Bring Onpipeline
to Pydantic AI
Learn how to connect Onpipeline to Pydantic AI and start using 11 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Onpipeline MCP Server?
Connect your Onpipeline account to any AI agent and take full control of your sales orchestration and pipeline management through natural conversation. Onpipeline is a powerful and intuitive CRM designed for high-velocity sales teams, and this integration allows you to retrieve deal metadata, update customer records, and monitor organization history directly from your chat interface.
What you can do
- Deal & Opportunity Orchestration — List all managed deals and retrieve detailed status metadata programmatically to ensure your sales pipeline is always synchronized.
- Contact & CRM Intelligence — Access and monitor your centralized database of persons and organizations directly from the AI interface to maintain high-fidelity customer profiles.
- Pipeline Discovery — Search through your sales stages and retrieve deal history via natural language to drive better forecasting efficiency.
- Lead Management Control — Create new deals, persons, and organization records using simple AI commands to reduce manual data entry.
- Operational Monitoring — Track system responses and manage organization-wide activity to ensure your sales workflows are always optimized.
How it works
1. Subscribe to this server
2. Enter your Onpipeline API Token from your account settings
3. Start managing your sales CRM from Claude, Cursor, or any MCP-compatible client
No more jumping between browser tabs to update a deal's status. Your AI acts as a dedicated sales coordinator or CRM lead.
Who is this for?
- Sales Representatives — quickly retrieve deal summaries and update prospect info without switching apps.
- Sales Managers — automate the retrieval of pipeline health metrics and track team activity via natural conversation.
- Operations Teams — streamline the retrieval of organization metadata and monitor organizational CRM health directly within the chat.
Built-in capabilities (11)
Create a new contact
Create a new deal
Create a new organization
Get details for a specific contact
Get details for a specific deal
List all CRM activities
List CRM contacts (persons)
List all sales deals
List calendar events
List CRM organizations (companies)
List all sales pipelines
Why Pydantic AI?
Pydantic AI validates every Onpipeline tool response against typed schemas, catching data inconsistencies at build time. Connect 11 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.
- —
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 Onpipeline integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Onpipeline connection logic from agent behavior for testable, maintainable code
Onpipeline in Pydantic AI
Onpipeline and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Onpipeline to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Onpipeline in Pydantic AI
The Onpipeline 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. All 11 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Onpipeline for Pydantic AI
Every tool call from Pydantic AI to the Onpipeline MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my AI automatically find the details for a specific deal by its ID?
Yes! Use the list_deals tool to find the Deal ID, then use your agent to retrieve full metadata for the opportunity, including status and associated contacts in seconds.
How do I find my Onpipeline API Token?
Log in to your Onpipeline account, navigate to Settings > API, and you will find your unique secret token there. Ensure you whitelist the IP 0.0.0.0 if you want to allow access from any cloud environment.
Does this work with custom fields?
Absolutely. This integration retrieves the full object metadata, allowing the AI to access and display values from any custom fields you've configured in your CRM.
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 Onpipeline MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai