TestRailSAFE
AI-native MCP server connecting Claude, Cursor, Windsurf, and other AI assistants to TestRail — manage test cases, runs, and results through natural-language conversation, with typed schemas built for LLMs.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
🚀 TestRail MCP Server
Connect Claude, Cursor, Windsurf, and VS Code to TestRail — an open-source Model Context Protocol (MCP) server for AI-assisted test management.
Manage TestRail projects, search and create test cases, kick off test runs, record results, and attach files through natural-language conversation with your AI assistant — or from CI/CD with the bundled testrail-cli. Built for QA engineers and AI-assisted test automation.
cb6784a89c8fOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add testrail-mcp-server --env TESTRAIL_API_KEY=${TESTRAIL_API_KEY} -- npx -y @uarlouski/[email protected]Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Authentication | read | Auth tests |
Billing | read | Billing root |
Checkbox | read | Boolean value, either true or false. |
General | read | |
Invoices | read | Invoice tests |
Login | read | Login tests |
OAuth | read | OAuth sub-tests |
test_tool | read | A test tool for unit verification |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (13)
.mcpbignore
import { TestRailClient } from "../../client/testrail.js";import { ToolDefinition } from "../../types/custom.js";import { normalizeEntityId, prepareUploadFile } from "../../utils/attachment_helper.js";import { TestRailClient } from "../../client/testrail.js";import { ToolDefinition } from "../../types/custom.js";vitepress, vue
@modelcontextprotocol/sdk, archiver, dotenv, zod, @jest/globals, @types/archiver, @types/jest, @types/node
The server validates the whole environment before it does anything else and exits with code `1`, printing a structured list of which variables failed and why. A URL without a scheme, a username that i
Full access. Appropriate for a trusted local workspace where you want the assistant to be able to clean up after itself.
Read the [Configuration guide](./guide/configuration.md) for the full permission matrix, or the [FAQ](./guide/faq.md) for shorter answers.
> The CLI exposes **all 35 tools**, including shared steps, case history, and the RAG export. The `TESTRAIL_ALLOW_*` permission toggles and `TESTRAIL_ENABLE_*` feature flags govern only what is regist
In TestRail, open **My Settings**, switch to the **API Keys** tab, and generate a new key. Copy it immediately — TestRail shows the key only once. Note that the API must also be enabled instance-wide
Gates applied: no_behavioural_pass.
cb6784a89c8ffull audit observations/trust-audit/mcp-server/uarlouski__testrail-3.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | cb6784a89c8f | SAFE | B | 89 | first audit |
Questions
What is the TestRail MCP server?
AI-native MCP server connecting Claude, Cursor, Windsurf, and other AI assistants to TestRail — manage test cases, runs, and results through natural-language conversation, with typed schemas built for LLMs.
What tools does TestRail expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is TestRail safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does TestRail need?
It reads TESTRAIL_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does TestRail run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @uarlouski/testrail-mcp-server at 3.2.0.
How current is this page?
The grade is for one exact copy of the source (cb6784a89c8f), read on 2026-10-08. The repository is watched and re-audited when it changes.