io.github.0xmortuex/kconfig-mcp

kconfig

Is the io.github.0xmortuex/kconfig-mcp MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-26.

Why can't I enable CONFIG_X? Explains Kconfig dependencies and finds a verified fix.

alive probed 2026-11-15 · unchanged since 2026-10-26

10tools

2.3ktokens in Claude Opus 5.5

1.1 %of Claude's 200k window

0.9×the median server

3.1 sto initialize

9 msto list tools

Run it: uvx kconfig-mcp@0.1.0 (stdio, probed in a container with the network off)
Host: pypi.org
Reports itself as: kconfig
Capabilities: prompts, resources, tools
Instructions: 537 characters
Of a 1M window: 0.2 % of a 1M context window
Count: 2.3k tokens in Claude Opus 5.5, exact, measured 2026-10-26. With the Claude Code prefix mcp__…__ on each tool name: 2.4k. The o200k_base estimate is 1.3k. Counted again when the tool definitions change. Method.
Repository: https://github.com/0xmortuex/kconfig-mcp
Registry: active, updated 2026-10-11 · 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

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
kconfig_load	562	315	25 %
kconfig_why_not	358	201	16 %
kconfig_diff	292	164	13 %
kconfig_set	244	137	11 %
kconfig_search	176	99	8 %

Other registry entries on pypi.org, the ones next to this name; all of them.

Servers that mention dependencies or explains.

We add a row when the result changes. A server with no change keeps its last row.

Probed	Result	Init	Tools	Claude	o200k
2026-10-26 06:58	alive	3.2 s	10	2.3k	1.3k
2026-10-19 06:50	alive	3.1 s	10		1.3k

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.