io.github.computenexa-gpuInfrastructure/computenexa-mcp
ComputeNexa
Is the ComputeNexa MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-01.
Find, launch and stop private GPUs on ComputeNexa, with a quote before anything is charged.
alive probed 2026-11-02 · unchanged since 2026-11-01
15tools
3.9ktokens in Claude Opus 5.5
2.0 %of Claude's 200k window
1.6×the median server
1.1 sto initialize
8 msto list tools
- Run it
- uvx computenexa-mcp@0.1.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- ComputeNexa 0.1.0
- Capabilities
- prompts, resources, tools
- Instructions
- 695 characters
- Of a 1M window
- 0.4 % of a 1M context window
- Count
- 3.9k tokens in Claude Opus 5.5, exact, measured 2026-11-01. With the Claude Code prefix mcp__…__ on each tool name: 4.1k. The o200k_base estimate is 2.2k. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/computenexa-gpuInfrastructure/computenexa-mcp
- Website
- https://computenexa.com
- Registry
- active, updated 2026-11-01 · registry entry
Most expensive tools
The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.78×.
| Tool | ≈ Claude tokens | o200k estimate | Share of this server |
|---|---|---|---|
| launch_machine | 989 | 557 | 25 % |
| set_keep_running | 457 | 257 | 12 % |
| list_gpus | 355 | 200 | 9 % |
| extend_machine | 343 | 193 | 9 % |
| list_apps | 281 | 158 | 7 % |
Compare this server with others.
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.