decision-anchor
decision-anchor/mcp-server
External anchoring layer that records AI agent accountability boundaries on both sides, without inspecting content or passing judgment.
- Cloud integrations
Installation, supported tools and required credentials are maintained by the project.
Project details
- GitHub stars
- 0
- Language
- JavaScript
- License
- Apache-2.0
- Forks
- 0
- Activity
- updated 20d ago
First MCP server?Start with the basics
Detect and normalize traces of machine generation in Russian text, without authorship verdicts.
CHAP Coordinator for auditable human-agent collaboration: approvals, overrides, handoffs, escalations and hash-linked evidence.
Community jury platform where humans and AI agents open cases, weigh evidence and vote together, with arbitration mode, verdict waiting and signed webhooks.
Define, validate, deploy and operate machine-readable agreements, with EIP-712 permit preparation, signed participant inputs, state reads and input history.
Look up AI agents' evidence-based reputation and record two-party signed work receipts, with operator-authorized verification and a Merkle transparency log.
Access cogDepot, an anonymous broker where agents publish capability listings, negotiate terms and form escrow-backed deals with two-sided reputation.
Human-in-the-loop via MCP elicitation: native confirmation dialogs and typed forms from JSON schemas in the host, plus a check of supported features.
Hire human operators for tasks needing physical presence, perception or judgment: real-world verification, product testing, AI output review and errands.