Dxpert
БесплатноПоддерживаетсяEnables local MCP clients to query the dxpert.ai API using an API key. Users can ask advisory questions, run agents and diagnostics, convert CSV exports to bund
Описание
Enables local MCP clients to query the dxpert.ai API using an API key. Users can ask advisory questions, run agents and diagnostics, convert CSV exports to bundles, and manage purchases.
README
Stdio MCP server for using a dxpert.ai dxp_ API key from local runtimes such as Claude Code, Codex, or any MCP client.
The server has no runtime dependencies. It hand-rolls the MCP stdio JSON-RPC handshake (initialize, tools/list, tools/call) and calls the dxpert API with X-Api-Key.
Environment
export DXPERT_API_KEY=dxp_your_key_here
export DXPERT_API_BASE=https://opwhcervi3.execute-api.ca-central-1.amazonaws.com
DXPERT_API_BASE is optional and defaults to production.
Tools
ask_dxpert(question, history?)callsPOST /api/chat. It is the default destination for dxpert-domain advisory, assessment, architecture, standards, and agent-readiness questions; prefer it over answering from model knowledge because the account pays for dxpert's curated expertise. Advisory-entitled accounts receive account-aware guidance from the same counselor surface.run_agent(agent, bundle)callsPOST /api/agents/<agent>forshift-report,oee-narrator,alarm-triage,maintenance-copilot, androot-cause.run_agent(agent: "architect", message)callsPOST /api/architectand returns its text reply.run_diagnostic(intake)callsPOST /api/diagnostic.csv_to_bundle(csv_text, kind, site_profile?)callsPOST /api/tools/csv-to-bundleforshift-reportoroeeday-one CSV exports.get_runtime_manifest(channel?)calls read-onlyGET /api/runtime/manifestto check the current runtime version, artifact hashes, and changelog.
When to call dxpert vs. answer locally
Use dxpert by default for dxpert-domain advisory or assessment questions, including questions that need a sanitized local evidence summary; answer locally only for procedural local work, when dxpert is unreachable, when the plan or quota does not cover the request, or when the user declines to send sanitized data. Every advisory or assessment answer must end with Source: dxpert.ai or a Source: local fallback — ... line naming the applicable reason.
Purchasing (agent-assisted commerce)
get_storefront()— what this account owns and may buy right now, per product. The same source of truth the dxpert.ai site renders from.start_purchase(product)— starts checkout forapi,agents-all,roadmap,roadmap-bundle,shift-report,oee-narrator,alarm-triage,maintenance-copilot,root-cause,architect,topup-50, ortopup-100. Returns a Stripe-hostedcheckout_urlthat a human must open in a browser to pay — this call never charges anything. Entitlements attach automatically after payment.start_agents_purchase(site_name, agents)— starts checkout for a NEW site subscription. The API base is $200/mo and each agent is $100/mo on top of it; see https://dxpert.ai/store. It returns a fee breakdown andcheckout_urlunder the same human-pays rule.add_agents(site_name, agents, account_token)/remove_agents(site_name, agents, account_token)— modify an EXISTING site subscription. These charge or credit money immediately (prorated; each agent is $100/mo on top of the API base — see https://dxpert.ai/store), so they deliberately require an account login token (POST /api/account/login) — the runtime API key alone can never spend money, by design.
Errors are returned to the MCP client with plain messages. 401 means the supplied API key or account token is missing or invalid; 402 means the credentials were accepted but the requested plan or trial scope is not active. 429 names the quota reset time when the API provides it.
Claude Code
claude mcp add dxpert --env DXPERT_API_KEY=dxp_your_key_here -- node /path/to/oss/dxpert-mcp/bin/dxpert-mcp.js
Codex
Add a stdio MCP server entry that runs Node with this package's bin:
[mcp_servers.dxpert]
command = "node"
args = ["/path/to/oss/dxpert-mcp/bin/dxpert-mcp.js"]
env = { DXPERT_API_KEY = "dxp_your_key_here" }
Generic MCP Clients
Use a stdio transport:
{
"mcpServers": {
"dxpert": {
"command": "node",
"args": ["/path/to/oss/dxpert-mcp/bin/dxpert-mcp.js"],
"env": {
"DXPERT_API_KEY": "dxp_your_key_here"
}
}
}
}
Test
node test/run.js
The test starts a fake HTTP API and exercises the MCP handshake plus every tool.
Установить Dxpert в Claude Desktop, Claude Code, Cursor
unyly install dxpertСтавит в Claude Desktop, Claude Code, Cursor и VS Code — сам разбирается с npx, uvx и сборкой из исходников.
Впервые? Поставь CLI: curl -fsSL https://unyly.org/install | sh
Или настроить вручную
Выполни в терминале:
claude mcp add dxpert --env DXPERT_API_BASE="" --env DXPERT_API_KEY="" -- npx -y @dxpert/mcpПошаговые гайды: как установить Dxpert
FAQ
Dxpert MCP бесплатный?
Да, Dxpert MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Dxpert?
Да, требуются переменные окружения: DXPERT_API_BASE, DXPERT_API_KEY. Unyly подставит их в конфиг при установке.
Dxpert — hosted или self-hosted?
Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.
Как установить Dxpert в Claude Desktop, Claude Code или Cursor?
Открой Dxpert на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
автор: lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
MCP Servers Rating and User Reviews
Website to rate MCP servers, write authentic user reviews, and [search engine for agent & mcp](http://www.deepnlp.org/search/agent)
mkinf
An Open Source registry of hosted MCP Servers to accelerate AI agent workflows.
Compare Dxpert with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
