How to Use the HeyReach MCP in Pydantic AI

Q: Can Pydantic AI validate HeyReach lead data?

Yes. When you call getleaddetails, the framework checks the returned profile information against your Pydantic model. If the API structure shifts, the agent fails loudly instead of processing corrupt data.

Q: How does a Pydantic AI agent handle HeyReach message sending?

The agent executes sendlinkedinmessage by passing a strictly typed JSON payload containing the conversationId and text. The framework ensures no malformed requests reach the API.

Build type-safe LinkedIn outreach agents that validate every HeyReach MCP Server response using 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 HeyReach MCP to Pydantic AI

Create your Vinkius account to connect HeyReach 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 HeyReach with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate LinkedIn account data at runtime

The `list_linkedin_accounts` tool pulls your active sender profiles and forces the output through your predefined schemas. If the API returns a missing account ID, Pydantic AI throws a validation error immediately. You use `get_api_profile` to verify your workspace connection before running any jobs. Here's the thing. The agent checks the basic account info and halts execution if the API key lacks the correct permissions, preventing silent failures later.

Manage campaigns with the HeyReach MCP Server

The `add_leads_to_campaign` tool expects a strict JSON array of names and profile URLs. Your Pydantic AI agent constructs this payload, validating every string type before it ever touches the network. You pull the target ID using `list_campaigns` first. If the campaign status changes unexpectedly, the agent triggers `pause_campaign` and logs a typed error report instead of hallucinating a successful run.

Process inbox messages with strict typing

The `list_conversations` tool fetches recent LinkedIn replies and maps them to your Pydantic models. Your agent parses the text, extracts the intent, and guarantees the output matches your exact expected schema. To reply, the agent fires `send_linkedin_message` using the validated conversation ID. It's simple. Because Pydantic AI is model-agnostic, you swap between Claude or local models without rewriting the payload validation logic.

Setup guide

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

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

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

Install the pydantic-ai-slim package with the MCP extra. Initialize an MCPToolset with your HTTP endpoint and pass it to your agent. This replaces the deprecated MCPServerHTTP approach.

Yes. When you call `get_lead_details`, the framework checks the returned profile information against your Pydantic model. If the API structure shifts, the agent fails loudly instead of processing corrupt data.

The agent executes `send_linkedin_message` by passing a strictly typed JSON payload containing the conversationId and text. The framework ensures no malformed requests reach the API.

Pydantic AI is completely model-agnostic. You run the LinkedIn outreach tools using Anthropic, OpenAI, or a local model, and the runtime validation remains identical across all of them.

The server processes target names, profile URLs, and direct message contents. Vinkius requires only one endpoint token and executes the tool inside an isolated sandbox. The memory wipes clean the second the validation completes.

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