Tork Governance

io.github.torkjacobsPublished by GitHub account torkjacobsv1.5.1Updated Oct 24, 2026

AI agent governance for MCP: PII detection, policy enforcement, compliance, and kill switch.

VerifiedSTDIODesktop onlySecurity & Monitoring

Overview

AI-generated overview

Local MCP server that adds AI agent governance to MCP workflows: PII detection, policy enforcement, compliance checks and a kill switch.

What you can do
  • Detect and flag personally identifiable information in agent activity
  • Apply and enforce governance policies on agent actions
  • Support compliance checks for agent workflows
  • Provide a kill switch to stop agent activity
  • All of this is exposed to the assistant through the Tork governance service rather than a documented tool list
When to use it
Worth adding when an assistant or agent runs in a setting where outputs and actions must be screened for PII, constrained by policy, or audited for compliance, and you want a way to halt it quickly.
Requirements
Runs as a local stdio process from the npm package @torknetwork/mcp-server, so Node.js is needed. Requires a Tork API key supplied in the TORK_API_KEY environment variable, obtained from the Tork admin site. Desktop-only; no remote endpoint.
Before you install
The server needs a Tork API key, a credential that should be kept out of shared configs and logs. Agent activity and content screened for PII are presumably sent to the Tork service, so review what leaves the machine. The kill switch and policy enforcement can block or stop agent actions, so test policies before relying on them.

Installation

In SourceWeft

  1. Open Tork Governance 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

This repository has no README.

Tools

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

Version history

1
  1. v1.5.1LatestSep 16, 2026

Score

25% 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

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.