4,000+ servers built on vurb.ts
Vinkius

Infracost MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 13 tools to Create Guardrail, Create Price Book, Delete Guardrail, and more

MCP Inspector GDPR Free for Subscribers

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Infracost through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Ask AI about this MCP Server for OpenAI Agents SDK

The Infracost MCP Server for OpenAI Agents SDK is a standout in the Loved By Devs category — giving your AI agent 13 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
python
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Infracost Assistant",
            instructions=(
                "You help users interact with Infracost. "
                "You have access to 13 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Infracost"
        )
        print(result.final_output)

asyncio.run(main())
Infracost
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 Infracost MCP Server

Connect Infracost to your AI agent to bring financial visibility and governance to your Infrastructure as Code (IaC) workflows. Prevent cloud cost surprises before they happen.

The OpenAI Agents SDK auto-discovers all 13 tools from Infracost through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Infracost, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

  • Cost Guardrails — List, create, and manage guardrails that trigger alerts or block Pull Requests when cost increases exceed your defined thresholds.
  • Tagging Governance — Enforce organizational standards by updating tagging policies, ensuring all cloud resources are correctly attributed to departments or projects.
  • Custom Pricing — Manage enterprise-specific price books for AWS and Azure to ensure cost estimates reflect your actual negotiated discounts.
  • Business Context — Upload custom properties from external systems like ServiceNow or Backstage to map cloud costs to your internal organizational hierarchy.
  • Pricing Queries — Programmatically query cloud pricing data to compare costs across different resource types and regions.

The Infracost MCP Server exposes 13 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 13 Infracost tools available for OpenAI Agents SDK

When OpenAI Agents SDK connects to Infracost through Vinkius, your AI agent gets direct access to every tool listed below — spanning terraform, cloud-cost, finops, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

create

Create guardrail on Infracost

Create a new guardrail

create

Create price book on Infracost

Create a custom price book for an enterprise

delete

Delete guardrail on Infracost

Delete a guardrail

get

Get guardrail on Infracost

Get a specific guardrail by ID

get

Get price book on Infracost

Poll this to wait for SUCCESS status. Get the status and details of a price book

get

Get price book files url on Infracost

Use the returned URL to PUT the CSV file. Get a presigned URL to upload a price book CSV

ingest

Ingest price book on Infracost

Call this after uploading the CSV to the presigned URL. Trigger ingestion of an uploaded price book CSV

list

List guardrails on Infracost

List all guardrails for an organization

query

Query pricing on Infracost

Provide a valid GraphQL query string. Query the Cloud Pricing API using GraphQL

update

Update guardrail on Infracost

Update an existing guardrail

update

Update organization on Infracost

Pass the customPriceBookId to activate it. Update organization settings, such as activating a custom price book

update

Update tagging policy on Infracost

Update allowed tag values for a tagging policy

upload

Upload custom properties on Infracost

g., from ServiceNow or Backstage) for cost attribution. Provide raw CSV data. Upload custom business properties via CSV

Connect Infracost to OpenAI Agents SDK via MCP

Follow these steps to wire Infracost into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Install the SDK

Run pip install openai-agents in your Python environment
02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
03

Run the script

Save the code above and run it: python agent.py
04

Explore tools

The agent will automatically discover 13 tools from Infracost

Why Use OpenAI Agents SDK with the Infracost MCP Server

OpenAI Agents SDK provides unique advantages when paired with Infracost through the Model Context Protocol.

01

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

02

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

03

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

04

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Infracost + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Infracost MCP Server delivers measurable value.

01

Automated workflows: build agents that query Infracost, process the data, and trigger follow-up actions autonomously

02

Multi-agent orchestration: create specialist agents. one queries Infracost, another analyzes results, a third generates reports

03

Data enrichment pipelines: stream data through Infracost tools and transform it with OpenAI models in a single async loop

04

Customer support bots: agents query Infracost to resolve tickets, look up records, and update statuses without human intervention

Example Prompts for Infracost in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Infracost immediately.

01

"List all cost guardrails for the organization 'acme-corp'."

02

"Create a new guardrail for 'acme-corp' that triggers when cost increase exceeds $200 and blocks the PR."

03

"Update the tagging policy for 'acme-corp' to make the 'Environment' tag mandatory."

Troubleshooting Infracost MCP Server with OpenAI Agents SDK

Common issues when connecting Infracost to OpenAI Agents SDK through Vinkius, and how to resolve them.

01

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents
02

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Infracost + OpenAI Agents SDK FAQ

Common questions about integrating Infracost MCP Server with OpenAI Agents SDK.

01

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
02

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
03

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.

Explore More MCP Servers

View all →