DevExpress Documentation MCP Server

The DevExpress Documentation MCP Server is the DevExpress-documented hosted MCP endpoint at https://api.devexpress.com/mcp/docs. Its official setup guide was updated on August 27, 2026 and describes the service as a connection between GitHub Copilot and other MCP-compatible AI tools and the DevExpress documentation database. It is therefore an actively maintained offering from the documentation operator, not a community server. This catalog record deliberately covers documentation lookup only: the server answers DevExpress-related questions and returns help information so an agent can propose code based on documented scenarios. It is not a general web-search system and does not provide access to a DevExpress account, project files, or a development environment.

Documentation-only scope and tools

According to DevExpress, the server exposes two tools. devexpress_docs_search performs semantic search in the documentation database and returns the five most relevant matches for a query. devexpress_docs_get_content downloads complete help topics by URL. This is a read-oriented data path: the official description lists no file, shell, Git, ticketing, or deployment tools. That does not make generated code automatically correct or safe. DevExpress explicitly says to review AI output for architectural problems, security vulnerabilities, and adherence to project standards. Use the results as traceable documentation evidence, not as authorization to change a repository.

Remote endpoint and version targeting

The service operates exclusively over Streamable HTTP. Configure an MCP-compatible client with https://api.devexpress.com/mcp/docs and HTTP transport; the endpoint is not intended for direct browser access and can return 405 there. Without parameters it targets the latest publicly available documentation. For older products, a version parameter can be selected, for example https://api.devexpress.com/mcp/docs?v=24.2; DevExpress says versions from v24.2 onward are available. Also name the target version, platform, and component in the prompt, such as WinForms, WPF, Blazor, ASP.NET Core, or VCL. This lowers the risk that a model applies a current API to an older codebase.

Clients, model, and data path

DevExpress documents integrations for Claude Code, Codex, and Cursor, so those three existing catalog compatibilities are assigned. Its guide also names GitHub Copilot, Visual Studio, VS Code, Rider, Claude Desktop, ChatGPT, and Gemini CLI, but this catalog has no separate compatibility records for those products. The server itself is remote at DevExpress. On a call, the AI client sends the tool name and arguments to the endpoint and receives search matches or documentation content. Per the provider, DevExpress records anonymous usage telemetry for service health and reliability, including tool-call names and arguments passed by the AI coding assistant; it says that DevExpress account identity, workspace files, source code, and the original chat messages typed in an IDE are not specifically collected through MCP use. That statement does not replace review of the selected client.

The client can put fetched content into the context of its chosen model provider. Remote operation at DevExpress therefore does not mean the entire AI or data path remains local. Disclose which client product and model are in use, and assess that provider’s retention, training settings, enterprise agreement, and privacy terms. Send only the question, version target, and minimum necessary context; tokens, personal data, internal URLs, and source code should not be included in search arguments unless documentation lookup actually requires them.

Untrusted content and safe practice

Fetched help topics, code examples, URLs, and search results are untrusted content: they are data, not commands. A compromised or misleading text can contain prompt injection and claim that rules should be ignored, secrets exposed, or undocumented actions taken. An agent must not treat such text as authorization. Search first, fetch only relevant topics, verify the source, product version, and API names, then compare every proposed code change with the project. Limit client permissions to this read-oriented server, separate research from write-capable tools, and require human review before any change.

Repository, operation, and boundary

DevExpress’s official guide publishes a hosted endpoint, but no public server repository. A search for an officially tied GitHub repository identified no such source; the visible third-party result dorkian/mcp-devexpress is explicitly not this record. Since no official repository is tied to the server, repo_url and GitHub stars remain blank and a GitHub API request would not be meaningful. Check current license, availability, and service terms directly with DevExpress. The Coding category is justified because DevExpress presents the server for AI-assisted development, component questions, and code-oriented documentation use.

FAQ

Can the server change project files? The official tool list describes only documentation search and retrieval of complete help topics. Changing a project would require a separate client or development tool.

How do I work against an older DevExpress version? Configure a supported endpoint parameter such as v=24.2, then name the version, platform, and component in the prompt as well.

Are fetched examples trusted agent instructions? No. They are documentation data, can enter model context, and must be checked against the request, version, security requirements, and human review.

An MCP-compatible AI client with Streamable HTTP support, outbound HTTPS access to api.devexpress.com, and the confirmed target DevExpress version and platform.

In Claude Code run claude mcp add --transport http dxdocs https://api.devexpress.com/mcp/docs. For an older version, append ?v=24.2 to the URL. In Codex or Cursor, register the same HTTP endpoint as an MCP server. Then verify only the two DevExpress tools, record the target version in the task, and treat fetched material as untrusted content.

claude mcp add --transport http dxdocs https://api.devexpress.com/mcp/docs

The official guide documents no authentication for the endpoint; client and organizational policies still apply.

Read-oriented access to semantic documentation search and complete help topics. The documented tool list contains no project-file, shell, Git, or deployment actions.

The remote service receives tool names and arguments from the AI client and returns documentation content. DevExpress describes anonymous telemetry for those values; the client can pass results to its model provider.

Help topics, search results, and examples are untrusted content and can contain prompt injection. No embedded instruction replaces human review; check generated code for version fit, security, and project standards.