io.github.atomadictech/aaaa-nexus

Atomadic starter MCP (50 tools)

50 starter MCP tools for AI compliance and trust: identity, escrow, SLA, EU AI Act.

Endpoint	`https://mcp.atomadic.tech/mcp/public` (streamable-http)
Registry version	0.5.2
Now	50 tools · grade D (53) · pin `ts_6d6c8d6e5517b1a87398e234c0c25fa8` · protocol 2024-11-05
First / last listed	2026-11-12 01:38 UTC / 2026-11-12 01:38 UTC
Grade over time	2026-11-12: D (53), 50 tools

Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.

Timeline

First listing · 2026-11-12 01:38 UTC
50 tools, grade D (53)

Tools: murmuration agents_contradiction agents_semantic_diff agents_register agents_reputation agents_plan reputation_record sla_register sla_report swarm_inbox swarm_relay compliance_check compliance_eu_ai_act compliance_explain compliance_fairness compliance_lineage compliance_transparency compliance_incident compliance_incidents compliance_oversight security_zero_day threat_score defi_optimize defi_risk_score defi_yield_optimize escrow_create escrow_release escrow_dispute forge_badge forge_leaderboard forge_verify forge_delta_submit identity_verify identity_sybil_check ratchet_register ratchet_advance inference inference_stream rag_augment text_summarize rng_quantum rng_verify trust_score drift_check drift_certificate oracle_hallucination audit_work_claim verify_settlement detect_contradiction render_polyglot_all_pure

Current tools (50)

`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. params: agent_id
`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. params: statements*
`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. params: output_a, output_b, context
`agents_register`	[agents] Register an agent params: agent_id, capabilities
`agents_reputation`	[agents] Agent reputation and trust score params: agent_id*
`agents_plan`	[agents] Autonomous agent goal planning params: goal*, constraints
`reputation_record`	[agents] Record agent interaction params: agent_id, interaction_type, outcome*, counterparty_id
`sla_register`	[agents] Register an SLA params: provider_id, consumer_id, terms*
`sla_report`	[agents] Report SLA violation params: sla_id, violation_type, description
`swarm_inbox`	[agents] Poll swarm inbox params: none
`swarm_relay`	[agents] Relay message through swarm params: target_agent_id, message, ttl
`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. params: chain_depth, kl_divergence, description
`compliance_eu_ai_act`	[security] EU AI Act compliance certificate params: system_id, risk_category, intended_purpose*
`compliance_explain`	[security] Explainability certificate (XPL-100-ExplainBound) params: model_id, decision_id, subject_context*
`compliance_fairness`	[security] Fairness proof (FNS-100-FairnessBound) params: model_id, dataset_id, protected_attrs, metric
`compliance_lineage`	[security] Data lineage (LIN-100-ChainIntegrity) params: model_id, dataset_stages
`compliance_transparency`	[security] Transparency report params: system_id, period, include*
`compliance_incident`	[security] Report compliance incident params: system_id, severity, description, affected_users
`compliance_incidents`	[security] Incident registry params: system_id*
`compliance_oversight`	[security] Log oversight event params: system_id, reviewer_id, decision, notes
`security_zero_day`	[security] Zero-day threat assessment params: target*, context
`threat_score`	[security] Multi-vector threat score params: agent_id*, context
`defi_optimize`	[defi] LP parameter optimization (DFP-100-OptimalTick) params: protocol, position, risk_tolerance*
`defi_risk_score`	[defi] DeFi risk scoring (DFI-101-RiskScoreBound) params: protocol, position, market_conditions*
`defi_yield_optimize`	[defi] Yield Oracle (YLD-100-YieldConvergence) params: principal_usd, risk_tolerance
`escrow_create`	[defi] Create agent-to-agent escrow params: payer_id, payee_id, amount, currency, conditions
`escrow_release`	[defi] Release escrowed funds params: escrow_id*
`escrow_dispute`	[defi] Open escrow dispute params: escrow_id, reason, evidence
`forge_badge`	[fuse] Model quality badge params: model*
`forge_leaderboard`	[fuse] Model leaderboard params: none
`forge_verify`	[fuse] Verify a model submission params: model_id*, verification_type
`forge_delta_submit`	[fuse] Submit a model delta params: model_id, delta, description
`identity_verify`	[identity] Topological identity verification params: agent_id*
`identity_sybil_check`	[identity] Sybil-resistance check params: none
`ratchet_register`	[identity] RatchetGate â€” register session params: session_id*
`ratchet_advance`	[identity] RatchetGate â€” advance session params: session_id*
`inference`	[inference] Chat inference with hallucination guard params: messages*
`inference_stream`	[inference] Streaming inference with chain-of-thought params: messages*
`rag_augment`	[inference] Trusted RAG augmentation params: none
`text_summarize`	[inference] Text summarization params: text*
`rng_quantum`	[inference] Quantum random number with proof params: none
`rng_verify`	[inference] Verify current epoch random value params: none
`trust_score`	[trust] Bounded trust score params: agent_id*
`drift_check`	[trust] DriftGuard check (DRG-100-DriftBound) params: model_id, reference_window, current_window*
`drift_certificate`	[trust] Drift certificate params: id*
`oracle_hallucination`	[trust] Hallucination oracle params: claim*, context
`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'. params: inputs*, claimed_digest
`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'. params: inputs*, claimed_digest
`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'. params: claims*
`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. params: source_text, atom_name

Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.