io.github.Nantiai/ocl-standard

OCL Context Layer

Is the OCL Context Layer MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-31.

Reference MCP server for OCL, an open standard giving AI agents scoped business meaning for Odoo.

alive probed 2026-11-15 · unchanged since 2026-10-31

3tools

183tokens in Claude Opus 5.5

<0.1 %of Claude's 200k window

0.1×the median server

338 msto initialize

1 msto list tools

Run it: docker run -i --rm ghcr.io/nantiai/ocl-examples:0.1.0-alpha.1 (stdio, probed in a container with the network off)
Host: ghcr.io
Reports itself as: ocl-public-examples 0.1.0-alpha.1
Capabilities: tools
Instructions: none
Of a 1M window: <0.1 % of a 1M context window
Count: 183 tokens in Claude Opus 5.5, exact, measured 2026-10-31. With the Claude Code prefix mcp__…__ on each tool name: 216. The o200k_base estimate is 90. Counted again when the tool definitions change. Method.
Repository: https://github.com/Nantiai/ocl-standard
Website: https://nanti.ai
Registry: active, updated 2026-09-07 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 2.03×.

Tool	≈ Claude tokens	o200k estimate	Share of this server
get_context	61	30	33 %
resolve_noun	61	30	33 %
explain_field	61	30	33 %

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

Servers that mention standard.

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.