INDIVIDUAL MCP TOOL
caliper_rubrics_create
Creates the scoring rubric an eval's LLM judge uses — 1-10 criteria, each scored on a numeric scale (default 1-5), judged pass/fail (kind pass_fail), or checked in code with no judge (kind check: contains, not_contains, matches a regex, valid_json, max_chars, equals_expected).
LIVE ENDPOINT
https://api.zerowidth.ai/mcp/x/caliper
Connect to this endpoint to inspect the live schema for caliper_rubrics_create and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Potential side effects detected · medium confidence · heuristic, not a guarantee.
- A tool name or description suggests code or command execution.
Parent server
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.zerowidth-mcp]
url = "https://api.zerowidth.ai/mcp/x/caliper"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"zerowidth-mcp": {
"type": "http",
"url": "https://api.zerowidth.ai/mcp/x/caliper"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: zerowidth-mcp
Remote MCP URL: https://api.zerowidth.ai/mcp/x/caliper
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"zerowidth-mcp": {
"url": "https://api.zerowidth.ai/mcp/x/caliper"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"zerowidth-mcp": {
"type": "http",
"url": "https://api.zerowidth.ai/mcp/x/caliper"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "zerowidth-mcp",
"transport": "streamable-http",
"url": "https://api.zerowidth.ai/mcp/x/caliper"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
search_docs— Search ZeroWidth product documentation.get_doc— Fetch the full Markdown body of a specific docs page by its slug.list_docs— Enumerate all available docs pages, optionally filtered by product (e.caliper_datasets_get— One dataset with a page of its items — read this BEFORE editing items (caliper_datasets_update_item needs the item id) and before extending coverage, so you don't add cases that already exist.caliper_datasets_update— Changes a dataset's title, description, or visibility.caliper_datasets_delete— Deletes a dataset.caliper_datasets_update_item— Rewrites one item's content, keeping its id (ratings and eval results keyed to it stay attached).caliper_datasets_remove_item— Drops one item.