MCP Safety Board · server report · November 2026
hashicorp/terraform-mcp-server
A
96 / 100
Grade A · ★ 1,562 · Go checked by hand
How the score was worked out
| Check | What was found | Points |
|---|---|---|
| Risky tools labelled | 2 of 13 tools whose name or description suggests delete, write or run declare neither destructiveHint nor readOnlyHint. −2 each. | −4 |
| Tools with any label | 57 of 68 tools (84%) carry any annotation; half or more. | 0 |
| README install command | The README has no npx / bunx / uvx / pnpm dlx launch command, so there is nothing to pin. | 0 |
| Committed config | No committed MCP config with an unpinned package, a moving tag, a broad filesystem root, a privileged docker server or plain http. | 0 |
| Score | 100 minus the penalties above (never below 0). | 96 |
Changes that would raise this grade
- +4Label the 2 tools that delete, write or run: add destructiveHint (or readOnlyHint) to their annotations. Alone, this gives 100 (A).
What was checked
- Commit checked
3e38ca694399- Repository
- github.com/hashicorp/terraform-mcp-server
- Tools found
- 68, of which 57 carry any label (84%)
- Risky tools
- 13, of which 11 labelled
- README install
- no npx/uvx snippet
- Last push
- 2026-11-13
Written in a language the source-code rules do not read, so only the tool, README and config checks were run.
Static reading of this one commit. No code was installed or run. This is a hygiene grade, not a security audit.
Maintainer?
Fixed something, or think a count is wrong? Request a re-check (opens a GitHub issue). Re-checks run on the latest commit.
README badge
[](https://mcp-safety-board.pages.dev/s/hashicorp--terraform-mcp-server.html)Want a written review of your agent's tools and permissions?
48-hour written review. Which tools your agent can call, what each one can change, which need a confirmation step, and what to lock down first. Send a message to start.