How to Use the CRM PipeRun MCP in Pydantic AI

Q: How do I add CRM PipeRun to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your Vinkius HTTP endpoint and provide it to your Agent's toolsets parameter.

Q: Can Pydantic AI manage CRM PipeRun files?

The framework supports uploadfile, getfile, and deletefile. Your agent can attach base64 encoded documents to specific deals or company records.

Bring strict type safety to your CRM PipeRun operations by connecting this MCP Server to 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 CRM PipeRun MCP to Pydantic AI

Create your Vinkius account to connect CRM PipeRun 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 CRM PipeRun with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Task Management

Triggering the `create_activity` and `update_activity` tools happens under strict runtime validation. If the CRM PipeRun API expects a specific integer for an assignee ID and the model hallucinates a string, Pydantic AI throws a validation error immediately. Reading existing tasks works the same way with `get_activity` and `list_activities`. The agent parses the returned JSON into strict Pydantic models, ensuring your Python code never crashes downstream due to missing fields.

Validate CRM Taxonomies

Discovering valid categories requires the `list_activity_types` and `get_activity_type` tools. The agent fetches the exact taxonomy your sales team uses before attempting to log new appointments or calls. Passing the `MCPToolset` to your agent makes these tools available across any LLM backend. You can swap between Anthropic or local models without rewriting a single line of tool execution code.

Handle Attachments via MCP Server

Pushing documents to records relies on the `upload_file` tool. The agent must provide exactly what the schema demands: base64 encoded content and a valid deal, person, or company ID. Managing the existing document list uses `list_files` and `delete_file`. Pagination parameters are validated before the request fires, preventing the agent from requesting impossible page numbers or invalid filter combinations.

Setup guide

Set up CRM PipeRun 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": {
        "crm-piperun-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your Vinkius HTTP endpoint and provide it to your Agent's `toolsets` parameter.

Pydantic AI catches it before the request leaves your machine. The framework validates the inputs for tools like `create_activity` against the exact schema and fails loudly on errors.

The framework supports `upload_file`, `get_file`, and `delete_file`. Your agent can attach base64 encoded documents to specific deals or company records.

Yes. Because Pydantic AI is model-agnostic, any compatible backend can execute the tools as long as it supports function calling.

Base64 document payloads travel through an isolated V8 environment managed by Vinkius. The server operates ephemerally, ensuring your proprietary sales agreements vanish from memory the moment the HTTP request concludes.

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