io.github.wundam/orchex
orchex
Is the io.github.wundam/orchex MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-31.
Autopilot AI orchestration — auto-plan, parallelize, self-heal, and route across 6 LLMs.
alive probed 2026-11-15 · unchanged since 2026-10-31
- Run it
- npx -y @wundam/orchex@1.0.0-rc.11 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- orchex 1.0.0
- Capabilities
- tools
- Instructions
- none
- Of a 1M window
- 0.4 % of a 1M context window
- Count
- 3.8k tokens in Claude Opus 5.5, exact, measured 2026-10-17. With the Claude Code prefix mcp__…__ on each tool name: 3.9k. The o200k_base estimate is 2.1k. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/wundam/orchex
- Registry
- active, updated 2026-03-13 · registry entry
Most expensive tools
The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.82×.
| Tool | ≈ Claude tokens | o200k estimate | Share of this server |
|---|---|---|---|
| init | 813 | 446 | 21 % |
| execute | 466 | 256 | 12 % |
| add_stream | 452 | 248 | 12 % |
| auto | 408 | 224 | 11 % |
| learn | 379 | 208 | 10 % |
Compare this server with others.
More servers
Other registry entries on npmjs.com, the ones next to this name; all of them.
- AEM Content Manager (ACM) io.github.wttech/acm-mcp-server · needs env
- io.github.wtznicy/my-websearch · alive
- io.github.wudongjie/hourledger-mcp · alive
- io.github.wujinkim/korea-business-verify · alive
- io.github.wundervault/wundervault-mcp · alive
- GoldBean MCP Server io.github.wuzenghai616-lang/goldbean · alive
- Yuque MCP io.github.wwwwujl/yuque-mcp · no executable
- Nigeria Admin Divisions MCP by Wycord io.github.wycord/nigeria-admin-divisions · alive
Servers that mention orchestration or parallelize.
- ai.getvda/llm-observability-orchestration · newer protocol
- ai.getvda/llm-observability-orchestration-agent-langchain · newer protocol
- ai.getvda/llm-observability-orchestration-agent-langchain-community · newer protocol
- ai.getvda/llm-orchestration-agent-2 · newer protocol
- ai.getvda/llm-orchestration-agent-2-df5979 · newer protocol
- ai.getvda/llm-orchestration-agent-cryptography · newer protocol
- ai.getvda/llm-orchestration-agent-d0a1a1 · newer protocol
- ai.getvda/llm-orchestration-agent-d2feb0 · newer protocol
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 server answers initialize and tools/list. Nothing to fix.