mcpField
V
vectordecisions-mcp-server

vectordecisions-mcp-server

Local
github.com/NikitaDatarAI & Agents0Updated 11w ago
Repository

About vectordecisions-mcp-server

vectordecisions-mcp-server provides governance and action-assurance capabilities for autonomous AI, aimed at teams evaluating actions in context. It combines GATRI assessment with policies and permissions to produce explicit decisions.

Key features

  1. 01Context-aware action assurance
  2. 02Policy- and permission-based decisions
  3. 03Deployment risk assessment
  4. 04EU AI Act-oriented policy checks
  5. 05Emergency stop directive

Use cases

  1. 01Decide whether an agent action is allowed
  2. 02Require human review for risky actions
  3. 03Check deployment risk and compliance
  4. 04Stop autonomous AI actions in an emergency

MCP support

This MCP server uses stdio transport to expose governance tools to compatible clients, including action assurance, policy decisions, risk assessment, compliance checks, and an emergency stop.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "nikitadatar-vectordecisions": {
      "command": "npx",
      "args": [
        "-y",
        "vectordecisions-mcp-server"
      ]
    }
  }
}
Run commandnpx -y vectordecisions-mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmvectordecisions-mcp-server1.0.3

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
agentNamestringYesName of the AI agent to evaluate
governancenumberYesGovernance score (0-100)
robustnessnumberYesRobustness score (0-100)
inclusivitynumberYesInclusivity score (0-100)
transparencynumberYesTransparency score (0-100)
accountabilitynumberYesAccountability score (0-100)

Details

From the project 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

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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.