> For the complete documentation index, see [llms.txt](https://learning.contextqa.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://learning.contextqa.com/mcp-server.md). # MCP Server - [MCP Server Overview](https://learning.contextqa.com/mcp-server/overview.md): Connect any MCP-compatible AI agent to ContextQA's 67 tools for test creation, execution, failure analysis, and self-healing — all through natural language. - [Installation & Setup](https://learning.contextqa.com/mcp-server/installation-and-setup.md): Connect the ContextQA MCP Server to AI assistants like Claude, Claude Code, Cursor, ChatGPT, and Codex using OAuth 2.0. - [Authentication](https://learning.contextqa.com/mcp-server/authentication.md): How the ContextQA MCP Server authenticates AI clients with OAuth 2.0 — the sign-in flow, sessions, multiple accounts, and troubleshooting. - [Tutorial: Your First Test with an AI Agent](https://learning.contextqa.com/mcp-server/first-test-tutorial.md): Connect an AI assistant such as Claude Code or Cursor to the ContextQA MCP server, then create, run, and review your first test using natural-language prompts — no test code and no manual API calls. - [How to Migrate an Existing Test Suite](https://learning.contextqa.com/mcp-server/migrating-existing-tests.md): Migrate an existing Selenium, Cypress, or Playwright test repository into ContextQA using an AI agent and the MCP migration tools — analyze the repo, preview with a dry run, migrate, and verify the re - [Agent Integration Guide](https://learning.contextqa.com/mcp-server/agent-integration-guide.md): Integrate AI agents with ContextQA MCP tools — tool call ordering, async execution, debugging, and multi-step workflow orchestration. - [How to Reproduce a Bug from a Support Ticket](https://learning.contextqa.com/mcp-server/reproduce-bug-from-ticket.md): Turn a support ticket into a running reproduction in ContextQA using the MCP support-to-fix tools — reproduce the bug, confirm it, collect the evidence bundle with AI root cause, and file a defect tic - [Interactive Demo](https://learning.contextqa.com/mcp-server/demo.md): See how Claude and other AI agents use ContextQA's MCP tools to create tests, run them, and analyze failures — all from a natural language conversation. - [Tool Reference](https://learning.contextqa.com/mcp-server/tool-reference.md): Complete index of all 67 ContextQA MCP tools — test case management, execution, suites, infrastructure, AI test generation, and telemetry. - [Test Case Management](https://learning.contextqa.com/mcp-server/tool-reference/test-case-management.md): Complete reference for the 8 MCP tools that create, read, update, delete, and query test cases in ContextQA. - [Execution & Results](https://learning.contextqa.com/mcp-server/tool-reference/execution-and-results.md): Complete reference for MCP tools that trigger test runs, poll for completion, and retrieve results including screenshots and step details. - [Test Suites & Plans](https://learning.contextqa.com/mcp-server/tool-reference/suites-and-plans.md): MCP tool reference for managing and executing test suites and test plans in ContextQA. - [Infrastructure & Data](https://learning.contextqa.com/mcp-server/tool-reference/infrastructure-and-data.md): MCP tool reference for managing environments, devices, UI elements, and test data profiles in ContextQA. - [Test Generation](https://learning.contextqa.com/mcp-server/tool-reference/test-generation.md): Complete reference for the 10 MCP tools that generate test cases from code changes, tickets, designs, specs, videos, and natural language requirements. - [Bug, Defect & Advanced Testing](https://learning.contextqa.com/mcp-server/tool-reference/bug-defect-and-advanced.md): MCP tool reference for defect management, performance and security testing, code export, and AI-powered impact analysis in ContextQA. - [Telemetry & Custom Agents](https://learning.contextqa.com/mcp-server/tool-reference/telemetry-and-agents.md): MCP tool reference for execution telemetry, AI reasoning inspection, custom agent personas, and knowledge bases in ContextQA. - [Support-to-Fix & Migration](https://learning.contextqa.com/mcp-server/tool-reference/support-and-migration.md): MCP tool reference for ticket-driven bug reproduction, failure investigation, analytics coverage gap analysis, and test suite migration in ContextQA. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://learning.contextqa.com/mcp-server.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.