How do I find my LinkedIn Access Token?

Create a developer account at [**developer.linkedin.com**](https://developer.linkedin.com/), create an App, and perform the OAuth 2.0 flow to generate a token with the required permissions. Copy and paste it below.

Can the agent post to my company page?

Yes. Use the `create_post` tool providing the organization's URN as the author. Your agent will publish the content and confirm the status instantly.

Is it possible to see my primary email via the agent?

Yes. The `get_email` tool allows your agent to retrieve the primary email address associated with your LinkedIn account, ensuring your profile data is accurate.

LinkedIn MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: LinkedIn
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect LinkedIn through 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 LinkedIn "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in LinkedIn?"
    )
    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 LinkedIn MCP Server

Empower your AI agent to orchestrate your entire professional ecosystem on LinkedIn, the world's largest professional network. By connecting LinkedIn to your agent, you transform professional networking and publishing into a natural conversation. Your agent can instantly list your administered organizations, audit recent posts, and create new content without you ever touching a dashboard. Whether you are building a personal brand or managing a corporate page, your agent acts as a real-time professional assistant, ensuring your presence is always active and your networking data is organized.

Pydantic AI validates every LinkedIn tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through 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

Post Distribution — Create and publish new posts (UGC) directly to your profile or administered organization pages.
Organization Oversight — List all organizations where you have administrative access and retrieve detailed metadata.
Content Auditing — Query recent posts for any author URN to stay on top of your content strategy and engagement.
Profile Intelligence — Retrieve detailed authenticated user info and primary email to ensure organizational alignment.
URN Management — Quickly identify unique identifiers (URNs) for people and organizations to facilitate precise API operations.

The LinkedIn MCP Server exposes 6 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 LinkedIn to Pydantic AI via MCP

Follow these steps to integrate the LinkedIn 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 6 tools from LinkedIn with type-safe schemas

Why Use Pydantic AI with the LinkedIn MCP Server

Pydantic AI provides unique advantages when paired with LinkedIn 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 LinkedIn integration code

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

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

LinkedIn + Pydantic AI Use Cases

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

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

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

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

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

LinkedIn MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect LinkedIn to Pydantic AI via MCP:

create_post

Create a new post (UGC) on LinkedIn

get_email

Get primary email address of the authenticated user

get_me

Get authenticated user info from LinkedIn

get_organization

Get details for a specific organization

list_organizations

List organizations where the user is an administrator

list_posts

List recent posts for an author

Example Prompts for LinkedIn in Pydantic AI

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

"Get my LinkedIn profile and email."

"List all organizations I manage on LinkedIn."

"Create a public post on my profile: 'Excited to launch our new MCP servers!'"

Troubleshooting LinkedIn MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

LinkedIn + Pydantic AI FAQ

Common questions about integrating LinkedIn 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 LinkedIn MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.