Vectordecisions Mcp Server

io.github.NikitaDatarPublished by GitHub account NikitaDatarv1.0.3Updated Oct 24, 2026

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

VerifiedSTDIODesktop onlySecurity & MonitoringAI & ML

Overview

AI-generated overview

A local MCP server that gives an assistant governance tools for scoring AI trust, assessing action risk, checking EU AI Act policy, and issuing allow, restrict,

What you can do
Score trust with a legacy composite GATRI trust score and run deployment risk assessments for an AI system or agent action. Evaluate a single agent action with evidence-backed, context-aware assurance and turn assurance, policy, permissions and context into an ALLOW, RESTRICT, REQUIRE_HUMAN or DENY decision. Run EU AI Act-oriented compliance checks against policy. Issue an emergency kill-switch stop directive. The model treats assurance as per-action rather than a blanket claim that an agent is safe.
When to use it
Useful when you want an assistant to apply governance checks around autonomous agent actions: gating a proposed action, documenting a risk or compliance assessment, or triggering an emergency stop. It suits local experimentation with AI governance primitives rather than production enforcement.
Requirements
Runs as a local process over stdio, installed from the npm package vectordecisions-mcp-server; the README lists npm install, npm run build and npm start. No authentication, environment variables or headers are declared. Intended for MCP-compatible desktop clients.
Before you install
The kill_switch tool issues an emergency stop directive and decide_action returns restrictive outcomes, so results can block or halt agent work. The README describes this as a protocol-oriented V0 with deterministic local evaluation only; evidence ingestion, persistent assurance records, policy registries, signed attestations and remote APIs are not yet included, so do not treat its outputs as certified compliance.

Installation

In SourceWeft

  1. Open Vectordecisions Mcp Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

text
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

bash
npm installnpm run buildnpm 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.

Source: README.md at commit 2b8918c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.3LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.