← Index

Sunaiva Gate — Agent Rule Enforcement

io.sunaivacore/gate·v2.0.2·Other

MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.

In-path gate · all MCP tools

Using Sunaiva Gate — Agent Rule Enforcement 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

curl -fsSL https://mcpindex.ai/install.sh | sh
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 →

Environment variables
SUNAIVA_GATE_API_KEY
secret

Pro-tier API key for premium rules. Free tier (31 constitutional rules) needs no key.

SUNAIVA_GATE_DRY_RUN

Set to '1' to evaluate without blocking — writes 'would_have_blocked' to audit log.

DISABLE_SUNAIVA_GATE

Emergency kill-switch: set to '1' to allow all actions unconditionally.

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
15
installability
25
documentation
10
stability
10
Alternatives in Other