Terraform MCP Server
The Terraform MCP Server is a Model Context Protocol (MCP)
server that integrates seamlessly with Terraform Registry and HCP Terraform APIs, enabling advanced
automation and interaction capabilities for Infrastructure as Code (IaC) development.
Table of Contents
Features
- Dual Transport Support: Both Stdio and StreamableHTTP transports with configurable endpoints
- Terraform Registry Integration: Direct integration with public Terraform Registry APIs for providers, modules, and policies
- HCP Terraform & Terraform Enterprise Support: Full workspace management, organization/project listing, and private registry access
- Workspace Operations: Create, update, delete workspaces with support for variables, tags, and run management
- OTel metrics for monitoring tool usage: Integration with open telemetry meters to track tool-call volume, latency and failures in Streamable HTTP mode. Also exposes default http server metrics when this feature is enabled
Security Note: Depending on the query, the MCP server may expose certain Terraform data to the MCP client and LLM. Do not use the MCP server with untrusted MCP clients or LLMs.
Legal Note: Your use of a third party MCP Client/LLM is subject solely to the terms of use for such MCP/LLM, and IBM is not responsible for the performance of such third party tools. IBM expressly disclaims any and all warranties and liability for third party MCP Clients/LLMs, and may not be able to provide support to resolve issues which are caused by the third party tools.
Caution: The outputs and recommendations provided by the MCP server are generated dynamically and may vary based on the query, model, and the connected MCP client. Users should thoroughly review all outputs/recommendations to ensure they align with their organization’s security best practices, cost-efficiency goals, and compliance requirements before implementation.
Prerequisites
- Ensure Docker is installed and running to use the server in a containerized environment.
- Install an AI assistant that supports the Model Context Protocol (MCP).
Command Line Options
Environment Variables:
| Variable | Description | Default |
|---|
TFE_ADDRESS | Sets the Terraform Enterprise/HCP Terraform address for API calls. Must include the protocol (e.g., https://app.terraform.io). In streamable-http mode this is the only way to set the address; it cannot be supplied by clients via header or query parameter. | Optional |
TFE_TOKEN | Terraform Enterprise API token | "" (empty) |
TF_MCP_SHARED_SECRET | Shared secret sent as the X-Tf-Mcp-Secret header on requests to HCP Terraform / TFE, used to identify requests originating from a hosted MCP deployment. Should only be used over TLS. | "" (empty) |
TFE_SKIP_TLS_VERIFY | Skip HCP Terraform or Terraform Enterprise TLS verification | false |
LOG_LEVEL | Logging level: trace, debug, , , , , (overrides flag) |
# Stdio mode
terraform-mcp-server stdio [--log-file /path/to/log] [--log-level info] [--log-format text] [--toolsets <toolsets>] [--tools <tools>]
# StreamableHTTP mode
terraform-mcp-server streamable-http [--transport-port 8080] [--transport-host 127.0.0.1] [--mcp-endpoint /mcp] [--organization-allowlist <orgs-csv>] [--log-file /path/to/log] [--log-level info] [--log-format text] [--toolsets <toolsets>] [--tools <tools>]
Instructions
Default instructions for the MCP server is located in cmd/terraform-mcp-server/instructions.md, if those do not seem appropriate for your organization's Terraform practices or if the MCP server is producing inaccurate responses, please replace them with your own instructions and rebuild the container or binary. An example of such instruction is located in instructions/example-mcp-instructions.md
AGENTS.md essentially behaves as READMEs for coding agents: a dedicated, predictable place to provide the context and instructions to help AI coding agents work on your project. One AGENTS.md file works with different coding agents. An example of such instruction is located in instructions/example-AGENTS.md, in order to use it commit a file name AGENTS.md to the directory where your Terraform configurations reside.
Usage with Bob IDE / Shell
More about using and adding MCP servers tools in Bob IDE or Shell Using MCP in Bob.
{
"mcpServers": {
"terraform": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e", "TFE_ADDRESS=<<PASTE_TFE_ADDRESS_HERE>>",
"-e", "TFE_TOKEN=<<PASTE_TFE_TOKEN_HERE>>",
"hashicorp/terraform-mcp-server:1.3.0"
],
"disabled": false
}
}
}
{
"mcpServers": {
"terraform": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"hashicorp/terraform-mcp-server:0.2.3"
],
"disabled": false
}
}
}
Building the Docker Image locally
Before using the server, you need to build the Docker image locally:
- Clone the repository:
git clone https://github.com/hashicorp/terraform-mcp-server.git
cd terraform-mcp-server
- Build the Docker image:
make docker-build
- This will create a local Docker image that you can use in the following configuration.
# Run in stdio mode
docker run -i --rm terraform-mcp-server:dev
# Run in streamable-http mode
docker run -p 8080:8080 --rm -e TRANSPORT_MODE=streamable-http -e TRANSPORT_HOST=0.0.0.0 terraform-mcp-server:dev
# Filter tools (optional)
docker run -i --rm terraform-mcp-server:dev --toolsets=registry,terraform
docker run -i --rm terraform-mcp-server:dev --tools=search_providers,get_provider_details
Note: When running in Docker, you should set TRANSPORT_HOST=0.0.0.0 to allow connections from outside the container.
- (Optional) Test connection in http mode
# Test the connection
curl http://localhost:8080/health
- You can use it on your AI assistant as follow:
{
"mcpServers": {
"terraform": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"terraform-mcp-server:dev"
]
}
}
}
Available Tools
Check out available tools here :link:
Available Resources
Check out available resources here :link:
Available Metrics
Two kinds of metrics are collected.
First, standard HTTP server metrics are added by wrapping the HTTP mux with otelhttp.NewHandler(...). This emits:
- http.server.request.body.size
- http.server.response.body.size
- http.server.request.duration
Second, the MCP server records custom tool metrics around tool execution using MCP hooks (BeforeCallTool / AfterCallTool). These emit:
- mcp_tool_calls_total
- mcp_tool_errors_total
- mcp_tool_duration_seconds
Tool Filtering
Control which tools are available using --toolsets (groups) or --tools (individual):
# Enable tool groups (default: registry)
terraform-mcp-server --toolsets=registry,terraform
# Enable specific tools only
terraform-mcp-server --tools=search_providers,get_provider_details,list_workspaces
Available toolsets: registry, registry-private, terraform, all, default. See pkg/toolsets/mapping.go for individual tool names. Cannot use both flags together.
Transport Support
The Terraform MCP Server supports multiple transport protocols:
1. Stdio Transport (Default)
Standard input/output communication using JSON-RPC messages. Ideal for local development and direct integration with MCP clients.
2. StreamableHTTP Transport
Modern HTTP-based transport supporting both direct HTTP requests and Server-Sent Events (SSE) streams. This is the recommended transport for remote/distributed setups.
Features:
- Endpoint:
http://{hostname}:8080/mcp
- Health Check:
http://{hostname}:8080/health
- Environment Configuration: Set
TRANSPORT_MODE=http or TRANSPORT_PORT=8080 to enable
- Organization Allowlist: Set
MCP_ORGANIZATION_ALLOWLIST or --organization-allowlist to a CSV list of allowed HCP Terraform organization names
Session Modes
The Terraform MCP Server supports two session modes when using the StreamableHTTP transport:
- Stateful Mode (Default): Maintains session state between requests, enabling context-aware operations.
- Stateless Mode: Each request is processed independently without maintaining session state, which can be useful for high-availability deployments or when using load balancers.
To enable stateless mode, set the environment variable:
export MCP_SESSION_MODE=stateless
Token Passthrough for Centralized Deployments
When running the MCP server centrally (StreamableHTTP mode) for multiple users, each user can pass their own Terraform token via HTTP headers for RBAC enforcement. This allows a single server instance to serve multiple users with different permissions.
When MCP_ORGANIZATION_ALLOWLIST or --organization-allowlist is configured, the allowlist must be a CSV list of HCP Terraform organization names. The server requires Authorization: Bearer <token> and rejects requests unless that token can access at least one organization in the CSV allowlist. The bearer token takes precedence if the request also includes a TFE_TOKEN header, ensuring the token validated by the allowlist is the token used for Terraform API requests. Organization name matching is case-insensitive. If the configured CSV value parses to zero organization names, the server exits with a malformed organization allowlist error.
Client IP Forwarding
When running the MCP server centrally behind a proxy or load balancer, you can forward the originating client's IP to HCP Terraform / TFE via the X-Forwarded-For header. This is off by default and must be enabled with MCP_FORWARD_CLIENT_IP=true.
When enabled, the server sources the client IP according to MCP_REMOTE_IP_METHOD:
| Method | Behavior |
|---|
RemoteAddr (default) | Uses only the address of the direct TCP connection. Ignores X-Forwarded-For and X-Real-IP. |
X-Real-IP | Uses the X-Real-IP header if it is a valid IP, otherwise falls back to RemoteAddr. |
X-Forwarded-For | Uses the X-Forwarded-For chain, selecting the entry MCP_XFF_TRUSTED_HOPS positions from the right. Falls back to RemoteAddr if the value is missing or invalid. |
Trust model
X-Forwarded-For and X-Real-IP are set by clients and intermediary proxies, so they can be spoofed unless a trusted proxy in front of the server overwrites them. For this reason the default is RemoteAddr, which trusts only the peer the server is directly connected to. Only enable X-Real-IP or X-Forwarded-For when the server sits behind a proxy you control that sets these headers.
Trusted hops
When using X-Forwarded-For, MCP_XFF_TRUSTED_HOPS is the number of proxies you operate between the server and the internet. Hops are counted from the right of the chain, since each proxy appends the address it received the request from and the rightmost entry is set by the proxy closest to the server. The server skips that many trusted entries and takes the next one to the left.
For example, with MCP_XFF_TRUSTED_HOPS=1 and a header of 200.1.2.3, 10.1.1.10, the server selects 200.1.2.3. With MCP_XFF_TRUSTED_HOPS=2 and 108.0.0.1, 200.1.2.3, 10.1.1.10, 192.168.0.1, it selects 200.1.2.3. If the hop count is greater than the number of entries, or the selected entry is not a valid IP, the server falls back to RemoteAddr.
Setting the hop count too low will trust a client-supplied value; setting it too high will trust an address further into your own infrastructure. Set it to the exact number of proxies you run.
Limitations
- The server reads only the first
X-Forwarded-For header on a request. It is valid for a request to carry multiple X-Forwarded-For headers, but Go's standard library returns only the first, and the server does not join them. If your proxy chain emits multiple headers, configure it to emit a single combined X-Forwarded-For header.
- IPv4 and IPv6 addresses are both supported. Values that are not valid IPs are rejected and the server falls back to
RemoteAddr.
Migrating from earlier versions
Earlier versions used the leftmost X-Forwarded-For value when the header was present, with no configuration. This was insecure, since the leftmost value is the most easily spoofed. The default is now RemoteAddr. If you run the server behind a proxy and rely on X-Forwarded-For being forwarded to HCP Terraform / TFE, set MCP_REMOTE_IP_METHOD=X-Forwarded-For and MCP_XFF_TRUSTED_HOPS to the number of proxies you operate.
Supported Headers
| Header | Description |
|---|
TFE_TOKEN | Terraform API token |
Authorization: Bearer <token> | Alternative method using standard Bearer auth |
TFE_SKIP_TLS_VERIFY | Skip TLS verification for the request |
Example: curl
# Using TFE_TOKEN header
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "TFE_TOKEN: your-user-token" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize",...}'
# Using Authorization Bearer header
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your-user-token" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize",...}'
Security Considerations
- TFE_ADDRESS cannot be set by clients. In streamable-http mode the Terraform address is sourced only from the server-side
TFE_ADDRESS environment variable (or the default). Requests that attempt to set TFE_ADDRESS via HTTP header or query parameter are rejected with a 403. This prevents a client from redirecting requests, and the Authorization token, to a malicious server.
- Hosted deployment identification: setting
TF_MCP_SHARED_SECRET sends that value as the X-Tf-Mcp-Secret header on every HCP Terraform / TFE request, letting the backend identify requests from a known hosted deployment (e.g. to apply IP allowlists). It is a static secret sent in a header, so only use it over TLS and treat the value as a credential.
- Never pass tokens in query parameters - the server will reject such requests with a 400 error.
- Always use TLS (
MCP_TLS_CERT_FILE/MCP_TLS_KEY_FILE) when deploying centrally to protect tokens in transit.
- Configure
MCP_ALLOWED_ORIGINS to restrict which clients can connect.
Centralized Deployment Example
# Start server centrally (no token set server-side)
docker run -p 8080:8080 \
-e TRANSPORT_MODE=streamable-http \
-e TRANSPORT_HOST=0.0.0.0 \
-e TFE_ADDRESS=https://tfe.company.com \
-e MCP_TLS_CERT_FILE=/certs/server.pem \
-e MCP_TLS_KEY_FILE=/certs/server-key.pem \
-e MCP_ALLOWED_ORIGINS=https://ide.company.com \
-e MCP_ORGANIZATION_ALLOWLIST=team-alpha,team-beta \
-v /path/to/certs:/certs \
hashicorp/terraform-mcp-server:1.3.0
Users then connect with their individual tokens passed via headers, enabling per-user RBAC enforcement.
Troubleshooting
Corporate Proxy / TLS Inspection (Zscaler, etc.)
If you're behind a corporate proxy that performs TLS inspection (like Zscaler Internet Access), you may see certificate errors:
tls: failed to verify certificate: x509: certificate signed by unknown authority
Solution: Mount your corporate CA certificate into the container:
docker run -i --rm \
-v /path/to/corporate-ca.pem:/etc/ssl/certs/corporate-ca.pem \
-e SSL_CERT_FILE=/etc/ssl/certs/corporate-ca.pem \
hashicorp/terraform-mcp-server:1.3.0
For MCP client configurations:
{
"mcpServers": {
"terraform": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v", "/path/to/corporate-ca.pem:/etc/ssl/certs/corporate-ca.pem",
"-e", "SSL_CERT_FILE=/etc/ssl/certs/corporate-ca.pem",
"-e", "TFE_TOKEN=<>",
"hashicorp/terraform-mcp-server:1.3.0"
]
}
}
}
Alternative: Run the binary directly
If Docker is not permitted in your environment, you can install and run the server binary directly, which will use your system's certificate store:
go install github.com/hashicorp/terraform-mcp-server/cmd/terraform-mcp-server@latest
terraform-mcp-server stdio
Development
Prerequisites
- Go (check go.mod file for specific version)
- Docker (optional, for container builds)
Available Make Commands
| Command | Description |
|---|
make build | Build the binary |
make test | Run all tests |
make test-e2e | Run end-to-end tests |
make docker-build | Build Docker image |
make run-http | Run HTTP server locally |
make docker-run-http | Run HTTP server in Docker |
make test-http | Test HTTP health endpoint |
make clean | Remove build artifacts |
make help | Show all available commands |
Contributing
- Fork the repository
- Create your feature branch
- Make your changes
- Run tests
- Submit a pull request
License
This project is licensed under the terms of the MPL-2.0 open source license. Please refer to LICENSE file for the full terms.
Security
For security issues, please contact security@hashicorp.com or follow our security policy.
Support
For bug reports and feature requests, please open an issue on GitHub.
For general questions and discussions, open a GitHub Discussion.