MCP Kinetic Gain

@Miz Causevic

Visit Server

2 days ago

mcp-kinetic-gain is a single stdio MCP server that exposes all eleven Kinetic Gain Protocol Suite specs to any MCP-compatible client (Claude Desktop, Cline, Cursor, etc.) — 71 tools across AEO Protocol, Prompt Provenance, Agent Cards, AI Evidence Format, MCP Tool Cards, AI Tutor Cards, Student AI Disclosure, Classroom AI AUP, Clinical AI Disclosure, AI Incident Card, AI Procurement Decision Card, plus the DefenseTech 6-pack tooling shipped in v0.8.0. Includes ed25519 attestation verification, hash-chained audit-stream event composition and chain verification (offline AND live against a running audit-stream-py via the optional AUDIT_STREAM_URL env var), cross-spec drift detection, and a Decision Intelligence preview that generates a PolicyBundle from a Decision Card, infers rubric status, and plans incident remediation. Also doubles as a CLI: `npx mcp-kinetic-gain validate path/to/doc.json` auto-detects which Suite spec a JSON file belongs to and validates it against the same zod schemas the MCP tools use. No API key. No build step. Headline tools: aup_check_compliance, decision_card_validate, decision_card_to_policy_bundle, attestation_verify, suite_doc_drift, audit_chain_verify, audit_event_emit, audit_events_query, audit_chain_verify_live. Repo: https://github.com/mizcausevic-dev/mcp-kinetic-gain Suite: https://suite.kineticgain.com License: Apache-2.0

Overview Tools Comments

Overview

Unified MCP server for the Kinetic Gain Protocol Suite

71 tools across 11 specs, plus DefenseTech tooling. Stdio. No API key. No build step.

Drop into Claude Desktop, Cursor, Cline, or any MCP-compatible client with a single config entry. The agent gains the entire Kinetic Gain Protocol Suite as callable tools.

Quick install

npm install -g mcp-kinetic-gain

Or run directly with npx -y mcp-kinetic-gain (no global install needed).

What's inside (71 tools across 11 specs + 8 DefenseTech)

Protocol Suite specs (47 tools):

AEO Protocol — Answer Engine Optimization for AI-readable disclosure
Prompt Provenance — verifiable chain of prompt → response attribution
Agent Cards — capability + identity disclosure for AI agents
AI Evidence Format — hash-chained evidence packaging
MCP Tool Cards — describe what MCP tools do, for whom
AI Tutor Cards — disclosure for educational AI deployments
Student AI Disclosure — FERPA-aligned classroom AI surface
Classroom AI AUP — Acceptable Use Policy primitives
Clinical AI Disclosure — HIPAA-aligned health AI surface
AI Incident Card — postmortem + remediation scaffold
AI Procurement Decision Card — buyer-side policy enforcement

Implementation tooling (16 tools): ed25519 attestation verification, hash-chained audit-stream event composition + chain verification (offline AND live against a running audit-stream-py via the optional AUDIT_STREAM_URL env var), cross-spec drift detection, Decision Intelligence preview (Decision Card → PolicyBundle, rubric status inference, incident remediation planning).

DefenseTech 6-pack (8 tools, new in v0.8.0): scaffolding for defense / national-security AI procurement workflows.

Headline tools

aup_check_compliance, decision_card_validate, decision_card_to_policy_bundle, attestation_verify, suite_doc_drift, audit_chain_verify, audit_event_emit, audit_events_query, audit_chain_verify_live.

Doubles as a CLI

npx mcp-kinetic-gain validate path/to/doc.json

Auto-detects which Suite spec the JSON belongs to and validates it against the same zod schemas the MCP tools use.

License

AGPL-3.0. Free to use, free to fork, free to study — but if you build a SaaS that wraps it, the SaaS must publish its source.

Try in Playground

Server Config

{
  "mcpServers": {
    "kinetic-gain": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-kinetic-gain"
      ]
    }
  }
}

Build with ShipAny.