How do I find my HelpCrunch API Key?

Log in to your HelpCrunch dashboard, navigate to **Settings > Developers > Public API**. You will be able to generate and copy your unique Bearer token from there.

Can I reassign a chat to another team member?

Yes! Use the `update_chat_assignee` tool. You must provide the `chat_id` and the numeric `assignee_id` of the team member you wish to assign the conversation to.

How can I filter chats by status?

Use the `search_chats` tool and provide a JSON filter string. For example, to find open chats, pass `{"status": "open"}` in the `filter_json` parameter.

Is it possible to tag customers through this integration?

Yes, you can use the `add_customer_tag` tool. Provide the `customer_id` and the name of the tag you want to add to their profile.

HelpCrunch MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: HelpCrunch
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

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

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

Connect your HelpCrunch account to any AI agent and take full control of your customer communication and support workflows through natural conversation.

Pydantic AI validates every HelpCrunch tool response against typed schemas, catching data inconsistencies at build time. Connect 11 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

Chat Oversight — List all active and past conversations, retrieve full transcripts, and monitor response times.
Customer Management — Access detailed customer profiles, add descriptive tags, and track user interaction history.
Team Coordination — Reassign chats to specific team members or departments to ensure the right person handles every query.
Proactive Support — Search through chats using complex filters to identify trends or urgent customer issues.
Workflow Automation — Update chat statuses (closed, open, snoozed) directly from the chat interface.
Operational Efficiency — List support departments and monitor the overall health of your customer service operations.

The HelpCrunch MCP Server exposes 11 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 HelpCrunch to Pydantic AI via MCP

Follow these steps to integrate the HelpCrunch 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 11 tools from HelpCrunch with type-safe schemas

Why Use Pydantic AI with the HelpCrunch MCP Server

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

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

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

HelpCrunch + Pydantic AI Use Cases

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

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

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

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

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

HelpCrunch MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect HelpCrunch to Pydantic AI via MCP:

add_customer_tag

Add a label/tag to a customer profile

get_chat_details

Get detailed information about a specific chat

get_customer_details

Get detailed profile information for a specific customer

list_chat_messages

Useful for understanding context or historical interactions. List all messages within a specific chat

list_chats

Each chat includes basic metadata and status. List all conversations (chats) in HelpCrunch

list_customers

List all customers (contacts) in HelpCrunch

list_departments

List all support departments

search_chats

Pass filter criteria as a JSON string in "filter_json" (e.g., {"status": "open"}). Search for chats using filters

send_message

Pass the payload as a JSON string in "body_json" (e.g., {"chat": 123, "text": "Hello"}). Send a message to a chat

update_chat_assignee

Assign a chat to a specific team member

update_chat_status

Update the status of a chat (e.g., closed, open)

Example Prompts for HelpCrunch in Pydantic AI

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

"List all open chats and show the last message for each."

"Search for all chats from the customer with email 'john.doe@example.com'."

"Tag customer ID 5592 with 'VIP' and 'Priority Support'."

Troubleshooting HelpCrunch MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

HelpCrunch + Pydantic AI FAQ

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