool runs side effects and external integrations through Convex actions. When your Pydantic AI agent triggers this tool, the arguments undergo the same strict type-checking as standard queries. You can also use `run_function` to target specific endpoints by their URL path. This keeps your agent's capabilities narrow and highly focused, reducing the chance of runtime errors.

Setup guide

Set up Convex MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "convex-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Convex tools.",
)

result = await agent.run("List recent Convex transactions")
print(result.output)

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 Pydantic AI

You initialize the `MCPToolset` with your Vinkius HTTP endpoint URL. This unified setup registers these MCP tools directly with your Pydantic AI agent, enabling instant type-safe queries.

Yes, the framework validates all arguments against your Pydantic models before calling `run_mutation`. This prevents the agent from sending malformed payloads to your Convex backend.

Yes, the server supports both streamable HTTP and SSE transports. You configure your Pydantic AI agent to connect to the external Vinkius URL using whichever transport fits your production architecture.

The framework raises a validation error immediately rather than letting the agent proceed with bad data. This strict behavior ensures your agent fails loudly instead of making decisions based on corrupted backend state.

All query results and mutation parameters are processed in ephemeral V8 isolates on Vinkius. Your actual Convex data is never stored, ensuring complete privacy for your database transactions.

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