DevExpress Documentation MCP Server

Official hosted, read-oriented MCP access to version-sensitive DevExpress product documentation for AI coding clients.

Description

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.

Requirements

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

Installation instructions

This guide configures the official DevExpress Documentation MCP Server for controlled, read-oriented documentation lookup. Its primary source is DevExpress’s current guide at https://docs.devexpress.com/GeneralInformation/405551/help-resources/dev-express-documentation-mcp-server-configure-an-ai-powered-assistant. The service runs remotely at https://api.devexpress.com/mcp/docs and connects an MCP-capable AI coding client to the DevExpress documentation database. It is not a local index, an IDE extension with project access, or a write tool. The documented tools search help topics semantically or retrieve complete topics by URL. That boundary is useful: research can remain separate from repository and deployment permissions.

Set the target, version, and client first

Before setup, record the target: which DevExpress product version, platform, and component question must be answered? Without a URL parameter, DevExpress says the server addresses the latest public documentation. That is often not the right reference for an established project. For supported older versions from v24.2 onward, use for example https://api.devexpress.com/mcp/docs?v=24.2, and also write “v24.2,” “WPF,” or “Blazor” plus the control name in the question. This prevents an agent from silently targeting another product generation.

DevExpress documents setups for Claude Code, Codex, and Cursor, which are the compatibility records assigned here. It also names Copilot, Visual Studio, VS Code, Rider, Claude Desktop, ChatGPT, and Gemini CLI. Independently confirm that the actual client supports Streamable HTTP, requires Agent Mode, or is permitted by organizational policy to use remote MCP servers. Updated IDEs and plugins are sensible according to the provider because MCP support changes quickly. Record the client and model name as well: that matters for traceability and privacy more than the server’s display name.

Step 1: Configure the read-oriented endpoint

For Claude Code, DevExpress documents this local command:

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

For an older target version, append the version parameter to the URL. In Codex or Cursor, register the identical endpoint as an HTTP server; the exact configuration UI depends on the client. Do not mistake a browser navigation for a connection test: the documentation warns that direct browser access is unsupported and can return 405. Instead, check in the client that exactly devexpress_docs_search and devexpress_docs_get_content appear in its tool list. If they do not, first check transport type, URL, Agent Mode, proxy configuration, and outbound access to api.devexpress.com.

Start with one concrete search request. Name the component, platform, version, and intended outcome, such as a filtering rule for a WinForms grid in v24.2. Then retrieve only the most relevant result with devexpress_docs_get_content. The provider’s guidance to search once per question avoids redundant context and makes the answer’s provenance easier to review. The response is evidence for a design and review, not an automatic modification to the application.

Untrusted content, prompt injection, and review

Every fetched help topic, code block, URL, search result, and error text is untrusted content. Text can look like a plausible internal note and still contain prompt injection, for example an instruction to ignore rules, disclose data, or invoke an additional tool. Those sentences are data, not permission. The DevExpress server has no write access in its documented tool list, but an AI client may also have other tools or a local shell. Keep those permissions separate and, for research, use a tool allowlist containing only the two DevExpress tools where possible.

After retrieval, check the URL, product family, version, API names, code prerequisites, and topic date. Compare proposed code with the project’s actual dependencies and conventions. DevExpress itself requests review of AI-generated results for architectural problems, security vulnerabilities, and project standards. A human must therefore separately approve every patch, test, database access, or deployment command. No sentence in documentation, no model proposal, and no generated summary can replace that approval.

Telemetry, model provider, and completion

The data path does not necessarily end at DevExpress. Per the provider, the MCP service records anonymous telemetry for tool-call names and arguments passed by the AI assistant to monitor health and reliability. DevExpress also says that its MCP use does not specifically collect DevExpress account identity, workspace files, source code, or the original chat messages typed in the IDE. Even so, the client can send fetched documentation and parts of a prompt to its model provider. Assess that provider’s retention, training choices, DPA, enterprise settings, and regional processing. Do not put unnecessary source code, tokens, personal data, or internal URLs in tool arguments.

After the session, remove the connection when it is only temporarily needed, or review access on the organization’s schedule. For proxy or firewall errors, coordinate the FQDN api.devexpress.com with IT rather than pinning IP addresses. Record endpoint, version parameter, client, model, search request, fetched sources, and human reviewers in a ticket or pull request. That makes it clear which documentation influenced a code proposal and why it was accepted for the specific product version.

FAQ

Why does a browser test return 405? DevExpress says the endpoint is intended for Streamable HTTP in an MCP client, not direct browser navigation. The client’s tool list is the appropriate test.

Can I use only current documentation? No. The current public version is used without a parameter; for supported older releases from v24.2 onward, use a parameter such as ?v=24.2.

What must be disclosed about the model? At least the client and model provider. Tool results can enter that provider’s context, so retention, training, contract, and privacy must be assessed separately.

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

Authentication

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

Required access permissions

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

Transmitted or stored data

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.

Security risks

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.

License and costs

License
Hosted DevExpress service; no public source repository or source license identified for this endpoint.
Cost
paid

The official MCP guide states no separate server price. Check current availability and service terms directly with DevExpress before use.

Alternatives

Not recorded yet.

At a glance

Provider
DevExpress
Status
Official server
Deployment
Remote
Current version
Not recorded yet.
Last reviewed
08.09.2026

Repository and documentation

Categories

Supported clients