AI & Machine Learning
getzero.dev
Manages and simulates AI agents for the ZERO Runtime platform.
ENDPOINT 1
https://getzero.dev/oss/mcp
Known tools 31
validate_mandatev95 Protocol compute alias for validating an agent mandate without installing it.
Inferred read-onlyrun_paper_simulationv95 Protocol compute alias for a paper-only simulation preview.
Inferred read-onlyget_evidence_bundlev95 Protocol read-only alias for a public-safe ZERO Proof evidence bundle.
Inferred read-onlyzero_get_safety_catalogReturn ZERO public safety invariants and operator boundaries.
Inferred read-onlyzero_get_public_proofReturn public proof artifacts and repository launch-readiness links.
Inferred read-onlyzero_list_public_operatorsList public ZERO operators with profile, proof, custody, and evidence endpoints.
Inferred read-onlyzero_get_public_operatorFetch a normalized public ZERO operator profile by handle.
Inferred read-onlyzero_evaluateEvaluate a public market symbol through the read-only ZERO Protocol surface.
Inferred read-onlyzero_get_heatFetch public market heat and regime pressure for operator decision support.
Inferred read-onlyzero_get_pulseFetch public pulse events for recent market observations and engine context.
Inferred read-onlyzero_get_regimeFetch public regime context for the current Hyperliquid market environment.
Inferred read-onlyzero_get_briefFetch the public market brief used for operator situational awareness.
Inferred read-onlyzero_get_engine_productFetch the public Hyperliquid ZERO Runtime product truth contract.
Inferred read-onlyzero_get_engine_proofFetch the public ZERO Proof contract for live canary, immune, refusal, near-miss, and execution-quality systems.
Inferred read-onlyzero_get_engine_evidence_depthFetch retained ZERO Runtime evidence depth and sample readiness for launch-grade proof.
Inferred read-onlyzero_get_engine_cadenceFetch the public retained Runtime evidence freshness cadence and native-route readiness summary.
Inferred read-onlyzero_get_immune_statusFetch native public immune-system readback: protective state, redacted samples, and read-only boundary.
Inferred read-onlyzero_get_circuit_breakerFetch native public circuit-breaker readback for halt, risk, and non-immune order blocking evidence.
Inferred read-onlyzero_get_rejectionsFetch native public rejection evidence explaining weak setups ZERO refused before capital exposure.
Inferred read-onlyzero_get_near_missesFetch native public near-miss evidence for blocked signals and later follow-through calibration.
Inferred read-onlyzero_get_execution_qualityFetch native public execution-quality readback for slippage, latency, fills, and dampener calibration.
Inferred read-onlyzero_get_diagnosticsFetch public diagnostics for ZERO Runtime health and decision-support context.
Inferred read-onlyCONNECT 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.getzero-dev]
url = "https://getzero.dev/oss/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"getzero-dev": {
"type": "http",
"url": "https://getzero.dev/oss/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: getzero-dev
Remote MCP URL: https://getzero.dev/oss/mcp
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": {
"getzero-dev": {
"url": "https://getzero.dev/oss/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"getzero-dev": {
"type": "http",
"url": "https://getzero.dev/oss/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "getzero-dev",
"transport": "streamable-http",
"url": "https://getzero.dev/oss/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for getzero.dev was fetched 2026-08-23T22:16:47.958Z and is being refreshed.
getzero.dev is assessed as Trusted: Domain has an established technology history spanning over a year.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.