Atomadic MCP server

• agents_contradictionFree

  [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_intent_classifyFree

  [agents] Agent intent classification

• agents_planFree

  [agents] Autonomous agent goal planning

• agents_registerFree

  [agents] Register an agent

• agents_reputationFree

  [agents] Agent reputation and trust score

• agents_semantic_diffFree

  [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.

• agents_topologyFree

  [agents] Live swarm topology

• audit_work_claimFree

  [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'.

• compliance_checkFree

  [security] GDPR/CCPA compliance gate

• compliance_eu_ai_actFree

  [security] EU AI Act compliance certificate

• compliance_explainFree

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

• compliance_fairnessFree

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

• compliance_incidentFree

  [security] Report compliance incident

• compliance_incidentsFree

  [security] Incident registry

• compliance_lineageFree

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

• compliance_oversightFree

  [security] Log oversight event

• compliance_oversight_historyFree

  [security] Oversight history

• compliance_transparencyFree

  [security] Transparency report

• defi_bridge_verifyFree

  [defi] Bridge Proof (BRP-100-BridgeIntegrity)

• defi_contract_auditFree

  [defi] Contract Verify (CVR-100-AuditBound)

• defi_liquidation_checkFree

  [defi] Liquid Shield (LQS-100-LiquidationBound)

• defi_optimizeFree

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

• defi_oracle_verifyFree

  [defi] Oracle guard (OGD-100-ManipulationBound)

• defi_risk_scoreFree

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

• defi_yield_optimizeFree

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

• detect_contradictionFree

  [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'.

• drift_certificateFree

  [trust] Drift certificate

• drift_checkFree

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

• enforce_slaFree

  [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'.

• escrow_createwrite actionFree

  [defi] Create agent-to-agent escrow

• escrow_disputeFree

  [defi] Open escrow dispute

• escrow_releaseFree

  [defi] Release escrowed funds

• forge_badgeFree

  [fuse] Model quality badge

• forge_delta_submitwrite actionFree

  [fuse] Submit a model delta

• forge_leaderboardFree

  [fuse] Model leaderboard

• forge_quarantineFree

  [fuse] Quarantined models

• forge_verifyFree

  [fuse] Verify a model submission

• identity_sybil_checkFree

  [identity] Sybil-resistance check

• identity_verifyFree

  [identity] Topological identity verification

• inferenceFree

  [inference] Chat inference with hallucination guard

• inference_streamFree

  [inference] Streaming inference with chain-of-thought

• murmurationFree

  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.

• oracle_entropyFree

  [trust] Entropy epoch oracle

• oracle_hallucinationFree

  [trust] Hallucination oracle

• rag_augmentFree

  [inference] Trusted RAG augmentation

• ratchet_advanceFree

  [identity] RatchetGate — advance session

• ratchet_probeFree

  [identity] RatchetGate — health probe

• ratchet_registerFree

  [identity] RatchetGate — register session

• receipt_reputationFree

  [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'.

• render_polyglot_all_pureFree

  [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.

• render_polyglot_roundtrip_pureFree

  [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.

• reputation_recordFree

  [agents] Record agent interaction

• rng_quantumFree

  [inference] Quantum random number with proof

• rng_verifyFree

  [inference] Verify current epoch random value

• route_capabilityFree

  [Ledger product, entitlement: ledger] Route a natural-language intent to a deterministic capability/pipeline coordinate. 3 free calls/day, then entitlement 'ledger'.

• security_zero_dayFree

  [security] Zero-day threat assessment

• sla_registerFree

  [agents] Register an SLA

• sla_reportFree

  [agents] Report SLA violation

• swarm_inboxFree

  [agents] Poll swarm inbox

• swarm_relayFree

  [agents] Relay message through swarm

• text_keywordsFree

  [inference] Keyword extraction

• text_sentimentFree

  [inference] Sentiment analysis

• text_summarizeFree

  [inference] Text summarization

• threat_scoreFree

  [security] Multi-vector threat score

• trust_decayFree

  [trust] Current trust ceiling value

• trust_historyFree

  [trust] Trust score history

• trust_scoreFree

  [trust] Bounded trust score

• verify_settlementFree

  [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'.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 321ms20/20
• Tool poisoning68 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 2 write-action tools with no auth3/15
• Maintenanceno repository listed3/15
• Maintainer identityendpoint served from the registry-verified namespace domain8/10

Safety score

65/100

higher than 25% of 4,460 AI and agents servers

Tools

68

the typical AI and agents server has 6

Tools that change things

3%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote AI and agents server answers 100%

Response time

45 ms

faster than 96% of 2,331 AI and agents servers

Atomadic MCP: common questions

Is Atomadic MCP server safe?

With care: it is graded C, so read the findings first (65/100). Read the Atomadic MCP safety report

How do I install Atomadic MCP?

It runs remotely at mcp.atomadic.tech. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Atomadic MCP need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Atomadic MCP maintained?

The latest release is v0.6.9.

Is Atomadic MCP up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of Atomadic MCP?

Servers from other publishers that do the same job: Attestix MCP server.

How does Atomadic MCP compare with other AI and agents MCP servers?

safety score 65/100 (higher than 25% of 4,460 AI and agents servers); tools 68 (the typical AI and agents server has 6); tools that change things 3% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.