Is the integration read-only?

Yes. All tools only read from your Stoplight workspace — projects, nodes, schemas, and activity logs. No modifications or deletions are possible through this integration.

What is the workspace slug?

It's the subdomain of your Stoplight URL. For example, if your workspace is at `https://acme.stoplight.io`, the slug is `acme`. You can find it in the address bar when logged in.

What data can the agent access?

Projects, workspace members, activity logs, and all project nodes (endpoints, models, articles). Each node's full content — including OpenAPI schemas — can be retrieved via `get_node_details`.

Stoplight MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Stoplight
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Stoplight through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Stoplight "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Stoplight?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Stoplight MCP Server

Integrate the industry-leading API design and documentation capabilities of Stoplight into your conversational AI workflows. Empower your engineering teams to explore workspaces, evaluate OpenAPI schemas, and audit API projects natively from their conversational assistant. Securely map your AI to your Stoplight workspace, enabling the orchestration of complex documentation tasks, project navigation, and architectural reviews naturally without switching contexts or opening complex dashboards.

Pydantic AI validates every Stoplight tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Workspace Exploration — Rapidly inspect top-level organizational containers invoking list_workspaces, and track operational changes programmatically leveraging list_workspace_activity.
Project Management — Audit your API documentation repositories cataloging initiatives securely using list_projects, and retrieve full visibility metadata invoking get_project_details.
Schema & Documentation Discovery — Dive deeply into specific documentation structures retrieving files, endpoints, and models leveraging list_project_nodes, and parse their raw text safely utilizing get_node_details.
Team & Governance — Map project ownership accurately and enforce governance metrics iteratively assigning roles retrieving authorized contributors naturally via list_workspace_members.

The Stoplight MCP Server exposes 7 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Stoplight to Pydantic AI via MCP

Follow these steps to integrate the Stoplight MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 7 tools from Stoplight with type-safe schemas

Why Use Pydantic AI with the Stoplight MCP Server

Pydantic AI provides unique advantages when paired with Stoplight through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Stoplight integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Stoplight connection logic from agent behavior for testable, maintainable code

Stoplight + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Stoplight MCP Server delivers measurable value.

Type-safe data pipelines: query Stoplight with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Stoplight tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Stoplight and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Stoplight responses and write comprehensive agent tests

Stoplight MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Stoplight to Pydantic AI via MCP:

get_node_details

Retrieves details for a specific documentation node

get_project_details

Retrieves details for a specific Stoplight project

list_project_nodes

Lists all documentation nodes (files, endpoints, models) within a project

list_projects

Lists all projects in a specific Stoplight workspace

list_workspace_activity

Lists recent activity logs for a Stoplight workspace

list_workspace_members

Lists all members of a Stoplight workspace

list_workspaces

Lists all accessible Stoplight workspaces

Example Prompts for Stoplight in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Stoplight immediately.

"List my Stoplight projects and show recent workspace activity."

"Retrieve the detailed schema documentation for the processing node in our core billing API project."

"List all active members in the current workspace."

Troubleshooting Stoplight MCP Server with Pydantic AI

Common issues when connecting Stoplight to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Stoplight + Pydantic AI FAQ

Common questions about integrating Stoplight MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Stoplight MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.