
Connect Infracost to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Stop infrastructure cost surprises before they hit your bill.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 13 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 13 available through Infracost.
- 01
Get guardrail
Retrieves a specific guardrail using its unique ID.
- 02
Get price book
Checks the current status and specific details of a price book.
- 03
Get price book files URL
Generates a presigned URL so you can upload a price book CSV file.
- 04
Ingest price book
Triggers the ingestion process for a price book after you upload the CSV.
05-07
3 capabilities in this set.
Part of 13 available through Infracost.
- 05
Upload custom properties
Uploads custom business properties via CSV to help with cost attribution.
- 06
Create price book
Sets up a new custom price book for your enterprise.
- 07
Delete guardrail
Removes an existing guardrail from your organization.
08-10
3 capabilities in this set.
Part of 13 available through Infracost.
- 08
List guardrails
Shows all active guardrails currently set for your organization.
- 09
Query pricing
Runs a GraphQL query against the Cloud Pricing API to get specific cost data.
- 10
Update organization
Updates organization settings, such as activating a new custom price book.
11-13
3 capabilities in this set.
Part of 13 available through Infracost.
- 11
Update tagging policy
Modifies the allowed values for tags within a specific tagging policy.
- 12
Create guardrail
Sets up a new cost guardrail to monitor your infrastructure changes.
- 13
Update guardrail
Edits the parameters of an existing guardrail.
Real work
What teams actually run
Automated PR Blocking
An engineer submits a Terraform change that would double the monthly spend. The agent detects this via a guardrail and blocks the PR automatically.
Discount Management
A FinOps lead updates the enterprise price book through the agent to ensure all new cost estimates include negotiated AWS discounts.
Tagging Compliance
The agent updates a tagging policy to require a 'ProjectID' tag, ensuring all new resources are correctly billed to the right cost center.
Cost Attribution
You upload custom properties from Backstage to the agent to map cloud resources to specific internal teams.
Automate a task
Put Infracost to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Infracost works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Infracost to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
1091ms average. Fast in production.
Infracost is checked daily against the live service.
- Fastest day
- 811ms
- Slowest day
- 1271ms
- 14-day trend
- Slowing+14%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 13 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Infracost, so you can see the experience inside your AI.
It does not authenticate your account with Infracost. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Infracost Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_xeAIkzobHaNXul6wABfvaOhG1zW1KbvYBWGhp0O0/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Infracost capabilities are ready to use.
{
"mcpServers": {
"infracost-mcp": {
"url": "https://edge.vinkius.com/vk_preview_xeAIkzobHaNXul6wABfvaOhG1zW1KbvYBWGhp0O0/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Infracost in Claude and other AIs
Who it's for
Built for the work Infracost owners hand off.
This MCP is built for teams that need to bridge the gap between infrastructure code and financial accountability.
- 01
DevOps Engineers
They use the agent to automate cost policy enforcement within CI/CD pipelines.
- 02
FinOps Teams
They use the agent to manage enterprise discounts and track spend without manual spreadsheets.
- 03
Engineering Managers
They use the agent to set budget limits and get summaries of cost impacts for new changes.
FAQ
Questions Infracost owners ask.
- 01
How does this MCP help with Terraform costs?
It allows your AI agent to interact with Infracost to set guardrails, manage pricing, and enforce policies directly related to your Terraform infrastructure.
- 02
Can I use my own negotiated cloud discounts?
Yes. You can create and manage custom enterprise price books for AWS and Azure to ensure your cost estimates are accurate to your actual rates.
- 03
What AI clients can I use with this MCP?
You can connect this MCP to any compatible client, including Claude, Cursor, Windsurf, and VS Code.
- 04
How do I enforce tagging standards?
You can use the agent to update tagging policies, which allows you to mandate specific tags for all managed cloud resources.
- 05
Does this work with AWS and Azure?
Yes, the MCP supports managing custom price books for both AWS and Azure to reflect enterprise-specific pricing.
- 06
How can I see all active cost guardrails for my organization?
You can use the list_guardrails capability by providing your organization slug. The agent will return a list of all configured thresholds, including cost increase limits and whether they block PRs.
- 07
Can I enforce mandatory tags for my cloud resources using this server?
Yes! Use the update_tagging_policy capability to define mandatory tag keys and allowed values. This helps maintain standards across all your repositories.
- 08
Is it possible to block expensive Pull Requests automatically?
Absolutely. When using create_guardrail or update_guardrail, you can set the blockPr parameter to true. This ensures that any infrastructure change exceeding your budget cannot be merged without review.
Explore
More in Loved By Devs
Civo (Cloud-native Kubernetes Cloud Provider API) AI Connector
Manage Civo cloud infrastructure — provision Kubernetes clusters, control compute instances, and monitor usage
ViewJD Cloud Infrastructure AI Connector
Manage JD Cloud supply-chain infrastructure from your AI. Control VMs, disks, databases, and monitor resource
ViewTerraform Cloud (HCP) AI Connector
Manage infrastructure lifecycle via Terraform Cloud (HCP) — list organizations, manage workspaces, trigger run
ViewDoiT AI Connector
Equip your AI agent to manage cloud costs, track assets across AWS/GCP/Azure, and monitor cost anomalies via t
View
Suggestions
OpenCost (K8s Cost) AI Connector
Monitor and analyze Kubernetes infrastructure costs — query workload allocations, backing assets, and cloud bi
ViewJD Cloud / 京东云 AI Connector
China's leading supply chain cloud platform — manage VMs, storage, and cloud infrastructure via AI.
ViewConstruction Cost Estimator AI Connector
Instantly get a precise cost range estimate for any construction project using area, local region data, and de
ViewAI Infrastructure Cost Optimizer AI Connector
Calculate potential savings and implementation costs for AI computing infrastructure.
View
Connect Infracost to Claude, Cursor, ChatGPT & more
