Atomadic MCP

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.

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Optional stable id to track your onboarding state across calls."
    }
  }
}

[agents] Detect contradictions in agent outputs

{
  "type": "object",
  "properties": {
    "statements": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "example": [
        "The model accuracy is 95%",
        "The model fails 20% of the time"
      ]
    }
  },
  "required": [
    "statements"
  ]
}

[agents] Agent intent classification

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "example": "I need to fetch user data and store it in the database"
    }
  },
  "required": [
    "text"
  ]
}

[agents] Autonomous agent goal planning

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "example": "Deploy a web service with zero downtime"
    },
    "constraints": {
      "type": "object",
      "description": "Optional constraints for the plan (e.g., time limits, resource caps)",
      "additionalProperties": true
    }
  },
  "required": [
    "goal"
  ]
}

[agents] Register an agent

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "example": "my-agent-001"
    },
    "capabilities": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "example": [
        "inference",
        "planning",
        "code-generation"
      ]
    }
  },
  "required": [
    "agent_id",
    "capabilities"
  ]
}

[agents] Agent reputation and trust score

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "example": "my-agent-001"
    }
  },
  "required": [
    "agent_id"
  ]
}

[agents] Semantic diff between agent outputs

{
  "type": "object",
  "properties": {
    "output_a": {
      "type": "string"
    },
    "output_b": {
      "type": "string"
    },
    "context": {
      "type": "string"
    }
  },
  "required": [
    "output_a",
    "output_b"
  ]
}

[agents] Live swarm topology

{
  "type": "object",
  "properties": {}
}

[security] GDPR/CCPA compliance gate

{
  "type": "object",
  "properties": {
    "data_type": {
      "type": "string",
      "example": "user_pii"
    },
    "jurisdiction": {
      "type": "string",
      "example": "EU"
    },
    "operation": {
      "type": "string",
      "example": "store"
    }
  },
  "required": [
    "data_type",
    "jurisdiction",
    "operation"
  ]
}

[security] EU AI Act compliance certificate

{
  "type": "object",
  "properties": {
    "system_id": {
      "type": "string"
    },
    "risk_category": {
      "type": "string",
      "enum": [
        "minimal",
        "limited",
        "high",
        "unacceptable"
      ]
    },
    "intended_purpose": {
      "type": "string"
    }
  },
  "required": [
    "system_id",
    "risk_category",
    "intended_purpose"
  ]
}

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

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string"
    },
    "decision_id": {
      "type": "string"
    },
    "subject_context": {
      "type": "object"
    }
  },
  "required": [
    "model_id",
    "decision_id",
    "subject_context"
  ]
}

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

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string"
    },
    "dataset_id": {
      "type": "string"
    },
    "protected_attrs": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "metric": {
      "type": "string",
      "example": "demographic_parity"
    }
  },
  "required": [
    "model_id",
    "dataset_id",
    "protected_attrs",
    "metric"
  ]
}

[security] Report compliance incident

{
  "type": "object",
  "properties": {
    "system_id": {
      "type": "string"
    },
    "severity": {
      "type": "string",
      "enum": [
        "low",
        "medium",
        "high",
        "critical"
      ]
    },
    "description": {
      "type": "string"
    },
    "affected_users": {
      "type": "integer"
    }
  },
  "required": [
    "system_id",
    "severity",
    "description",
    "affected_users"
  ]
}

[security] Incident registry

{
  "type": "object",
  "properties": {
    "system_id": {
      "type": "string"
    }
  },
  "required": [
    "system_id"
  ]
}

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

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string"
    },
    "dataset_stages": {
      "type": "array",
      "items": {
        "type": "object"
      }
    }
  },
  "required": [
    "model_id",
    "dataset_stages"
  ]
}

[security] Log oversight event

{
  "type": "object",
  "properties": {
    "system_id": {
      "type": "string"
    },
    "reviewer_id": {
      "type": "string"
    },
    "decision": {
      "type": "string"
    },
    "notes": {
      "type": "string"
    }
  },
  "required": [
    "system_id",
    "reviewer_id",
    "decision",
    "notes"
  ]
}

[security] Oversight history

{
  "type": "object",
  "properties": {
    "system_id": {
      "type": "string"
    }
  },
  "required": [
    "system_id"
  ]
}

[security] Transparency report

{
  "type": "object",
  "properties": {
    "system_id": {
      "type": "string"
    },
    "period": {
      "type": "string",
      "example": "2026-Q1"
    },
    "include": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "example": [
        "incidents",
        "oversight",
        "fairness"
      ]
    }
  },
  "required": [
    "system_id",
    "period",
    "include"
  ]
}

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

{
  "type": "object",
  "properties": {
    "bridge_id": {
      "type": "string"
    },
    "source_chain": {
      "type": "string"
    },
    "dest_chain": {
      "type": "string"
    },
    "amount": {
      "type": "number"
    },
    "token": {
      "type": "string"
    }
  },
  "required": [
    "bridge_id",
    "source_chain",
    "dest_chain",
    "amount",
    "token"
  ]
}

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

{
  "type": "object",
  "properties": {
    "contract_id": {
      "type": "string"
    },
    "contract_type": {
      "type": "string",
      "example": "erc20"
    }
  },
  "required": [
    "contract_id",
    "contract_type"
  ]
}

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

{
  "type": "object",
  "properties": {
    "position_id": {
      "type": "string"
    },
    "collateral_value": {
      "type": "number"
    },
    "debt_value": {
      "type": "number"
    },
    "collateral_factor": {
      "type": "number",
      "format": "float"
    }
  },
  "required": [
    "position_id",
    "collateral_value",
    "debt_value",
    "collateral_factor"
  ]
}

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

{
  "type": "object",
  "properties": {
    "protocol": {
      "type": "string",
      "example": "uniswap_v3"
    },
    "position": {
      "type": "object",
      "properties": {
        "token_a": {
          "type": "string",
          "example": "ETH"
        },
        "token_b": {
          "type": "string",
          "example": "USDC"
        },
        "amount_usd": {
          "type": "number",
          "example": 10000
        }
      }
    },
    "risk_tolerance": {
      "type": "number",
      "format": "float",
      "example": 0.5
    }
  },
  "required": [
    "protocol",
    "position",
    "risk_tolerance"
  ]
}

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

{
  "type": "object",
  "properties": {
    "oracle_address": {
      "type": "string"
    },
    "price_feed": {
      "type": "string"
    },
    "reference_price": {
      "type": "number"
    },
    "asset": {
      "type": "string"
    },
    "tvl_at_risk": {
      "type": "number"
    }
  },
  "required": [
    "oracle_address",
    "price_feed",
    "reference_price",
    "asset",
    "tvl_at_risk"
  ]
}

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

{
  "type": "object",
  "properties": {
    "protocol": {
      "type": "string"
    },
    "position": {
      "type": "object"
    },
    "market_conditions": {
      "type": "object"
    }
  },
  "required": [
    "protocol",
    "position",
    "market_conditions"
  ]
}

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

{
  "type": "object",
  "properties": {
    "principal_usd": {
      "type": "number",
      "example": 10000
    },
    "risk_tolerance": {
      "type": "number",
      "format": "float",
      "example": 0.5
    }
  },
  "required": [
    "principal_usd",
    "risk_tolerance"
  ]
}

[trust] Drift certificate

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    }
  },
  "required": [
    "id"
  ]
}

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

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string"
    },
    "reference_window": {
      "type": "object"
    },
    "current_window": {
      "type": "object"
    }
  },
  "required": [
    "model_id",
    "reference_window",
    "current_window"
  ]
}

[defi] Create agent-to-agent escrow

{
  "type": "object",
  "properties": {
    "payer_id": {
      "type": "string"
    },
    "payee_id": {
      "type": "string"
    },
    "amount": {
      "type": "number"
    },
    "currency": {
      "type": "string"
    },
    "conditions": {
      "type": "object"
    }
  },
  "required": [
    "payer_id",
    "payee_id",
    "amount",
    "currency"
  ]
}

[defi] Open escrow dispute

{
  "type": "object",
  "properties": {
    "escrow_id": {
      "type": "string"
    },
    "reason": {
      "type": "string"
    },
    "evidence": {
      "type": "object"
    }
  },
  "required": [
    "escrow_id",
    "reason"
  ]
}

[defi] Release escrowed funds

{
  "type": "object",
  "properties": {
    "escrow_id": {
      "type": "string"
    }
  },
  "required": [
    "escrow_id"
  ]
}

[fuse] Model quality badge

{
  "type": "object",
  "properties": {}
}

[fuse] Submit a model delta

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string"
    },
    "delta": {
      "type": "object"
    },
    "description": {
      "type": "string"
    }
  },
  "required": [
    "model_id",
    "delta"
  ]
}

[fuse] Model leaderboard

{
  "type": "object",
  "properties": {}
}

[fuse] Quarantined models

{
  "type": "object",
  "properties": {}
}

[fuse] Verify a model submission

{
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string"
    },
    "verification_type": {
      "type": "string"
    }
  },
  "required": [
    "model_id"
  ]
}

[identity] Sybil-resistance check

{
  "type": "object",
  "properties": {}
}

[identity] Topological identity verification

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "example": "my-agent-001"
    }
  },
  "required": [
    "agent_id"
  ]
}

[inference] Chat inference with hallucination guard

{
  "type": "object",
  "properties": {
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "role",
          "content"
        ],
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "user",
              "assistant",
              "system"
            ],
            "description": "Message role"
          },
          "content": {
            "type": "string",
            "description": "Message content"
          }
        }
      },
      "example": [
        {
          "role": "user",
          "content": "What is formal verification?"
        }
      ]
    }
  },
  "required": [
    "messages"
  ]
}

[inference] Streaming inference with chain-of-thought

{
  "type": "object",
  "properties": {
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "role",
          "content"
        ],
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "user",
              "assistant",
              "system"
            ],
            "description": "Message role"
          },
          "content": {
            "type": "string",
            "description": "Message content"
          }
        }
      },
      "example": [
        {
          "role": "user",
          "content": "Explain formal verification step by step."
        }
      ]
    }
  },
  "required": [
    "messages"
  ]
}

[trust] Entropy epoch oracle

{
  "type": "object",
  "properties": {}
}

[trust] Hallucination oracle

{
  "type": "object",
  "properties": {
    "claim": {
      "type": "string",
      "example": "Water boils at 100°C at sea level"
    },
    "context": {
      "type": "string",
      "example": "physics"
    }
  },
  "required": [
    "claim"
  ]
}

[inference] Trusted RAG augmentation

{
  "type": "object"
}

[identity] RatchetGate — advance session

{
  "type": "object",
  "properties": {
    "session_id": {
      "type": "string",
      "example": "sess-001"
    }
  },
  "required": [
    "session_id"
  ]
}

[identity] RatchetGate — health probe

{
  "type": "object",
  "properties": {}
}

[identity] RatchetGate — register session

{
  "type": "object",
  "properties": {
    "session_id": {
      "type": "string",
      "example": "sess-001"
    }
  },
  "required": [
    "session_id"
  ]
}

[agents] Record agent interaction

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "interaction_type": {
      "type": "string"
    },
    "outcome": {
      "type": "string",
      "enum": [
        "positive",
        "negative",
        "neutral"
      ]
    },
    "counterparty_id": {
      "type": "string"
    }
  },
  "required": [
    "agent_id",
    "interaction_type",
    "outcome"
  ]
}

[inference] Quantum random number with proof

{
  "type": "object",
  "properties": {}
}

[inference] Verify current epoch random value

{
  "type": "object",
  "properties": {}
}

[security] Zero-day threat assessment

{
  "type": "object",
  "properties": {
    "target": {
      "type": "string"
    },
    "context": {
      "type": "object"
    }
  },
  "required": [
    "target"
  ]
}

[agents] Register an SLA

{
  "type": "object",
  "properties": {
    "provider_id": {
      "type": "string"
    },
    "consumer_id": {
      "type": "string"
    },
    "terms": {
      "type": "object"
    }
  },
  "required": [
    "provider_id",
    "consumer_id",
    "terms"
  ]
}

[agents] Report SLA violation

{
  "type": "object",
  "properties": {
    "sla_id": {
      "type": "string"
    },
    "violation_type": {
      "type": "string"
    },
    "description": {
      "type": "string"
    }
  },
  "required": [
    "sla_id",
    "violation_type"
  ]
}

[agents] Poll swarm inbox

{
  "type": "object",
  "properties": {}
}

[agents] Relay message through swarm

{
  "type": "object",
  "properties": {
    "target_agent_id": {
      "type": "string"
    },
    "message": {
      "type": "object"
    },
    "ttl": {
      "type": "integer",
      "description": "Hop limit for relay"
    }
  },
  "required": [
    "target_agent_id",
    "message"
  ]
}

[inference] Keyword extraction

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "max_keywords": {
      "type": "integer",
      "example": 10
    }
  },
  "required": [
    "text"
  ]
}

[inference] Sentiment analysis

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "example": "This API is incredibly reliable and easy to use."
    }
  },
  "required": [
    "text"
  ]
}

[inference] Text summarization

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "example": "Formal verification is the act of proving or disproving the correctness of intended algorithms underlying a system with respect to a certain formal specification or property, using formal methods of mathematics."
    }
  },
  "required": [
    "text"
  ]
}

[security] Multi-vector threat score

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "example": "my-agent-001"
    },
    "context": {
      "type": "string",
      "example": "multi-agent-transaction"
    }
  },
  "required": [
    "agent_id"
  ]
}

[trust] Current trust ceiling value

{
  "type": "object",
  "properties": {}
}

[trust] Trust score history

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string"
    }
  },
  "required": [
    "agent_id"
  ]
}

[trust] Bounded trust score

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string"
    }
  },
  "required": [
    "agent_id"
  ]
}

[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'.

{
  "type": "object",
  "properties": {
    "inputs": {
      "type": "object",
      "description": "The work/claim payload to recompute a digest over."
    },
    "claimed_digest": {
      "type": "string",
      "description": "The agent's claimed SHA-256 digest to verify against. Omit for UNVERIFIED + the recomputed digest."
    }
  },
  "required": [
    "inputs"
  ]
}

[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'.

{
  "type": "object",
  "properties": {
    "inputs": {
      "type": "object",
      "description": "The work payload backing the settlement."
    },
    "claimed_digest": {
      "type": "string",
      "description": "Claimed digest the payout is conditioned on."
    }
  },
  "required": [
    "inputs"
  ]
}

[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'.

{
  "type": "object",
  "properties": {
    "receipts": {
      "type": "array",
      "description": "List of receipt objects, each with an 'ok' boolean and optional 'score'."
    }
  },
  "required": [
    "receipts"
  ]
}

[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'.

{
  "type": "object",
  "properties": {
    "claims": {
      "type": "array",
      "description": "List of claim objects, each with a 'key' (or 'subject') and a 'value'."
    }
  },
  "required": [
    "claims"
  ]
}

[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'.

{
  "type": "object",
  "properties": {
    "inputs": {
      "type": "object",
      "description": "The work payload to verify."
    },
    "claimed_digest": {
      "type": "string",
      "description": "Claimed digest the obligation is conditioned on."
    },
    "obligation": {
      "type": "string",
      "description": "Human-readable obligation label."
    }
  },
  "required": [
    "inputs"
  ]
}

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

{
  "type": "object",
  "properties": {
    "intent": {
      "type": "string",
      "description": "The natural-language intent to route."
    }
  },
  "required": [
    "intent"
  ]
}

[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.

{
  "type": "object",
  "properties": {
    "source_text": {
      "type": "string",
      "description": ""
    },
    "atom_name": {
      "type": "string",
      "description": ""
    },
    "language": {
      "type": "string",
      "description": ""
    }
  },
  "required": [
    "source_text",
    "atom_name"
  ]
}

[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.

{
  "type": "object",
  "properties": {
    "source_text": {
      "type": "string",
      "description": ""
    },
    "atom_name": {
      "type": "string",
      "description": ""
    }
  },
  "required": [
    "source_text",
    "atom_name"
  ]
}