io.github.commet/argus-decision-mcp
Save a falsifiable prediction, then record what reality did. Reality grades you, not the model.
Using io.github.commet/argus-decision-mcp 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).
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-wireVerdict 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 io.github.commet/argus-decision-mcp’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.
ARGUS_DIRDirectory for the append-only ledger (.argus). Set once and every tool falls back to it. Claude Code expands ${CLAUDE_PROJECT_DIR}; on other hosts use an absolute path.
ARGUS_TOKENOptional Argus account token. Set it and saved predictions sync so Argus can email you at the check-by date. Unset = fully local, no network.
ARGUS_TZTimezone that decides when a check-by date becomes today (e.g. Asia/Seoul). Unset = your machine's local timezone.
Resolve .hood names on Robinhood Chain — forward/reverse, text records, availability & pricing.
AI-powered trading strategy development: backtesting, market data, and portfolio analysis
Feature flagging and A/B testing platform with AI-first experimentation workflows.