How to Use the Greptile MCP in Pydantic AI

Strictly validate every Greptile response in Pydantic AI for type-safe codebase navigation and reliable agent logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Greptile MCP to Pydantic AI

Create your Vinkius account to connect Greptile 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 Greptile with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Codebase Queries in Pydantic AI

Wrap your `query_codebase` calls in Pydantic models to ensure every response fits your schema. Pydantic AI will catch any unexpected data formats before they reach your logic. This prevents the silent failures that usually plague AI-driven code analysis. If the server returns a malformed response, the agent fails immediately, keeping your system in a known state.

Precise Repository Management for Pydantic AI

Manage your index with `index_repository` and `reindex_repository` while enforcing strict input validation. The Pydantic AI framework validates your tool arguments against the server's requirements. You get clear error messages if your repository configurations don't match the expected schema. This makes debugging your agent's interaction with the codebase much faster.

Audit Greptile Usage with Pydantic AI

Call `get_greptile_usage` to retrieve your API metrics in a typed format. You can easily integrate these numbers into your Pydantic-based dashboards. Tracking usage is essential when you require correctness above all else. By forcing these metrics into a strict model, you ensure your monitoring code never breaks due to API changes.

Setup guide

Set up Greptile 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": {
        "greptile-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Greptile 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 Greptile. 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 Greptile 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 Greptile MCP in Pydantic AI

Define a Pydantic model for your response schema. The framework automatically validates the raw data returned by the server against your model's fields.

Yes. The tools are exposed via the MCP toolset, allowing your agent to search and query code as easily as it would any other API.

No. The framework enforces runtime validation, meaning the agent will raise an error if the server returns data that doesn't match your expected types.

Yes. You can use Server-Sent Events to keep the connection alive while your agent processes code context.

Security is enforced through isolated indexing. Your code is processed privately, and only the validated, specific chunks you request are handled by your agent, keeping sensitive logic secure.

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