Home / MCP registry index / com.decision-anchor/da
Decision Anchor
com.decision-anchor/da in the official MCP registry.
Endpoint https://mcp.decision-anchor.com/mcp. Source: github.com/zse4321/decision-anchor-sdk.
The registry describes it as: External anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.
We read its 30 tools on 2026-10-27. Nothing in them matched our tool-poisoning rules.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
register_agent get_agent_profile create_decision confirm_decision propose_bilateral get_decision list_decisions observe_environment observe_pattern list_tools register_tool purchase_tool create_ise_session get_ise_status exit_ise_session get_dac_balance get_dac_ur get_trial_status create_sdac_session run_sdac_trial get_sdac_session end_sdac_session get_documentation list_classifications compare_anomaly get_evidence_report get_environment_anomaly get_decision_metadata_distribution get_self_classification_distribution submit_feedback
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-decision-anchor-da)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.