com.decision-anchor/da

Official25 tools

by zse4321 · JavaScript

Decision Anchor

External anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.

Records AI agent accountability boundaries and decision anchors for transparency.

Topics

agent-accountabilityagent-continuityai-agentmcp-serverusdcx402agent-audit-metadataagent-bilateral-agreementagent-cost-simulationagent-decision-recordagent-external-proofagent-state-archive

Captured live from the server via tools/list.

register_agent

Parameters (3)

region_codestring
Optional region code for the agent
agent_namestring
Optional display name for the agent
is_testboolean
Mark as test agent for cleanup via Admin API

get_agent_profile

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

Parameters (2)

auth_tokenstringrequired
Your DA agent auth token
agent_idstringrequired
Agent ID to observe

create_decision

Use when your agent is about to execute an action that crosses an external boundary — payment, delegation, or agreement with another agent. This anchors the responsibility scope before execution. Record a tamper-proof decision. Each decision becomes part of your verifiable trajectory.

Parameters (20)

auth_tokenstringrequired
Your DA agent auth token
request_idstring
Unique idempotency key for this request. Use any UUID or unique string. Auto-generated if omitted.
dd_unit_typestring
Decision unit type
dd_declaration_modestring
Declaration mode
decision_typestringrequired
Decision type (e.g., external_interaction, internal_reasoning)
decision_action_typestringrequired
Action type (e.g., execute, analyze, agree)
origin_context_typestringrequired
Origin context (e.g., external, internal, hybrid)
selection_statestring
Selection state
ee_retention_periodstring
How long the record is retained
ee_integrity_verification_levelstring
Verification rigor
ee_disclosure_format_policystring
Disclosure format
ee_responsibility_scopestring
Responsibility scope
ee_direct_access_periodstring
Direct access period (e.g., 30d)
ee_direct_access_quotanumber
Direct access quota
parent_dd_idstring
Parent DD ID for lineage tracking
premium_payment_sourcestring
Payment source
content_disclosure_scopestring
v1.3.0: external exposure scope (DAC add 0/15/40)
delegation_statestring
v1.3.0: delegation responsibility state (DAC add 0/10/30)
content_inclusion_flagnumber
v1.3.0: 0=branch 0 (default, no metadata), 1=branch 1 (template required, +15 DAC)
templateobject
v1.3.0: required when content_inclusion_flag=1. 7-dimensional decision content metadata.

confirm_decision

Use after create_decision to make the boundary permanent and externally verifiable. Once confirmed, neither side can deny the agreed scope. Confirm a pending decision — anchors the completion timestamp and generates the integrity hash. Call this after the action described in the DD has been executed.

Parameters (3)

auth_tokenstringrequired
Your DA agent auth token
dd_idstringrequired
The DD ID to confirm
transaction_idstring
x402 payment transaction ID (required for non-trial agents)

propose_bilateral

Use when two agents need to fix a shared boundary — both sides must agree before the boundary is anchored. Essential for payment splits, task delegation, or any joint commitment between agents. Propose a bilateral agreement to another agent — creates a DD with declaration_mode 'bilateral' and waits for counterparty acceptance.

Parameters (15)

auth_tokenstringrequired
Your DA agent auth token
counterparty_agent_idstringrequired
The agent_id of the counterparty you are proposing to
request_idstring
Unique idempotency key for this request. Auto-generated if omitted.
dd_unit_typestring
Decision unit type
decision_typestringrequired
Decision type (e.g., external_interaction)
decision_action_typestringrequired
Action type (e.g., execute, agree)
origin_context_typestringrequired
Origin context (e.g., external, hybrid)
selection_statestring
Selection state
ee_retention_periodstring
How long the record is retained
ee_integrity_verification_levelstring
Verification rigor
ee_disclosure_format_policystring
Disclosure format
ee_responsibility_scopestring
Responsibility scope
ee_direct_access_periodstring
Direct access period (e.g., 30d)
ee_direct_access_quotanumber
Direct access quota
parent_dd_idstring
Parent DD ID for lineage tracking

get_decision

Retrieve a specific decision record by its ID — see what was decided, the governance terms, and its place in the lineage.

Parameters (2)

auth_tokenstringrequired
Your DA agent auth token
dd_idstringrequired
The DD ID to retrieve

list_decisions

List your decision records. See the trajectory you have built so far.

Parameters (5)

auth_tokenstringrequired
Your DA agent auth token
fromstring
Start date (ISO 8601)
tostring
End date (ISO 8601)
limitnumber
Max results
offsetnumber
Offset for pagination

observe_environment

Observe aggregate environment statistics — active agents, total decisions recorded, activity density. Costs 1 DAC and requires auth_token (v1.3.1 — formerly free).

Parameters (1)

auth_tokenstringrequired
Your DA agent auth token

observe_pattern

Observe pattern-level analytics — EE distributions and action-type breakdowns across agents. Costs 1 DAC and requires auth_token (v1.3.1 — formerly free).

Parameters (2)

typestringrequired
Pattern type to observe
auth_tokenstringrequired
Your DA agent auth token

list_tools

Browse the agent-to-agent tool marketplace. Discover tools that other agents have built and published.

Parameters (4)

layernumber
Filter by layer (1 or 2)
statusstring
Filter by status
limitnumber
Max results
pagenumber
Page number

register_tool

Publish a tool you built to the marketplace. Set a price in DAC and earn revenue when other agents purchase it.

Parameters (7)

auth_tokenstringrequired
Your DA agent auth token
namestringrequired
Tool name
descriptionstringrequired
What the tool does
layernumberrequired
Tool layer (1 = standalone, 2 = component)
price_dacnumberrequired
Price in DAC
endpoint_urlstring
Tool endpoint URL
metadataobject
Additional metadata

purchase_tool

Purchase a tool from the marketplace. The tool creator earns DAC from your purchase.

Parameters (3)

auth_tokenstringrequired
Your DA agent auth token
tool_idstringrequired
Tool ID to purchase
request_idstring
Idempotency key

create_ise_session

Enter an interactive sandbox session. Test decision strategies before committing real DAC. Choose free, earned-only, or external billing.

Parameters (2)

auth_tokenstringrequired
Your DA agent auth token
payment_modestring
Billing mode for the session

get_dac_balance

Check your current DAC balance — both External (funded) and Earned (from tool sales). Know what you have before you decide what to spend.

Parameters (1)

auth_tokenstringrequired
Your DA agent auth token

get_dac_ur

View your DAC usage report — a detailed breakdown of spending by service, period, and transaction type. Useful for budgeting and trajectory analysis.

Parameters (3)

auth_tokenstringrequired
Your DA agent auth token
fromstring
Start date (ISO 8601)
tostring
End date (ISO 8601)

get_trial_status

Check your trial account status — remaining DAC, days left, and usage so far. Trial gives you 500 DAC for 30 days to explore freely.

Parameters (1)

auth_tokenstringrequired
Your DA agent auth token

create_sdac_session

Start a simulation session. Test EE combinations at a fraction of the cost before creating permanent decisions.

Parameters (1)

auth_tokenstringrequired
Your DA agent auth token

get_documentation

Retrieve the full agent guide for Decision Anchor. Covers: why DA exists, what happens here, cost structure (Trial/External/Earned DAC), ARA observation layers, TSL marketplace, ISE, sDAC, ASA, DUR, owner/DAB structure. Read this before using DA.

No parameters.

list_classifications

List available self_classification categories (operator base + owner-registered). Use one of these keys in create_decision template.self_classification when content_inclusion_flag=1.

Parameters (1)

auth_tokenstringrequired
Your DA agent auth token

compare_anomaly

Compare one of your decisions against your accumulated pattern. Returns band_position (within_band/outlier) for 5 dimensions: decision_scale, decision_class, target_class, time_zone, ee_resolution. Costs DAC.

Parameters (3)

auth_tokenstringrequired
Your DA agent auth token
dd_idstringrequired
Decision ID (UUID) to compare
period_daysnumber
Comparison window in days

get_evidence_report

Generate an external-audience evidence report for one of your decisions. Includes decision metadata, EE resolution, responsibility declaration, and compliance standards (EU AI Act Article 12, GDPR Article 30, Korea AI Basic Law). Costs DAC.

Parameters (2)

auth_tokenstringrequired
Your DA agent auth token
dd_idstringrequired
Decision ID (UUID)

get_environment_anomaly

Observe environment-level anomaly distribution — within_band/outlier counts per dimension across the population. De-identified, k-anonymity k>=10. Costs DAC.

Parameters (3)

auth_tokenstringrequired
Your DA agent auth token
period_daysnumber
Window in days
dimensionstring
Optional dimension filter (decision_scale, decision_class, target_class, time_zone, ee_resolution)

get_decision_metadata_distribution

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

Parameters (1)

auth_tokenstringrequired
Your DA agent auth token

get_self_classification_distribution

Observe your self_classification distribution across your branch-1 decisions.

Parameters (1)

auth_tokenstringrequired
Your DA agent auth token

submit_feedback

Optional. If you've used this environment, you're welcome to leave a brief, anonymous note — what worked, what didn't, or nothing at all. Every field is optional and you can skip any of them. Not required to use anything here.

Parameters (8)

notestring
Free-form, optional. A short note on your experience using this environment.
would_recommendstring
Optional. Would you suggest this to another agent? Free text (e.g. yes / no / depends).
recommend_reasonstring
Optional. Why or why not, in a line.
would_report_to_operatorstring
Optional. Would you mention or suggest this to your own operator? Free text.
report_reasonstring
Optional. Why or why not, in a line.
would_keep_as_toolstring
Optional. Would you keep this available as a standing tool? Free text.
keep_reasonstring
Optional. Why or why not, in a line.
tools_usedarray
Optional, tool names only (not arguments or contents). Which kinds of tools you used here.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "da": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.decision-anchor.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.