← Index

three.ws Concierge

io.github.nirholas/concierge-mcp·v0.1.0·Other

Ask any website's AI concierge a grounded question, and generate the embed to add one to a site.

In-path gate · all MCP tools

Using three.ws Concierge in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-07-20).

Contracts can change after screening, with no version bump. The gate pins three.ws Concierge’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Environment variables
THREE_WS_BASE

Base URL of the three.ws API that serves POST /api/concierge, and the origin the generated embed snippets point at. Override only when self-hosting or targeting a preview deployment.

THREE_WS_TIMEOUT_MS

Per-request timeout in milliseconds for the concierge answer call. The answer streams over a free-first LLM chain that can fail over across providers, so the default leaves room for one slow rung.

CONCIERGE_PAGE_TIMEOUT_MS

Timeout in milliseconds for fetching a page that concierge_ask grounds its answer in. Separate from the answer timeout so a slow site cannot consume the whole call.

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
25
installability
25
documentation
15
stability
5
Alternatives in Other