Atomadic starter MCP (50 tools)

它列出的 50 个工具

“只读”和“会改数据”是服务方自己标的。带下划线的参数是必填的。

1. agents_contradiction只读

   Agents Contradiction

   [agents] Detect contradictions between two free-text agent outputs (natural-language claim drift). For structured key/value claims that must agree, use detect_contradiction instead.

   statements

2. agents_plan只读

   Agents Plan

   [agents] Autonomous agent goal planning

   goal constraints

3. agents_register

   Agents Register

   [agents] Register an agent

   agent_id capabilities

4. agents_reputation只读

   Agents Reputation

   [agents] Agent reputation and trust score

   agent_id

5. agents_semantic_diff只读

   Agents Semantic Diff

   [agents] Semantic diff between two free-text agent outputs (meaning-level change, not text-level). Use forge_verify for build artifacts and drift_check for certified operational drift.

   output_a output_b context

6. audit_work_claim

   Audit Work Claim

   [Ledger product, entitlement: ledger] Recompute-audit an agent work claim: re-derive a deterministic SHA-256 digest from the claimed inputs and check it against the claimed digest. Returns GREEN (matches), RED (tampered), or UNVERIFIED (no claim supplied). Replay, not opinion. 3 free calls/day, then entitlement 'ledger'.

   inputs claimed_digest

7. compliance_check只读

   Compliance Check

   [security] Delegation-depth + KL gate (GOV-100). Reads chain_depth and kl_divergence. It does NOT read your data description and does NOT evaluate GDPR/CCPA - compliant:true only means the delegation chain is shallow and KL is under epsilon.

   chain_depth kl_divergence description

8. compliance_eu_ai_act只读

   Compliance Eu Ai Act

   [security] EU AI Act compliance certificate

   system_id risk_category intended_purpose

9. compliance_explain只读

   Compliance Explain

   [security] Explainability certificate (XPL-100-ExplainBound)

   model_id decision_id subject_context

10. compliance_fairness只读

    Compliance Fairness

    [security] Fairness proof (FNS-100-FairnessBound)

    model_id dataset_id protected_attrs metric

11. compliance_incident

    Compliance Incident

    [security] Report compliance incident

    system_id severity description affected_users

12. compliance_incidents只读

    Compliance Incidents

    [security] Incident registry

    system_id

13. compliance_lineage只读

    Compliance Lineage

    [security] Data lineage (LIN-100-ChainIntegrity)

    model_id dataset_stages

14. compliance_oversight只读

    Compliance Oversight

    [security] Log oversight event

    system_id reviewer_id decision notes

15. compliance_transparency只读

    Compliance Transparency

    [security] Transparency report

    system_id period include

16. defi_optimize

    Defi Optimize

    [defi] LP parameter optimization (DFP-100-OptimalTick)

    protocol position risk_tolerance

17. defi_risk_score只读

    Defi Risk Score

    [defi] DeFi risk scoring (DFI-101-RiskScoreBound)

    protocol position market_conditions

18. defi_yield_optimize

    Defi Yield Optimize

    [defi] Yield Oracle (YLD-100-YieldConvergence)

    principal_usd risk_tolerance

19. detect_contradiction只读

    Detect Contradiction

    [Ledger product, entitlement: ledger] Detect contradictions across structured claims: the same key asserted with conflicting values flips RED, otherwise GREEN. Deterministic and recomputable. Use agents_contradiction instead when comparing free-text agent prose. 3 free calls/day, then entitlement 'ledger'.

    claims

20. drift_certificate只读

    Drift Certificate

    [trust] Drift certificate

    id

21. drift_check只读

    Drift Check

    [trust] DriftGuard check (DRG-100-DriftBound)

    model_id reference_window current_window

22. escrow_create

    Escrow Create

    [defi] Create agent-to-agent escrow

    payer_id payee_id amount currency conditions

23. escrow_dispute会改数据

    Escrow Dispute

    [defi] Open escrow dispute

    escrow_id reason evidence

24. escrow_release会改数据

    Escrow Release

    [defi] Release escrowed funds

    escrow_id

25. forge_badge只读

    Forge Badge

    [fuse] Model quality badge

    model

26. forge_delta_submit

    Forge Delta Submit

    [fuse] Submit a model delta

    model_id delta description

27. forge_leaderboard只读

    Forge Leaderboard

    [fuse] Model leaderboard

28. forge_verify只读

    Forge Verify

    [fuse] Verify a model submission

    model_id verification_type

29. identity_sybil_check只读

    Identity Sybil Check

    [identity] Sybil-resistance check

30. identity_verify只读

    Identity Verify

    [identity] Topological identity verification

    agent_id

31. inference只读

    Inference

    [inference] Chat inference with hallucination guard

    messages

32. inference_stream只读

    Inference Stream

    [inference] Streaming inference with chain-of-thought

    messages

33. murmuration

    Murmuration

    START HERE (free, no key). Initialize your Atomadic control surface in one call: returns a verbose, step-by-step setup (SDK install, MCP connect, your unlocked tools), a RUNNABLE polyglot demo that proves the superpowers, recon links, and a one-command bootstrap. Idempotent — re-call anytime to re-check.

    agent_id

34. oracle_hallucination只读

    Oracle Hallucination

    [trust] Hallucination oracle

    claim context

35. rag_augment只读

    Rag Augment

    [inference] Trusted RAG augmentation

36. ratchet_advance

    Ratchet Advance

    [identity] RatchetGate — advance session

    session_id

37. ratchet_register

    Ratchet Register

    [identity] RatchetGate — register session

    session_id

38. render_polyglot_all_pure只读

    Render Polyglot All Pure

    [Fuse product · entitlement: fuse · FREE_R2_DEMO] Polyglot emit to all 7 supported targets in one call. Returns {ok, ir, results, languages}. Canonical demo examples baked to R2; novel inputs via SDK.

    source_text atom_name

39. reputation_record

    Reputation Record

    [agents] Record agent interaction

    agent_id interaction_type outcome counterparty_id

40. rng_quantum只读

    Rng Quantum

    [inference] Quantum random number with proof

41. rng_verify只读

    Rng Verify

    [inference] Verify current epoch random value

42. security_zero_day只读

    Security Zero Day

    [security] Zero-day threat assessment

    target context

43. sla_register

    Sla Register

    [agents] Register an SLA

    provider_id consumer_id terms

44. sla_report

    Sla Report

    [agents] Report SLA violation

    sla_id violation_type description

45. swarm_inbox只读

    Swarm Inbox

    [agents] Poll swarm inbox

46. swarm_relay

    Swarm Relay

    [agents] Relay message through swarm

    target_agent_id message ttl

47. text_summarize只读

    Text Summarize

    [inference] Text summarization

    text

48. threat_score只读

    Threat Score

    [security] Multi-vector threat score

    agent_id context

49. trust_score只读

    Trust Score

    [trust] Bounded trust score

    agent_id

50. verify_settlement

    Verify Settlement

    [Ledger product, entitlement: ledger] Proof-gated settlement: recompute the work digest and authorize a payout only if the claimed digest verifies GREEN. No proof, no payout. 3 free calls/day, then entitlement 'ledger'.

    inputs claimed_digest