Atomadic starter MCP (50 tools)

[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.

[agents] Autonomous agent goal planning

[agents] Register an agent

[agents] Agent reputation and trust score

[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.

[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'.

[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.

[security] EU AI Act compliance certificate

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

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

[security] Report compliance incident

[security] Incident registry

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

[security] Log oversight event

[security] Transparency report

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

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

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

[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'.

[trust] Drift certificate

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

[defi] Create agent-to-agent escrow

[defi] Open escrow dispute

[defi] Release escrowed funds

[fuse] Model quality badge

[fuse] Submit a model delta

[fuse] Model leaderboard

[fuse] Verify a model submission

[identity] Sybil-resistance check

[identity] Topological identity verification

[inference] Chat inference with hallucination guard

[inference] Streaming inference with chain-of-thought

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.

[trust] Hallucination oracle

[inference] Trusted RAG augmentation

[identity] RatchetGate — advance session

[identity] RatchetGate — register session

[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.

[agents] Record agent interaction

[inference] Quantum random number with proof

[inference] Verify current epoch random value

[security] Zero-day threat assessment

[agents] Register an SLA

[agents] Report SLA violation

[agents] Poll swarm inbox

[agents] Relay message through swarm

[inference] Text summarization

[security] Multi-vector threat score

[trust] Bounded trust score

[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'.