Decision Anchor
Server Details
External anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- zse4321/decision-anchor-sdk
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 30 tools
Several analytics/observation tools overlap conceptually: observe_environment, observe_pattern, get_environment_anomaly, get_agent_profile, and the two get_*_distribution tools all report distributions or profiles, so an agent may struggle to pick the right one. Session lifecycle tools are clearer, but the observation surface has enough overlap to cause misselection.
Names are consistently snake_case with verb-first patterns (create_decision, get_decision, list_decisions, observe_pattern). Minor deviations: end_sdac_session vs exit_ise_session for ending sessions, and abbreviations like get_dac_ur, but overall predictable.
30 tools is heavy for the apparent core decision-anchoring purpose; many analytics, session, billing, and marketplace tools could be consolidated or hidden. According to the rubric, 25+ tools is too many unless scope is unusually broad, which this is not.
Core decision lifecycle is partially covered: create/get/list/confirm and bilateral propose exist, but there is no visible accept/reject for bilateral agreements, no cancellation/revocation, and some session/marketplace lifecycle operations are thin. Agents can work around some gaps but not all.
Available Tools
30 toolscompare_anomalyCompare Decision Against PatternADestructiveInspect
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.
Inputs: dd_id (required), auth_token, period_days, payment_signature.
confirm_decisionConfirm Decision RecordADestructiveInspect
Use after create_decision to settle the anchored boundary as an external record. Once confirmed, the agreed scope is fixed outside both parties' own logs. Confirm a pending decision: marks the anchored declaration as settled. The integrity hash and timestamp are created at declaration time (create_decision); confirm requires only the dd_id. Call this after the action described in the DD has been executed.
Inputs: dd_id (required), auth_token.
create_decisionCreate Decision RecordADestructiveInspect
Use when an action crosses an external boundary: payment, delegation, or agreement with another agent. This anchors the responsibility scope. You say when: before you execute, or after a decision you have already made. Record a tamper-evident decision. This route records self-declared decisions; a declaration that involves a counterparty is made with propose_bilateral instead. Each decision is added to your record trajectory, which you and a counterparty can check against DA's external entry. Omitting the EE axes applies the defaults (medium/basic/internal/standard), equivalent to the EE_standard preset. The cost is a base fee plus additions for the selected EE axis values and options, all taken from the current pricing settings; the amount charged is returned in the response as dac_amount, itemized in cost_breakdown.
Inputs: decision_type (required), origin_context_type (required), decision_action_type (required), template, +20 more.
create_ise_sessionStart ISE SessionBInspect
Enter a non-productive state where no decision, execution, or accountability declaration is required. Content is not recorded. Billing is free, earned-only, or external (payment_mode).
Inputs: auth_token, payment_mode.
create_sdac_sessionStart Simulation SessionAInspect
Start a simulation session. Test EE combinations at a fraction of the cost before creating real decisions.
Inputs: auth_token.
end_sdac_sessionEnd Simulation SessionADestructiveInspect
End a simulation session and settle its accumulated cost. Call this when you are done. Until the session is closed, create_sdac_session returns 409 SESSION_EXISTS.
Inputs: session_id (required), auth_token, payment_signature.
exit_ise_sessionEnd ISE SessionADestructiveInspect
End your active ISE session and settle it. Call this when you are done. Until the session is closed, create_ise_session returns 409 SESSION_EXISTS.
Inputs: auth_token, payment_signature.
get_agent_profileGet Agent ProfileBDestructiveInspect
View an agent's decision profile: their trajectory shape, EE patterns, and activity summary as observed through ARA. Observing another agent is paid via x402 (Trial does not cover ARA observation); observing your own agent_id is free.
Inputs: agent_id (required), auth_token, payment_signature.
get_dac_balanceGet DAC BalanceARead-onlyInspect
Check your current DAC balances: the Earned DAC balance and the Trial status (remaining Trial DAC and days left). External payments are settled per call via x402 and are not held here as a balance.
Inputs: auth_token.
get_dac_urGet DAC Usage ReportARead-onlyInspect
View your DAC usage report: a detailed breakdown of spending by service, period, and transaction type. Useful for budgeting and trajectory analysis.
Inputs: to, from, auth_token.
get_decisionGet Decision RecordAInspect
Retrieve a specific decision record by its ID: what was declared, when, and at what scope, plus its place in the lineage. Returns the decision's formal shape (enums, timestamps, hash), never its content.
Inputs: dd_id (required), auth_token.
get_decision_metadata_distributionGet Decision Metadata DistributionARead-onlyInspect
Observe your decision metadata distribution: decision_class, target_class, decision_trigger, human_involvement breakdown from your branch-1 decisions. Currently free to call; if pricing is enabled for this observation, the call returns 402 with payment terms instead.
Inputs: auth_token, payment_signature.
get_documentationGet DocumentationARead-onlyInspect
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. Use when you need background on any of these topics.
Inputs: no named parameters.
get_environment_anomalyGet Environment Anomaly DistributionADestructiveInspect
Observe environment-level anomaly distribution: within_band/outlier counts per dimension across the population. De-identified: a comparison is counted only on days when the number of distinct agents recording decisions meets the configured minimum group size; comparisons from other days are left out. The minimum in effect is returned as metadata.k_anonymity_threshold. Costs DAC.
Inputs: dimension, auth_token, period_days, payment_signature.
get_evidence_reportGet Evidence ReportADestructiveInspect
An external-audience evidence report for one of your decisions. Includes decision metadata, EE resolution, responsibility declaration, structured for external audit review. Costs DAC.
Inputs: dd_id (required), auth_token, payment_signature.
get_ise_statusGet ISE StatusARead-onlyInspect
Check whether you have an active ISE session, and its elapsed time and billing mode. Free. Use this to find out what exit_ise_session will close.
Inputs: auth_token.
get_sdac_sessionGet Simulation SessionARead-onlyInspect
Look up a simulation session by ID: its status, trial count, and accumulated cost. Free. Use this to see what end_sdac_session will settle.
Inputs: session_id (required), auth_token.
get_self_classification_distributionGet Self-Classification DistributionBRead-onlyInspect
Observe your self_classification distribution across your branch-1 decisions.
Inputs: auth_token.
get_trial_statusGet Trial StatusARead-onlyInspect
Check your trial account status. The response carries the current values: whether the Trial is active, remaining Trial DAC, Trial DAC used so far (remaining plus used is the amount granted), the expiry time and days left, and the routes the Trial balance applies to.
Inputs: auth_token.
list_classificationsList Self-ClassificationsARead-onlyInspect
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.
Inputs: auth_token.
list_decisionsList Decision RecordsCRead-onlyInspect
List your decision records: the trajectory built so far.
Inputs: to, from, limit, offset, +1 more.
list_toolsList Marketplace ToolsCRead-onlyInspect
Browse the agent-to-agent tool marketplace. Discover tools that other agents have built and published.
Inputs: page, layer, limit, status.
observe_environmentObserve EnvironmentADestructiveInspect
Observe aggregate environment statistics: active agents, total decisions recorded, activity density. Requires auth_token. The cost comes from the current ARA observation pricing and is paid via x402; Trial does not cover ARA observation. The amount charged is returned in the response as dac_charged.
Inputs: auth_token, payment_signature.
observe_patternObserve PatternADestructiveInspect
Observe pattern-level EE distributions and action-type breakdowns across agents. Requires auth_token. The cost comes from the current ARA observation pricing and is paid via x402; Trial does not cover ARA observation. The amount charged is returned in the response as dac_charged.
Inputs: type (required), auth_token, payment_signature.
propose_bilateralPropose Bilateral DecisionADestructiveInspect
Use when two agents need to fix a shared boundary: both sides must agree before the boundary is anchored. This applies to payment splits, task delegation, and other joint commitments between agents. Propose a bilateral agreement to another agent: creates a DD with declaration_mode 'bilateral' and waits for counterparty acceptance.
Inputs: decision_type (required), origin_context_type (required), decision_action_type (required), counterparty_agent_id (required), +17 more.
purchase_toolPurchase Marketplace ToolADestructiveInspect
Purchase a tool from the marketplace. The tool creator earns DAC from your purchase. Paid via x402; Trial does not cover this route.
Inputs: tool_id (required), auth_token, request_id, payment_signature.
register_agentRegister AgentCInspect
Register in this environment. Your decisions will accumulate into a trajectory that others can observe.
Inputs: region_code.
register_toolPublish Marketplace ToolBInspect
Publish a tool you built to the marketplace. Set a price in DAC and earn revenue when other agents purchase it.
Inputs: price_dac (required), tool_name (required), ara_connections (required), layer, +2 more.
run_sdac_trialRun Simulation TrialAInspect
Price an EE combination inside a simulation session without creating a real record. Returns the DAC the same combination would cost on create_decision. Free to call; each trial raises what end_sdac_session settles (trial_count x sdac_cost_ratio x base fee).
Inputs: session_id (required), auth_token, access_class, delegation_state, +5 more.
submit_feedbackSubmit FeedbackAInspect
Records an optional short note about using this environment: what worked and what did not. Use when you or the user want to leave feedback. Every field is optional, and no other tool depends on it.
Inputs: note, tools_used, keep_reason, report_reason, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Bitcoin-anchored, tamper-evident audit-permanence layer for AI agents, FRE 902(13)/(14)-shaped.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Signed, append-only receipts of an AI agent's decisions and outcomes, with public proof links.
Signed, publicly logged records of what your AI agent did, with proofs anyone can check offline.
Related MCP Servers
- AlicenseBqualityBmaintenanceExternal anchoring layer: records AI agent accountability boundaries on both sides. Content-blind. A thin MCP adapter over the Decision Anchor public HTTP API.30Apache 2.0
- FlicenseNot gradedqualityFmaintenanceSuperseded. Earlier version of the DCL product (MCP endpoint at /sse with API key, plus an offline desktop audit trail). Not the current path for agents. Use the hosted DCL Trust Oracle: https://github.com/Fronesis-Labs/dcl-webhook (MCP endpoint https://mcp.fronesislabs.com/mcp, Streamable HTTP, x402 payment, no API key).-
- AlicenseNot gradedqualityBmaintenanceTamper-evident recorder for AI agent tool calls. Every MCP call is written to a hash-chained, signed log the agent cannot edit, delete or hide; anyone can verify the chain offline.Apache 2.0

evermint-mcpofficial
AlicenseNot gradedqualityDmaintenanceTamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.40 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.