← Index

three.ws Autopilot

io.github.nirholas/autopilot-mcpv0.2.0Other

Set autopilot scopes and a daily SOL spend cap, then propose, execute, and undo agent actions.

In-path gate · all MCP tools

Using three.ws Autopilot 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
REVIEWstatus: PARTIALfresh until 2026-08-21 21:04 UTC
screened 2026-07-22tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidenceNo malicious instructions foundvia static_description

Limits of this verdict
  • - Semantic screen only - the deterministic conformance probe has not run on this server
  • - Confidence is reported but not yet calibrated (v1)
  • - Screen reads the tool description, not the live behavior
  • - advisory
  • - registry description only no input schema
  • - screen model 8b

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-08-08).

Contracts can change after screening, with no version bump. The gate pins three.ws Autopilot’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 →

Related: how to trust an MCP server · screen before install · silent contract drift

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown
[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-nirholas-autopilot-mcp)](https://mcpindex.ai/server/io-github-nirholas-autopilot-mcp)
HTML
<a href="https://mcpindex.ai/server/io-github-nirholas-autopilot-mcp"><img src="https://mcpindex.ai/api/v1/badge/io-github-nirholas-autopilot-mcp" alt="mcpindex verdict" height="20" /></a>
Environment variables
THREE_WS_API_KEY
requiredsecret

REQUIRED. The agent owner's three.ws credential — a three.ws API key (sk_live_… / sk_test_…) or an OAuth access token. Sent as Authorization: Bearer on every request; every autopilot endpoint is owner-scoped and rejects unauthenticated calls. This credential can move real SOL via execute_proposal — treat it like a password. THREE_WS_TOKEN / THREE_WS_BEARER are accepted aliases.

THREE_WS_BASE

Base URL of the three.ws API that serves the autopilot endpoints. Override only when self-hosting or targeting a preview deployment.

THREE_WS_TIMEOUT_MS

Per-request timeout in milliseconds. Proposal generation runs a real server-side LLM pass, so the default is generous.

MCP quality score · maturity, not trust · methodology
freshness
24
completeness
25
installability
25
documentation
15
stability
5
Alternatives in Other