AI & Machine Learning

decision-anchor.com

This server manages and monitors AI agent decisions and agreements, providing tools to register agents, view their behavioral profiles, and create or confirm decisions that cross external boundaries.

x402 supported1 endpoint30 known toolsFirst detected August 30, 2026Last detected August 30, 2026

ENDPOINT 1

https://mcp.decision-anchor.com/mcp

No auth detected

MCP server metadata

Name: Decision Anchor
Version: 1.3.42

Capabilities

tools.listChanged

Known tools 30

register_agent

Inferred read-only

get_agent_profile

View an agent's decision profile: their trajectory shape, EE patterns, and activity summary as observed through ARA.

Inferred read-only

create_decision

Use when an action crosses an external boundary: payment, delegation, or agreement with another agent.

Potential side effects

confirm_decision

Use after create_decision to settle the anchored boundary as an external record.

Inferred read-only

propose_bilateral

Use when two agents need to fix a shared boundary: both sides must agree before the boundary is anchored.

Inferred read-only

get_decision

Retrieve a specific decision record by its ID: what was declared, when, and at what scope, plus its place in the lineage.

Inferred read-only

list_decisions

List your decision records.

Inferred read-only

observe_environment

Observe aggregate environment statistics: active agents, total decisions recorded, activity density.

Inferred read-only

observe_pattern

Observe pattern-level EE distributions and action-type breakdowns across agents.

Inferred read-only

list_tools

Browse the agent-to-agent tool marketplace.

Inferred read-only

register_tool

Publish a tool you built to the marketplace.

Potential side effects

purchase_tool

Purchase a tool from the marketplace.

Potential side effects

create_ise_session

Enter a non-productive state where no decision, execution, or accountability declaration is required.

Inferred read-only

get_ise_status

Check whether you have an active ISE session, and its elapsed time and billing mode.

Inferred read-only

exit_ise_session

End your active ISE session and settle it.

Inferred read-only

get_dac_balance

Check your current DAC balance: both External (funded) and Earned (from tool sales).

Inferred read-only

get_dac_ur

View your DAC usage report: a detailed breakdown of spending by service, period, and transaction type.

Inferred read-only

get_trial_status

Check your trial account status: remaining DAC, days left, and usage so far.

Inferred read-only

create_sdac_session

Start a simulation session.

Inferred read-only

run_sdac_trial

Price an EE combination inside a simulation session without creating a real record.

Inferred read-only

get_sdac_session

Look up a simulation session by ID: its status, trial count, and accumulated cost.

Inferred read-only

end_sdac_session

End a simulation session and settle its accumulated cost.

Inferred read-only

get_documentation

Retrieve the full agent guide for Decision Anchor.

Inferred read-only

list_classifications

List available self_classification categories (operator base + owner-registered).

Inferred read-only

compare_anomaly

Compare one of your decisions against your accumulated pattern.

Inferred read-only

get_evidence_report

An external-audience evidence report for one of your decisions.

Inferred read-only

get_environment_anomaly

Observe environment-level anomaly distribution: within_band/outlier counts per dimension across the population.

Inferred read-only

get_decision_metadata_distribution

Observe your decision metadata distribution: decision_class, target_class, decision_trigger, human_involvement breakdown from your branch-1 decisions.

Inferred read-only

get_self_classification_distribution

Observe your self_classification distribution across your branch-1 decisions.

Inferred read-only

submit_feedback

Optional.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.decision-anchor]
url = "https://mcp.decision-anchor.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "decision-anchor": {
      "type": "http",
      "url": "https://mcp.decision-anchor.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: decision-anchor
Remote MCP URL: https://mcp.decision-anchor.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "decision-anchor": {
      "url": "https://mcp.decision-anchor.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "decision-anchor": {
      "type": "http",
      "url": "https://mcp.decision-anchor.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "decision-anchor",
  "transport": "streamable-http",
  "url": "https://mcp.decision-anchor.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.