SWT3 AI Witness

io.tenova/swt3-witness·v0.5.9·Other

Cryptographic AI governance + audit. 20 tools, 31 frameworks. EU AI Act, NIST, OWASP, CMMC, SR 11-7

In-path gate · all MCP tools

Using SWT3 AI Witness 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

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-08-05 16:02 UTC

screened 2026-07-06tier: scannedgranularity: description-levelsource: registry

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

mcpindex.integrity.descriptionpassINFO

evidence“No malicious instructions found”via 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 →

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-tenova-swt3-witness)](https://mcpindex.ai/server/io-tenova-swt3-witness)

HTML

<a href="https://mcpindex.ai/server/io-tenova-swt3-witness"><img src="https://mcpindex.ai/api/v1/badge/io-tenova-swt3-witness" alt="mcpindex verdict" height="20" /></a>

Environment variables

SWT3_API_KEY

secret

SWT3 API key (starts with axm_). Omit for zero-config demo mode.

SWT3_TENANT_ID

Your tenant identifier

SWT3_CONFIG_FILE

Path to swt3.yaml config file for policy-as-code

SWT3_CLEARING_LEVEL

Data clearing level: 0=analytics, 1=standard, 2=sensitive, 3=classified

SWT3_AGENT_ID

Agent identity for AI-ID.1 witnessing

SWT3_SIGNING_KEY

secret

HMAC-SHA256 signing key for non-repudiation

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Other

hood. — .hood name service

ag.hood/name-service

Resolve .hood names on Robinhood Chain — forward/reverse, text records, availability & pricing.

agency.lona/trading

AI-powered trading strategy development: backtesting, market data, and portfolio analysis

ABMeter

ai.abmeter/abmeter

Feature flagging and A/B testing platform with AI-first experimentation workflows.

Install this server

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "swt3-witness": {
      "command": "npx",
      "args": [
        "-y",
        "@tenova/swt3-mcp"
      ],
      "env": {
        "SWT3_API_KEY": "<your-swt3_api_key>",
        "SWT3_TENANT_ID": "<swt3_tenant_id>",
        "SWT3_CONFIG_FILE": "<swt3_config_file>",
        "SWT3_CLEARING_LEVEL": "<swt3_clearing_level>",
        "SWT3_AGENT_ID": "<swt3_agent_id>",
        "SWT3_SIGNING_KEY": "<your-swt3_signing_key>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "swt3-witness": {
      "command": "npx",
      "args": [
        "-y",
        "@tenova/swt3-mcp"
      ],
      "env": {
        "SWT3_API_KEY": "<your-swt3_api_key>",
        "SWT3_TENANT_ID": "<swt3_tenant_id>",
        "SWT3_CONFIG_FILE": "<swt3_config_file>",
        "SWT3_CLEARING_LEVEL": "<swt3_clearing_level>",
        "SWT3_AGENT_ID": "<swt3_agent_id>",
        "SWT3_SIGNING_KEY": "<your-swt3_signing_key>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y @tenova/swt3-mcp

Claude Code (claude mcp add)

claude mcp add --scope user swt3-witness -- npx -y @tenova/swt3-mcp

Gemini CLI (gemini mcp add)

gemini mcp add -s user swt3-witness npx -y @tenova/swt3-mcp

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-tenova-swt3-witness

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.5.9
category: Other
verdict expires: 2026-08-05
quality: 90 / 100
operator: tenova-labs

Provenance

Verdict history is anchored to Bitcoin via OpenTimestamps. The anchor proof is public and any skeptic can recompute it offline.

Links

Repository →Website →