How to Use the LinearB MCP in Pydantic AI

Run type-safe pipeline analysis in Pydantic AI with strict runtime validation 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 LinearB MCP to Pydantic AI

Create your Vinkius account to connect LinearB 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 LinearB with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate engineering metrics with this MCP Server

The `query_software_metrics` tool fetches complex DORA and delivery data directly into your type-safe agent. This tool works with `list_engineering_teams` to ensure every team-specific metric matches your exact Pydantic schemas before your application processes them. Using this MCP Server with Pydantic AI guarantees that any unexpected API response triggers an immediate validation error instead of passing bad data. This strict validation prevents silent corruption in your automated reporting pipelines.

Track deployments with strict type safety

The `record_new_deployment` tool logs new code releases by binding specific git references to repositories retrieved via `list_connected_repos`. Your agent validates the repository ID and git ref formats before sending the payload to the API. Integrating this with Pydantic AI means your deployment agent cannot submit malformed registration requests. The framework enforces strict type checks on the inputs, protecting your delivery log integrity from bad manual entries.

Audit incidents with guaranteed schema compliance

The `list_software_incidents` tool retrieves active engineering outages for validation against your internal incident schemas. This tool pairs with `record_new_incident` to let your agent log new production failures with guaranteed field compliance. When you run these tools inside a Pydantic AI agent, every incident field is parsed and verified at runtime. If an incident payload lacks required timestamp formats, the agent catches the schema mismatch instantly.

Setup guide

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

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

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

Install the Pydantic AI slim package with the MCP extra enabled. Initialize your toolset using your server URL and pass it to your agent constructor to start running validated queries.

The Pydantic AI agent will raise a validation error at runtime. This prevents your application from consuming or displaying incorrect metrics if the API schema changes.

Yes, you can define a Pydantic model for deployment inputs that matches the tool requirements. Your agent will enforce these types, ensuring only valid repository IDs and git refs are sent to the API.

Yes, Pydantic AI is model-agnostic and works with local models or commercial APIs. You can run your agent locally to query deployments and incidents without sending data to external model providers.

Your repository names and deployment logs are parsed entirely in-memory using strict type schemas. All data transit occurs over secure, encrypted connections managed by the Vinkius hosting environment.

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