How to Use the CRM PipeRun MCP in OpenAI Agents SDK

Q: How do I connect CRM PipeRun to OpenAI Agents SDK?

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Vinkius URL and pass it in the mcpservers array when creating your MCP agent.

Q: Can my agent upload attachments to deals?

Yes. The uploadfile tool handles base64 encoded data. Your agent can attach these files directly to deals, persons, or companies.

Q: How does OpenAI Agents SDK handle CRM PipeRun task updates?

The framework automatically discovers the updateactivity tool. You define the guardrails, and the agent modifies existing appointments or tasks based on those constraints.

Q: Will the agent know which activity types are valid?

It queries listactivitytypes before creating records. This guarantees that any new task matches your configured taxonomy.

Build production sales agents using OpenAI Agents SDK that manage activities and attachments in CRM PipeRun.

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 OpenAI Agents SDK

Create your Vinkius account to connect CRM PipeRun to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Sales Tasks with OpenAI Agents

The `create_activity` and `update_activity` tools let your agent schedule follow-ups and log calls directly in CRM PipeRun. When a specialized support agent finishes handling a ticket, it passes the context to a sales agent that immediately books a follow-up appointment. Passing this MCP Server to the Agent constructor makes these actions available with zero manual routing. You just set `cacheToolsList=True` to keep execution fast while OpenAI's tracing tracks exactly which activities were modified.

Attach Documents via MCP Server

Pushing contracts and proposals requires the `upload_file` tool, which accepts base64 encoded content and attaches it to specific deals or persons. Your agent pulls a signed PDF from a local directory, encodes it, and associates it with the correct company record in one step. Managing existing documents relies on `list_files` and `delete_file`. The agent filters attachments by deal ID, checks if an outdated proposal exists, and removes it before uploading the revised version.

Safe Pipeline Data Retrieval

Extracting current pipeline status happens through `list_activities` and `get_activity`. Built-in guardrails validate that the agent only pulls records relevant to the assigned sales rep before summarizing their daily tasks. Fetching the correct categorization uses `list_activity_types` to ensure new entries match your system's taxonomy. This prevents the agent from creating invalid task types and failing the API request.

Setup guide

Set up CRM PipeRun MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CRM PipeRun tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CRM PipeRun tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CRM PipeRun tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CRM PipeRun Agent",
            instructions="You have access to CRM PipeRun tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Initialize `MCPServerStreamableHttp` with your Vinkius URL and pass it in the `mcp_servers` array when creating your MCP agent.

Yes. The `upload_file` tool handles base64 encoded data. Your agent can attach these files directly to deals, persons, or companies.

The framework automatically discovers the `update_activity` tool. You define the guardrails, and the agent modifies existing appointments or tasks based on those constraints.

It queries `list_activity_types` before creating records. This guarantees that any new task matches your configured taxonomy.

Base64 file payloads and customer deal records process entirely within the Vinkius V8 Isolate Sandbox. The environment destroys itself immediately after the HTTP response completes, leaving no cached customer data behind.

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