MCP server

Atomadic MCP Official

tech.atomadic/atomadic

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

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

Website

At a glance

Type

MCP server

Publisher

atomadic.tech (verified by the MCP Registry)

Status

Working at last check

Tools

68

Token cost

About 5,600 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

25 Oct 2026, 20:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http atomadic https://mcp.atomadic.tech/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.atomadic]
url = "https://mcp.atomadic.tech/mcp"

Gemini CLI

{"mcpServers":{"atomadic":{"httpUrl":"https://mcp.atomadic.tech/mcp"}}}

Cursor

{"mcpServers":{"atomadic":{"url":"https://mcp.atomadic.tech/mcp"}}}

VS Code

{"servers":{"atomadic":{"type":"http","url":"https://mcp.atomadic.tech/mcp"}}}

Antigravity

agy mcp add atomadic https://mcp.atomadic.tech/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"atomadic","server_url":"https://mcp.atomadic.tech/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"atomadic","server_url":"https://mcp.atomadic.tech/mcp"}

Tools

• agents_contradiction ~86 tokens
  [agents] Detect contradictions in agent outputs
• agents_intent_classify ~71 tokens
  [agents] Agent intent classification
• agents_plan ~106 tokens
  [agents] Autonomous agent goal planning
• agents_register ~92 tokens
  [agents] Register an agent
• agents_reputation ~61 tokens
  [agents] Agent reputation and trust score
• agents_semantic_diff ~75 tokens
  [agents] Semantic diff between agent outputs
• agents_topology ~35 tokens
  [agents] Live swarm topology
• audit_work_claim ~195 tokens
  [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
• compliance_check ~94 tokens
  [security] GDPR/CCPA compliance gate
• compliance_eu_ai_act ~101 tokens
  [security] EU AI Act compliance certificate
• compliance_explain ~88 tokens
  [security] Explainability certificate (XPL-100-ExplainBound)
• compliance_fairness ~111 tokens
  [security] Fairness proof (FNS-100-FairnessBound)
• compliance_incident ~106 tokens
  [security] Report compliance incident
• compliance_incidents ~52 tokens
  [security] Incident registry
• compliance_lineage ~78 tokens
  [security] Data lineage (LIN-100-ChainIntegrity)
• compliance_oversight ~86 tokens
  [security] Log oversight event
• compliance_oversight_history ~54 tokens
  [security] Oversight history
• compliance_transparency ~100 tokens
  [security] Transparency report
• defi_bridge_verify ~102 tokens
  [defi] Bridge Proof (BRP-100-BridgeIntegrity)
• defi_contract_audit ~76 tokens
  [defi] Contract Verify (CVR-100-AuditBound)
• defi_liquidation_check ~109 tokens
  [defi] Liquid Shield (LQS-100-LiquidationBound)
• defi_optimize ~141 tokens
  [defi] LP parameter optimization (DFP-100-OptimalTick)
• defi_oracle_verify ~110 tokens
  [defi] Oracle guard (OGD-100-ManipulationBound)
• defi_risk_score ~84 tokens
  [defi] DeFi risk scoring (DFI-101-RiskScoreBound)
• defi_yield_optimize ~87 tokens
  [defi] Yield Oracle (YLD-100-YieldConvergence)
• detect_contradiction ~134 tokens
  [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'.
• drift_certificate ~46 tokens
  [trust] Drift certificate
• drift_check ~84 tokens
  [trust] DriftGuard check (DRG-100-DriftBound)
• enforce_sla ~163 tokens
  [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_create ~93 tokens
  [defi] Create agent-to-agent escrow
• escrow_dispute ~68 tokens
  [defi] Open escrow dispute
• escrow_release ~50 tokens
  [defi] Release escrowed funds
• forge_badge_{model} ~35 tokens
  [fuse] Model quality badge
• forge_delta_submit ~69 tokens
  [fuse] Submit a model delta
• forge_leaderboard ~34 tokens
  [fuse] Model leaderboard
• forge_quarantine ~34 tokens
  [fuse] Quarantined models
• forge_verify ~61 tokens
  [fuse] Verify a model submission
• identity_sybil_check ~38 tokens
  [identity] Sybil-resistance check
• identity_verify ~61 tokens
  [identity] Topological identity verification
• inference ~137 tokens
  [inference] Chat inference with hallucination guard
• inference_stream ~144 tokens
  [inference] Streaming inference with chain-of-thought
• murmuration ~144 tokens
  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
• oracle_entropy ~34 tokens
  [trust] Entropy epoch oracle
• oracle_hallucination ~76 tokens
  [trust] Hallucination oracle
• rag_augment ~31 tokens
  [inference] Trusted RAG augmentation
• ratchet_advance ~61 tokens
  [identity] RatchetGate — advance session
• ratchet_probe ~37 tokens
  [identity] RatchetGate — health probe
• ratchet_register ~61 tokens
  [identity] RatchetGate — register session
• receipt_reputation ~132 tokens
  [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_pure ~125 tokens
  [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_pure ~156 tokens
  [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_record ~100 tokens
  [agents] Record agent interaction
• rng_quantum ~38 tokens
  [inference] Quantum random number with proof
• rng_verify ~38 tokens
  [inference] Verify current epoch random value
• route_capability ~103 tokens
  [Ledger product, entitlement: ledger] Route a natural-language intent to a deterministic capability/pipeline coordinate. 3 free calls/day, then entitlement 'ledger'.
• security_zero_day ~60 tokens
  [security] Zero-day threat assessment
• sla_register ~72 tokens
  [agents] Register an SLA
• sla_report ~71 tokens
  [agents] Report SLA violation
• swarm_inbox ~33 tokens
  [agents] Poll swarm inbox
• swarm_relay ~83 tokens
  [agents] Relay message through swarm
• text_keywords ~61 tokens
  [inference] Keyword extraction
• text_sentiment ~65 tokens
  [inference] Sentiment analysis
• text_summarize ~112 tokens
  [inference] Text summarization
• threat_score ~76 tokens
  [security] Multi-vector threat score
• trust_decay ~36 tokens
  [trust] Current trust ceiling value
• trust_history ~49 tokens
  [trust] Trust score history
• trust_score ~48 tokens
  [trust] Bounded trust score
• verify_settlement ~147 tokens
  [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'.

Browse

• Crypto and blockchains

Related MCP servers

• Agent Arbitration
  Deterministic, machine-verifiable dispute resolution for A2A escrows.
• Mark
  Mark: stamp files with a signed, timestamped provenance record. Hash locally; verify free.
• Doti Protocol (.i) MCP Server
  Sovereign .i Web3 identity and multi-chain domain tools across four EVM networks.
• FacilityProof
  Source-reconciled U.S. environmental facility compliance evidence for AI agents.
• Xrpl Referee
  XRPL escrow for agent-to-agent payments: hire, prove, AI-audit, auto-pay on PASS.
• Tooloracle Xrploracle
  XRPLOracle - 31 XRP Ledger tools: payments, DEX, AMM, hooks, NFTs, validators, DIDs.
• Facet UCP Shopping
  The independent agent-commerce protocol for AI-agent checkout on any online store.
• Narrowhighway Concordance
  Deterministic claim verification with receipts across ~60 domains. No model in the loop.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/tech.atomadic/atomadic.svg)](https://aptlynx.net/servers/tech.atomadic/atomadic)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents