English Français العربية

io.github.NikitaDatar/vectordecisions-mcp-server

Official registry Data and databases

AI Governance MCP Server - GATRI trust scoring, kill-switch, EU AI Act compliance for Claude

Source code Documentation

What can you do with io.github.NikitaDatar/vectordecisions-mcp-server?

  • gatri_trust_score — legacy composite trust scoring.
  • assure_action — evidence-backed, context-aware assurance for one agent action.
  • decide_action — converts GATRI assurance + policy + permissions + context into ALLOW, RESTRICT, REQUIRE_HUMAN, or DENY.
  • risk_assessment — deployment risk assessment.
  • compliance_check — EU AI Act-oriented policy check.
  • kill_switch — emergency stop directive.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package vectordecisions-mcp-server
Claude Code 
claude mcp add vectordecisions-mcp-server -- npx -y vectordecisions-mcp-server@1.0.3
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "vectordecisions-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "vectordecisions-mcp-server@1.0.3"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Vector Decisions MCP Server
  2. Tools
  3. Core model
  4. Local development
  5. Status

Vector Decisions MCP Server

MCP-native governance and action-assurance primitives for autonomous AI.

Tools

  • gatri_trust_score — legacy composite trust scoring.
  • assure_action — evidence-backed, context-aware assurance for one agent action.
  • decide_action — converts GATRI assurance + policy + permissions + context into ALLOW, RESTRICT, REQUIRE_HUMAN, or DENY.
  • risk_assessment — deployment risk assessment.
  • compliance_check — EU AI Act-oriented policy check.
  • kill_switch — emergency stop directive.

Core model

agent × action × context × evidence
                 ↓
              GATRI
                 ↓
        Vector Decisions
                 ↓
      ALLOW / RESTRICT /
      REQUIRE_HUMAN / DENY

The important primitive is action assurance, not a generic claim that an agent is safe. The same agent can be acceptable for one action and unacceptable for another.

Local development

npm install
npm run build
npm start

The server uses stdio transport and is intended to be consumed by MCP-compatible clients.

Status

Version 1.1.0. This is a protocol-oriented V0: deterministic local evaluation first; evidence ingestion, persistent assurance records, policy registries, signed attestations and remote APIs are subsequent layers.

Frequently asked questions

What is io.github.NikitaDatar/vectordecisions-mcp-server?

AI Governance MCP Server - GATRI trust scoring, kill-switch, EU AI Act compliance for Claude

How do I install io.github.NikitaDatar/vectordecisions-mcp-server?

It runs on your machine. In Claude Code: claude mcp add vectordecisions-mcp-server -- npx -y vectordecisions-mcp-server@1.0.3. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.NikitaDatar/vectordecisions-mcp-server need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is io.github.NikitaDatar/vectordecisions-mcp-server open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains io.github.NikitaDatar/vectordecisions-mcp-server?

It is published by NikitaDatar. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.