Bring Infrastructure As Code
to OpenAI Agents SDK
Learn how to connect Terraform Cloud (HCP) to OpenAI Agents SDK and start using 42 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
Compatible with every major AI agent and IDE
What is the Terraform Cloud (HCP) MCP Server?
Connect your Terraform Cloud (HCP) account to any AI agent to orchestrate your Infrastructure as Code (IaC) workflows through natural language. This server provides comprehensive access to the HCP Terraform API, allowing for seamless management of the entire infrastructure lifecycle.
What you can do
- Organization & Project Management — List, create, and inspect organizations and projects to maintain high-level governance.
- Workspace Operations — Query workspaces, manage locks, and configure VCS integrations for automated deployments.
- Run & Plan Lifecycle — Trigger new runs, apply or discard plans, and monitor the progress of infrastructure changes in real-time.
- State & Outputs — Retrieve current state versions and extract specific output values to use in downstream automation or analysis.
- Governance & Security — Manage teams, access controls, variable sets, and Sentinel/OPA policies directly via the agent.
How it works
- Subscribe to this server
- Enter your Terraform Cloud User or Team API Token
- Start managing your cloud environments from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps & Platform Engineers — automate routine workspace management and run monitoring without leaving the terminal or chat.
- Cloud Architects — quickly inspect state outputs and policy compliance across multiple organizations.
- SRE Teams — troubleshoot failed runs and manage workspace locks during incident response.
Built-in capabilities (42)
Add a user to a team
Grant a team access to a workspace
Apply a planned run
Apply a variable set to a workspace
Associate a run task with a workspace
Cancel a run
Create a notification configuration for a workspace
Create a new organization
Create a policy
Create a policy set
Create a new project
Create a private registry module (No VCS)
Create a private registry provider
Create a new run (plan/apply)
Create a run task
Create a new state version
Create a new team
Create a variable set
Create a new workspace
Create a variable in a workspace
Destroy an organization
Discard a run
Execute an explorer query across workspaces
Force unlock a workspace
Get current state version for a workspace
Get JSON execution plan output
Get outputs for a state version
List organization audit events
List HCP Terraform organizations
List projects in an organization
List teams in an organization
List workspaces in an organization
Lock a workspace
Remove a user from a team
Safe delete a workspace
Show details of an apply
Show details of a specific organization
Show details of a plan
Unlock a workspace
Update an existing organization
Update a team
Upload code for a policy
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 42 tools from Terraform Cloud (HCP) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Terraform Cloud (HCP), another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Terraform Cloud (HCP) in OpenAI Agents SDK
Terraform Cloud (HCP) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Terraform Cloud (HCP) to OpenAI Agents SDK 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 | 4,000+ 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 Terraform Cloud (HCP) in OpenAI Agents SDK
The Terraform Cloud (HCP) 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 42 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK 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
Terraform Cloud (HCP) for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Terraform Cloud (HCP) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I trigger a new infrastructure deployment (run) using this server?
Yes. You can use the create_run tool by providing the Workspace ID. You can also subsequently use apply_run or discard_run to manage the lifecycle of that specific execution.
How do I see the output variables from my last successful Terraform apply?
Use the get_state_version_outputs tool with the Workspace ID. It will retrieve all calculated outputs from the current state, such as IP addresses, DNS names, or resource IDs.
Is it possible to list all workspaces across my organization?
Absolutely. Use the list_workspaces tool and provide your organization name. You can also filter the results by name or tags using optional parameters.
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.
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.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
RMSE & MAE Calculator
1 toolsCompute exact Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) for regression models. Stop hallucinating model validation metrics.

Mosaic (Resource Planning & Workforce Management)
12 toolsManage resource planning via Mosaic — track work plans, audit budget estimates, and monitor team capacity.

DeveloperHub
10 toolsEquip your AI agent to manage documentation projects, track pages, and monitor changelogs via the DeveloperHub API.

NewsCatcher
4 toolsSearch millions of news articles in real-time with AI clustering and topic tracking.
