StackMCP
Intermediate

QA / Testing Stack

Comprehensive testing toolkit with browser automation, error tracking, project management, and file access.

5 servers34.3K tokens17% of context

Token Budget

34.3K used (17.2%)165.7K remaining
Playwright MCP10.3K (5.1%)
GitHub MCP10.3K (5.1%)
Filesystem MCP5.7K (2.8%)
Puppeteer MCP4.1K (2.1%)
Sentry MCP4.1K (2.1%)

Moderate token usage. You will have good room for prompts but watch if adding more servers.

Config

Paste in ~/.claude.json

json
{
  "mcpServers": {
    "playwright-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@playwright/mcp"
      ]
    },
    "github-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_PERSONAL_ACCESS_TOKEN"
      }
    },
    "filesystem-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    },
    "puppeteer-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-puppeteer"
      ]
    },
    "sentry-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "sentry-mcp"
      ],
      "env": {
        "SENTRY_AUTH_TOKEN": "YOUR_SENTRY_AUTH_TOKEN"
      }
    }
  }
}

Included Servers

Puppeteer MCP

Anthropic

86
testing

Automate browsers with Puppeteer. Navigate pages, take screenshots, fill forms, and generate PDFs from your AI editor.

79.1k15.7k/wk4.1K tokens(2%)Official3d ago

A second browser automation engine for cross-tool coverage. Some legacy test suites depend on Puppeteer — having both avoids rewrites.

Sentry MCP

Sentry

70
monitoring

Query Sentry for error tracking, performance monitoring, and issue management directly from your AI editor.

5645/wk4.1K tokens(2%)Official2d ago

Pull real production errors into your test planning. Write regression tests for the exact bugs your users are hitting.