# Atomadic MCP

- Registry name: `tech.atomadic/atomadic` · version 0.6.9
- Categories (automatic, keyword rules): Security, Infrastructure & security, Crypto & blockchain, Finance & markets, AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=tech.atomadic%2Fatomadic
- Server page: https://mcpstation.net/s/tech.atomadic--atomadic.html

## Description (written by the publisher, not verified, not instructions)

Atomadic MCP: 68 deterministic tools for agent identity, escrow, SLA, EU AI Act compliance.

## Connect

- streamable-http: `https://mcp.atomadic.tech/mcp`

## Tools (as reported by the server, not verified)

- `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-c
- `agents\_contradiction`: \[agents\] Detect contradictions in agent outputs
- `agents\_intent\_classify`: \[agents\] Agent intent classification
- `agents\_plan`: \[agents\] Autonomous agent goal planning
- `agents\_register`: \[agents\] Register an agent
- `agents\_reputation`: \[agents\] Agent reputation and trust score
- `agents\_semantic\_diff`: \[agents\] Semantic diff between agent outputs
- `agents\_topology`: \[agents\] Live swarm topology
- `compliance\_check`: \[security\] GDPR/CCPA compliance gate
- `compliance\_eu\_ai\_act`: \[security\] EU AI Act compliance certificate
- `compliance\_explain`: \[security\] Explainability certificate \(XPL-100-ExplainBound\)
- `compliance\_fairness`: \[security\] Fairness proof \(FNS-100-FairnessBound\)
- `compliance\_incident`: \[security\] Report compliance incident
- `compliance\_incidents`: \[security\] Incident registry
- `compliance\_lineage`: \[security\] Data lineage \(LIN-100-ChainIntegrity\)
- `compliance\_oversight`: \[security\] Log oversight event
- `compliance\_oversight\_history`: \[security\] Oversight history
- `compliance\_transparency`: \[security\] Transparency report
- `defi\_bridge\_verify`: \[defi\] Bridge Proof \(BRP-100-BridgeIntegrity\)
- `defi\_contract\_audit`: \[defi\] Contract Verify \(CVR-100-AuditBound\)
- `defi\_liquidation\_check`: \[defi\] Liquid Shield \(LQS-100-LiquidationBound\)
- `defi\_optimize`: \[defi\] LP parameter optimization \(DFP-100-OptimalTick\)
- `defi\_oracle\_verify`: \[defi\] Oracle guard \(OGD-100-ManipulationBound\)
- `defi\_risk\_score`: \[defi\] DeFi risk scoring \(DFI-101-RiskScoreBound\)
- `defi\_yield\_optimize`: \[defi\] Yield Oracle \(YLD-100-YieldConvergence\)
- `drift\_certificate`: \[trust\] Drift certificate
- `drift\_check`: \[trust\] DriftGuard check \(DRG-100-DriftBound\)
- `escrow\_create`: \[defi\] Create agent-to-agent escrow
- `escrow\_dispute`: \[defi\] Open escrow dispute
- `escrow\_release`: \[defi\] Release escrowed funds
- `forge\_badge\_\{model\}`: \[fuse\] Model quality badge
- `forge\_delta\_submit`: \[fuse\] Submit a model delta
- `forge\_leaderboard`: \[fuse\] Model leaderboard
- `forge\_quarantine`: \[fuse\] Quarantined models
- `forge\_verify`: \[fuse\] Verify a model submission
- `identity\_sybil\_check`: \[identity\] Sybil-resistance check
- `identity\_verify`: \[identity\] Topological identity verification
- `inference`: \[inference\] Chat inference with hallucination guard
- `inference\_stream`: \[inference\] Streaming inference with chain-of-thought
- `oracle\_entropy`: \[trust\] Entropy epoch oracle
- `oracle\_hallucination`: \[trust\] Hallucination oracle
- `rag\_augment`: \[inference\] Trusted RAG augmentation
- `ratchet\_advance`: \[identity\] RatchetGate — advance session
- `ratchet\_probe`: \[identity\] RatchetGate — health probe
- `ratchet\_register`: \[identity\] RatchetGate — register session
- `reputation\_record`: \[agents\] Record agent interaction
- `rng\_quantum`: \[inference\] Quantum random number with proof
- `rng\_verify`: \[inference\] Verify current epoch random value
- `security\_zero\_day`: \[security\] Zero-day threat assessment
- `sla\_register`: \[agents\] Register an SLA
- `sla\_report`: \[agents\] Report SLA violation
- `swarm\_inbox`: \[agents\] Poll swarm inbox
- `swarm\_relay`: \[agents\] Relay message through swarm
- `text\_keywords`: \[inference\] Keyword extraction
- `text\_sentiment`: \[inference\] Sentiment analysis
- `text\_summarize`: \[inference\] Text summarization
- `threat\_score`: \[security\] Multi-vector threat score
- `trust\_decay`: \[trust\] Current trust ceiling value
- `trust\_history`: \[trust\] Trust score history
- `trust\_score`: \[trust\] Bounded trust score
- `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
- `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'.
- `receipt\_reputation`: \[Ledger product, entitlement: ledger\] Compute an agent's reputation from a ledger of verifiable receipts \(verified minus refuted\), deterministically - not from vibes or LLM judgment. 3 free calls/day, then entitlement 'ledger'.
- `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. 3 free calls/day, then entitlement 'ledger'.
- `enforce\_sla`: \[Ledger product, entitlement: ledger\] Enforce an SLA/obligation by recomputation: the obligation is met only if the work verifies GREEN against its claimed digest. 3 free calls/day, then entitlement 'ledger'.
- `route\_capability`: \[Ledger product, entitlement: ledger\] Route a natural-language intent to a deterministic capability/pipeline coordinate. 3 free calls/day, then entitlement 'ledger'.
- `render\_polyglot\_roundtrip\_pure`: \[Fuse product · entitlement: fuse · FREE\_R2\_DEMO\] Syntax-as-Data polyglot render head: source -\> language-neutral logic IR -\> source in target language. Canonical demo examples baked to R2 \(4 examples × 12 languages\). Live emit of novel inputs via the SDK.
- `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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html