CI
Hashicorp Terraform Cloud MCP connector
Connect Hashicorp Terraform Cloud to Elaichi and Claude, ChatGPT, Cursor and any MCP client can list, create, lock, unlock and update your Terraform Cloud workspaces, organizations and teams, with every call logged to a named person.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
290 tools
How to connect
How to connect Hashicorp Terraform Cloud to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Hashicorp Terraform Cloud once
-
Open Connections, choose Add connection, and pick Hashicorp Terraform Cloud.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Hashicorp Terraform Cloud API key. One person generates a token in Hashicorp Terraform Cloud and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect Hashicorp Terraform Cloud to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect Hashicorp Terraform Cloud to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect Hashicorp Terraform Cloud to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Hashicorp Terraform Cloud to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Hashicorp Terraform Cloud through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Platform
Lock a workspace before a risky change
Ask the agent to lock a Hashicorp Terraform Cloud workspace while you investigate a problem, then unlock it once the change is safe. Nobody can queue a run against it in the meantime.
-
DevOps
Spin up a workspace for a new service
Create a Hashicorp Terraform Cloud workspace with the right name and settings when a team starts a new project, and assign the SSH key it needs to pull private modules.
-
Security
Review who belongs to which team
List every team in a Hashicorp Terraform Cloud organization and see the details of each before an access review, without clicking through the console one team at a time.
-
Compliance
Check and set data retention policies
Ask what the data retention policy is on each Hashicorp Terraform Cloud organization, then create or update the ones that fall short of your standard.
-
SRE
Clear a stuck lock after a failed run
When a run dies and leaves a Hashicorp Terraform Cloud workspace locked, force unlock it from chat and get on with the fix instead of hunting for the button.
-
IT
Find every workspace across all organizations
Pull a single list of Hashicorp Terraform Cloud workspaces across every organization your account can see, with the settings on each, in one question.
Try asking
- “Which workspaces in the platform organization are currently locked?”
- “Create a workspace called payments-prod and assign the deploy SSH key.”
- “List every team in our production organization.”
AI tools
Hashicorp Terraform Cloud tools for your AI agents
290 tools are ready to call through Elaichi's MCP endpoint the moment you connect Hashicorp Terraform Cloud, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Hashicorp Terraform Cloud gets you
6 screens from the product, each doing one job for your Hashicorp Terraform Cloud account.
The agent
Ask about workspaces and get live answers.
Which Hashicorp Terraform Cloud workspaces are locked right now, answered from live records.
- workspaces
- organizations
- teams
- accounts
Ask Elaichi to work across your apps.
Which workspaces in the platform organization are currently locked?
Create a workspace called payments-prod and assign the deploy SSH key.
List every team in our production organization.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint for Claude, ChatGPT and Cursor.
Use Hashicorp Terraform Cloud from any MCP client, no SDK and no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
290 Hashicorp Terraform Cloud tools, no code needed.
Workspaces, organizations, teams and retention policies covered without writing a line of code.
- List all Hashicorp Terraform Cloud account
- Update a Hashicorp Terraform Cloud account by ID
- Hashicorp Terraform Cloud account change password
- List all Hashicorp Terraform Cloud organizations
ElaichiToolsToolboxes
Every team gets its own toolbox.
Platform keeps workspace locking, compliance sees retention policies, each toolbox scoped to a team.
- Platform
- DevOps
- Security
- Compliance
ElaichiToolboxesShared connections
Teammates work without ever seeing the token.
One person connects Hashicorp Terraform Cloud and shares it with teams and members.
- Platform
- Production
- Staging
- Security
ElaichiConnectionsAudit log
Know who locked which workspace, and when.
Every Hashicorp Terraform Cloud call is logged with who, what happened, type and resource.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule starts real work end to end.
Workspaces are fetched and grouped, a digest is drafted, approved, then posted back.
Hashicorp Terraform Cloud digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch workspaces
Hashicorp Terraform Cloud
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Hashicorp Terraform Cloud
Queued
Collections and dashboards
Workspace health, computed without a model.
Four metrics, 14 days of workspaces created and a breakdown by team, refreshed on schedule.
Hashicorp Terraform Cloud health
Refreshed 4 minutes ago · every 15 minutes · from the workspaces collection
Workspaces
1,284 ↓ 12%
Organizations
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Workspaces created
Last 14 days
By team
Share of activity
Platform 34%
Production 27%
Staging 21%
Security 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Hashicorp Terraform Cloud to Claude?
Connect Hashicorp Terraform Cloud in Elaichi by pasting a Terraform Cloud API token, then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. There is no OAuth application to register and no client ID or secret to generate. The whole thing takes a few minutes.
Does Hashicorp Terraform Cloud work with ChatGPT and Cursor as well as Claude?
Yes. Once Hashicorp Terraform Cloud is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any MCP client and the Elaichi Agent. You connect it once and every client picks it up.
What can an AI agent actually do with my Hashicorp Terraform Cloud data?
An agent can list and look up your Hashicorp Terraform Cloud organizations, workspaces, teams and accounts, create new workspaces and teams, lock, unlock or force unlock a workspace, assign or remove an SSH key, and view or change an organization's data retention policy. Because there are hundreds of actions, short concrete asks like lock the staging workspace work better than long sentences.
Does connecting Hashicorp Terraform Cloud give the AI access to every organization and workspace?
No. An agent working through Hashicorp Terraform Cloud only sees the organizations, workspaces and teams the signed-in person's token can already reach. Elaichi can narrow that access further with roles and restrictions, and it can never widen it beyond what Terraform Cloud itself allows.
Can I stop an agent from deleting or changing things in Hashicorp Terraform Cloud?
Yes. Restrictions in Elaichi work per action, so you can allow listing and locking Hashicorp Terraform Cloud workspaces while blocking anything that deletes an organization or changes a password. A blocked action is never advertised to the AI client at all, so no prompt can reach it.
What happens to a Hashicorp Terraform Cloud connection when someone leaves?
Offboarding a person in Elaichi ends their access to Hashicorp Terraform Cloud through every client at once. A connection they shared keeps working for everyone else on the team. If you want it gone entirely, disconnecting Hashicorp Terraform Cloud once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.
Put Hashicorp Terraform Cloud in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.