ai.dxpert/mcp
dxpert.ai — industrial AI-readiness & UNS agents
Is the dxpert.ai MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-01.
AI-readiness diagnostic, dxpert Advisor and the industrial agents of dxpert Pro, for MCP clients.
alive probed 2026-11-15 · unchanged since 2026-11-01
- Run it
- npx -y @dxpert/mcp@0.2.1 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- @dxpert/mcp 0.2.1
- Capabilities
- tools
- Instructions
- none
- Of a 1M window
- ≈ 0.2 % of a 1M context window, estimate
- Claude count
- The count_tokens endpoint refused the tool schemas: tools.2.custom.input_schema: input_schema does not support oneOf, allOf, or anyOf at the top level. The estimate stands in.
- Repository
- https://github.com/dxpert-ai/dxpert-mcp
- Website
- https://dxpert.ai
- Registry
- active, updated 2026-11-01 · registry entry
- Changes
- 2 recorded, reachable in 2 of them. A row is added when the result, the tool count or the cost changes.
Most expensive tools
Estimates with the o200k_base tokenizer.
| Tool | o200k estimate | Share of this server |
|---|---|---|
| run_agent | 625 | 27 % |
| ask_dxpert | 430 | 18 % |
| run_diagnostic | 366 | 16 % |
| start_purchase | 341 | 15 % |
| csv_to_bundle | 248 | 11 % |
Compare this server with others.
More servers
Other registry entries on npmjs.com, the ones next to this name; all of them.
- Yarr MCP ai.dinglebear/yarr · needs network
- Yarr MCP ai.dinglebear/yarr-mcp · not found
- YTDL RMCP ai.dinglebear/ytdl-rmcp · not found
- doublespeed — Xcode as an API ai.doublespeed/mcp · alive
- dxpert.ai — free UNS tools (no API key) ai.dxpert/uns-tools · alive
- ai.elfa/mcp · alive
- Elicitly ai.elicitly/elicitly · alive
- FlowDot ai.flowdot/mcp-server · needs env
Servers that mention dxpert.
- SynomosAI Governance MCP io.github.Medxpert-org/ubic-governance-mcp · not probed
- MedXpert 图书馆连接器（通用版） io.github.zhaoxinghua09-cell/medxpert-library-connector · alive
- MedXpert Global Regulatory Connector (reg-connector) io.github.zhaoxinghua09-cell/medxpert-reg-connector · alive
- MedXpert 标准检索连接器 io.github.zhaoxinghua09-cell/medxpert-standards-connector · alive
- MedXpert Regulatory Hub io.github.stevenzhao07/medxpert-reg-hub · alive
- LGD Engine io.github.Medxpert-org/lgd-engine · crashed on start
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-11-01 08:09 | alive | 104 ms | 7 | 2.3k | |
| 2026-10-18 06:37 | alive | 111 ms | 10 | 3.1k |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The Anthropic count_tokens endpoint refused the tool schemas (tools.2.custom.input_schema: input_schema does not support oneOf, allOf, or anyOf at the top level). A client that validates schemas can refuse them too.