decision-anchor/mcp-server
by Various
External anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.
MCP
decision-anchor/mcp-server
Added 3 Sept 2026
Overview
External anchoring layer that records AI agent accountability boundaries on both sides. Content-blind, so it does not inspect or interpret the data passing through. Written in JavaScript.
Best for
Best for
Teams needing privacy-preserving audit trails for AI agent boundaries
Use cases
- Logging agent permission boundaries for audit trails
- Tracking accountability between agent and host systems
- Recording boundary changes over time
Notes
External anchoring layer that records AI agent accountability boundaries on both sides. Content-blind, so it does not inspect or interpret the data passing through. Written in JavaScript.
0 stars on GitHub. Last updated 2026-08-29. Licensed Apache-2.0.
Use cases
- Logging agent permission boundaries for audit trails
- Tracking accountability between agent and host systems
- Recording boundary changes over time
Pros
- Content-blind design preserves privacy
- Lightweight external layer with minimal interference
- Simple JavaScript implementation
Cons
- No content awareness limits violation detection
- Requires external setup and maintenance
- No built-in enforcement, only recording
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Content-blind design preserves privacy
- Lightweight external layer with minimal interference
- Simple JavaScript implementation
Cons
- No content awareness limits violation detection
- Requires external setup and maintenance
- No built-in enforcement, only recording
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.