# Assertline

> Assertline is a freemium MCP server for developer tools. Remote MCP server to find, run and read results of recorded end-to-end web tests. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** Web, API, CLI
- **Website:** https://assertline.com/docs
- **MCP Registry name:** com.assertline/assertline
- **Categories:** developer tools
- **Listing updated:** 2026-11-14

## About

Assertline's server is deliberately narrow: an assistant can list projects and tests, start runs and batches, and read verdicts, but cannot edit or delete tests, invite people or pay, whatever key it holds. Tests themselves are recorded by a person in Chrome.

In a typical exchange the assistant calls list_projects, list_tests, then run_test, which returns a run id and link immediately. When you ask how it went, get_run gives the verdict and failed steps, get_run_results lists every step and get_run_network returns the network log. Starting a hosted run can use paid minutes, and get_plan_and_usage shows what is left.

Access is either OAuth 2.1 with PKCE sign-in from the assistant, removable under Settings, Connected apps, or a CI or organization API key as a Bearer header. CI keys are listed for the Pro plan. The API allows 1,000 requests in 5 minutes per address.

## Features

- **Read-only plus run:** Assistants can run tests and read results but not change or delete anything.
- **Run batches by tag:** run_batch starts every test with a given tag and get_batch tracks it.
- **Step-level results:** Inspect which step failed, and the network log of a run.
- **OAuth or key access:** Sign in from the assistant, or use a CI or organization key.
- **Usage check:** get_plan_and_usage reports plan limits and this month's usage.

## Good for

- Ask an assistant to run the checkout test after a deploy
- Read which step of a failed run broke
- Trigger a tagged batch from a pipeline
- Check how many cloud minutes remain

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http assertline https://app.assertline.com/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://app.assertline.com/api/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "assertline": {
      "url": "https://app.assertline.com/api/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "assertline": {
      "type": "http",
      "url": "https://app.assertline.com/api/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "assertline": {
      "serverUrl": "https://app.assertline.com/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "assertline": {
      "type": "http",
      "url": "https://app.assertline.com/api/mcp"
    }
  }
}
```

## Tools

- `whoami`: Who you are connected as, with organization and plan.
- `list_projects`: List projects of the organization.
- `list_tests`: List recorded tests of a project.
- `get_test`: One recorded test with its steps.
- `run_test`: Start a run of a test.
- `list_runs`: List runs of a test or project.
- `get_run`: Status and verdict of a run.
- `get_run_results`: Step results of a run.
- `get_run_network`: Network log of a run.
- `run_batch`: Run every test with a tag.
- `list_batches`: List batches.
- `get_batch`: A batch and its runs.
- `list_environments`: List environments.
- `list_devices`: List device profiles.
- `get_plan_and_usage`: The plan, its limits and this month's usage.

## FAQ

### Can an assistant change my tests?

No. The server offers only the listed operations and cannot edit, delete, invite people or pay.

### How does it authenticate?

OAuth 2.1 with PKCE sign-in, or a Bearer API key.

### Does running a test cost money?

Runs on your own machine are free; hosted cloud runs use minutes, at $0.02 a minute beyond Pro's 2,000 included.

### How do I disconnect an assistant?

Remove it under Settings, Connected apps in the dashboard.

### Is Assertline free?

Assertline has a free plan, with paid plans for more usage or features.

### How do I add Assertline to Claude Code?

Run this command in your terminal: claude mcp add --transport http assertline https://app.assertline.com/api/mcp

### What are the best alternatives to Assertline?

The closest alternatives to Assertline are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/assertline
