How do I get an API Key for Freshsuccess?

Log in to your Freshsuccess account, navigate to Settings > Third-party integrations > API, and generate or copy your active token.

What is my 'Region Domain'?

Your domain depends on where your account is hosted (e.g. 'api-us.freshsuccess.com' for US Data Center, 'api-eu.freshsuccess.com' for Europe).

Can I update an account's metadata using the agent?

Yes! Use the 'upsert_cs_account' tool. Provide the unique Account ID and the new name to instantly update the record in Freshsuccess.

Is it possible to log custom product metrics?

Absolutely. You can use the 'post_metric_value' tool to send raw numeric data for specific accounts or users to influence their health scores.

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

Name: Freshsuccess
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 Freshsuccess 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 Freshsuccess "
            "(11 tools)."
        ),
    )

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

Connect your Freshsuccess (Freshdesk Customer Success) account to any AI agent to automate your customer retention and engagement operations through the Model Context Protocol (MCP). Freshsuccess empowers Customer Success Managers (CSMs) to prevent churn, increase expansion revenue, and proactively manage accounts. This MCP server enables you to track health scores, update user metadata, and log custom metrics directly through natural conversation.

Pydantic AI validates every Freshsuccess 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.

Key Features

Account Oversight — List all customer accounts, retrieve detailed profiles including health scores, and map assigned CSMs instantly.
User & Engagement Tracking — Access detailed end-user profiles, monitor product usage, and upsert records to ensure accurate data.
Proactive Alerts — Monitor configured customer success alerts (e.g., drop in usage, poor health) to prioritize interventions.
Task Management — Retrieve pending CSM tasks and to-dos to keep your team aligned on retention efforts.
Custom Metric Logging — Post specific product usage values or custom metrics directly to accounts and users to influence health scoring.
Data Synchronization — Ensure your CRM and CS platforms are perfectly aligned by automating record updates.

The Freshsuccess 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 Freshsuccess to Pydantic AI via MCP

Follow these steps to integrate the Freshsuccess 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 Freshsuccess with type-safe schemas

Why Use Pydantic AI with the Freshsuccess MCP Server

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

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

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

Freshsuccess + Pydantic AI Use Cases

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

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

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

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

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

Freshsuccess MCP Tools for Pydantic AI (11)

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

check_api_status

Verify API connection

get_account_health

Get account metadata

get_user_health

Get user metadata

list_cs_accounts

List customer accounts

list_cs_alerts

g. drop in usage). List active alerts

list_cs_tasks

List pending tasks

list_cs_users

List account users

list_custom_metrics

List defined metrics

post_metric_value

Record custom metric

upsert_cs_account

Create/Update account

upsert_cs_user

Create/Update user

Example Prompts for Freshsuccess in Pydantic AI

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

"List all active customer success alerts."

"Show me the health score for account 'acc_123'."

"Post a custom metric 'api_calls' with value 150 for user 'user_987'."

Troubleshooting Freshsuccess MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Freshsuccess + Pydantic AI FAQ

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