Atomadic starter MCP (50 tools)
50 starter MCP tools for AI compliance and trust: identity, escrow, SLA, EU AI Act.
사용해야 할까요
품질 및 안전성
발견 사항 (30)
- LOWagents_contradiction에서
- LOWagents_register에서
- LOWagents_reputation에서
- LOWagents_plan에서
- LOWsla_register에서
- LOWsla_report에서
- LOWswarm_inbox에서
- LOWswarm_relay에서
- LOWcompliance_eu_ai_act에서
- LOWcompliance_explain에서
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"aaaa-nexus": {
"url": "https://aaaa-nexus.atomadictech.workers.dev/mcp"
}
}
}원격 엔드포인트
https://aaaa-nexus.atomadictech.workers.dev/mcpstreamable-httphttps://mcp.atomadic.tech/mcp/publicstreamable-http할 수 있는 일
도구 목록
도구 (50)
⚪murmuration(agent_id)
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.
입력 스키마
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"description": "Optional stable id to track your onboarding state across calls."
}
}
}🟢agents_contradiction(statements)
[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.
입력 스키마
{
"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_semantic_diff(output_a, output_b, context)
[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.
입력 스키마
{
"type": "object",
"properties": {
"output_a": {
"type": "string"
},
"output_b": {
"type": "string"
},
"context": {
"type": "string"
}
},
"required": [
"output_a",
"output_b"
]
}⚪agents_register(agent_id, capabilities)
[agents] Register an agent
입력 스키마
{
"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_reputation(agent_id)
[agents] Agent reputation and trust score
입력 스키마
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"example": "my-agent-001"
}
},
"required": [
"agent_id"
]
}🟢agents_plan(goal, constraints)
[agents] Autonomous agent goal planning
입력 스키마
{
"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"
]
}⚪reputation_record(agent_id, interaction_type, outcome, counterparty_id)
[agents] Record agent interaction
입력 스키마
{
"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"
]
}⚪sla_register(provider_id, consumer_id, terms)
[agents] Register an SLA
입력 스키마
{
"type": "object",
"properties": {
"provider_id": {
"type": "string"
},
"consumer_id": {
"type": "string"
},
"terms": {
"type": "object"
}
},
"required": [
"provider_id",
"consumer_id",
"terms"
]
}⚪sla_report(sla_id, violation_type, description)
[agents] Report SLA violation
입력 스키마
{
"type": "object",
"properties": {
"sla_id": {
"type": "string"
},
"violation_type": {
"type": "string"
},
"description": {
"type": "string"
}
},
"required": [
"sla_id",
"violation_type"
]
}🟢swarm_inbox
[agents] Poll swarm inbox
입력 스키마
{
"type": "object",
"properties": {}
}⚪swarm_relay(target_agent_id, message, ttl)
[agents] Relay message through swarm
입력 스키마
{
"type": "object",
"properties": {
"target_agent_id": {
"type": "string"
},
"message": {
"type": "object"
},
"ttl": {
"type": "integer",
"description": "Hop limit for relay"
}
},
"required": [
"target_agent_id",
"message"
]
}🟢compliance_check(chain_depth, kl_divergence, description)
[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.
입력 스키마
{
"type": "object",
"properties": {
"chain_depth": {
"type": "integer",
"description": "Delegation chain depth. Higher = deeper hand-off. Past the gate threshold the result escalates to quarantine_escalation.",
"example": 0
},
"kl_divergence": {
"type": "number",
"description": "eps_KL divergence of the current policy from baseline. Above epsilon fails the gate.",
"example": 0
},
"description": {
"type": "string",
"description": "Free text. Accepted for readability and IGNORED by the gate. It never changes the verdict."
}
},
"additionalProperties": false
}🟢compliance_eu_ai_act(system_id, risk_category, intended_purpose)
[security] EU AI Act compliance certificate
입력 스키마
{
"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"
]
}🟢compliance_explain(model_id, decision_id, subject_context)
[security] Explainability certificate (XPL-100-ExplainBound)
입력 스키마
{
"type": "object",
"properties": {
"model_id": {
"type": "string"
},
"decision_id": {
"type": "string"
},
"subject_context": {
"type": "object"
}
},
"required": [
"model_id",
"decision_id",
"subject_context"
]
}🟢compliance_fairness(model_id, dataset_id, protected_attrs, metric)
[security] Fairness proof (FNS-100-FairnessBound)
입력 스키마
{
"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"
]
}🟢compliance_lineage(model_id, dataset_stages)
[security] Data lineage (LIN-100-ChainIntegrity)
입력 스키마
{
"type": "object",
"properties": {
"model_id": {
"type": "string"
},
"dataset_stages": {
"type": "array",
"items": {
"type": "object"
}
}
},
"required": [
"model_id",
"dataset_stages"
]
}🟢compliance_transparency(system_id, period, include)
[security] Transparency report
입력 스키마
{
"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"
]
}⚪compliance_incident(system_id, severity, description, affected_users)
[security] Report compliance incident
입력 스키마
{
"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"
]
}🟢compliance_incidents(system_id)
[security] Incident registry
입력 스키마
{
"type": "object",
"properties": {
"system_id": {
"type": "string"
}
},
"required": [
"system_id"
]
}🟢compliance_oversight(system_id, reviewer_id, decision, notes)
[security] Log oversight event
입력 스키마
{
"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_zero_day(target, context)
[security] Zero-day threat assessment
입력 스키마
{
"type": "object",
"properties": {
"target": {
"type": "string"
},
"context": {
"type": "object"
}
},
"required": [
"target"
]
}🟢threat_score(agent_id, context)
[security] Multi-vector threat score
입력 스키마
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"example": "my-agent-001"
},
"context": {
"type": "string",
"example": "multi-agent-transaction"
}
},
"required": [
"agent_id"
]
}⚪defi_optimize(protocol, position, risk_tolerance)
[defi] LP parameter optimization (DFP-100-OptimalTick)
입력 스키마
{
"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_risk_score(protocol, position, market_conditions)
[defi] DeFi risk scoring (DFI-101-RiskScoreBound)
입력 스키마
{
"type": "object",
"properties": {
"protocol": {
"type": "string"
},
"position": {
"type": "object"
},
"market_conditions": {
"type": "object"
}
},
"required": [
"protocol",
"position",
"market_conditions"
]
}⚪defi_yield_optimize(principal_usd, risk_tolerance)
[defi] Yield Oracle (YLD-100-YieldConvergence)
입력 스키마
{
"type": "object",
"properties": {
"principal_usd": {
"type": "number",
"example": 10000
},
"risk_tolerance": {
"type": "number",
"format": "float",
"example": 0.5
}
},
"required": [
"principal_usd",
"risk_tolerance"
]
}🟡escrow_create(payer_id, payee_id, amount, currency, conditions)
[defi] Create agent-to-agent escrow
입력 스키마
{
"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"
]
}🔴escrow_release(escrow_id)
[defi] Release escrowed funds
입력 스키마
{
"type": "object",
"properties": {
"escrow_id": {
"type": "string"
}
},
"required": [
"escrow_id"
]
}🔴escrow_dispute(escrow_id, reason, evidence)
[defi] Open escrow dispute
입력 스키마
{
"type": "object",
"properties": {
"escrow_id": {
"type": "string"
},
"reason": {
"type": "string"
},
"evidence": {
"type": "object"
}
},
"required": [
"escrow_id",
"reason"
]
}🟢forge_badge(model)
[fuse] Model quality badge
입력 스키마
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id to fetch the quality badge for.",
"example": "gpt-4o"
}
},
"required": [
"model"
]
}🟢forge_leaderboard
[fuse] Model leaderboard
입력 스키마
{
"type": "object",
"properties": {}
}🟢forge_verify(model_id, verification_type)
[fuse] Verify a model submission
입력 스키마
{
"type": "object",
"properties": {
"model_id": {
"type": "string"
},
"verification_type": {
"type": "string"
}
},
"required": [
"model_id"
]
}🟡forge_delta_submit(model_id, delta, description)
[fuse] Submit a model delta
입력 스키마
{
"type": "object",
"properties": {
"model_id": {
"type": "string"
},
"delta": {
"type": "object"
},
"description": {
"type": "string"
}
},
"required": [
"model_id",
"delta"
]
}🟢identity_verify(agent_id)
[identity] Topological identity verification
입력 스키마
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"example": "my-agent-001"
}
},
"required": [
"agent_id"
]
}🟢identity_sybil_check
[identity] Sybil-resistance check
입력 스키마
{
"type": "object",
"properties": {}
}⚪ratchet_register(session_id)
[identity] RatchetGate — register session
입력 스키마
{
"type": "object",
"properties": {
"session_id": {
"type": "string",
"example": "sess-001"
}
},
"required": [
"session_id"
]
}⚪ratchet_advance(session_id)
[identity] RatchetGate — advance session
입력 스키마
{
"type": "object",
"properties": {
"session_id": {
"type": "string",
"example": "sess-001"
}
},
"required": [
"session_id"
]
}🟢inference(messages)
[inference] Chat inference with hallucination guard
입력 스키마
{
"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_stream(messages)
[inference] Streaming inference with chain-of-thought
입력 스키마
{
"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"
]
}🟢rag_augment
[inference] Trusted RAG augmentation
입력 스키마
{
"type": "object"
}🟢text_summarize(text)
[inference] Text summarization
입력 스키마
{
"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"
]
}🟢rng_quantum
[inference] Quantum random number with proof
입력 스키마
{
"type": "object",
"properties": {}
}🟢rng_verify
[inference] Verify current epoch random value
입력 스키마
{
"type": "object",
"properties": {}
}🟢trust_score(agent_id)
[trust] Bounded trust score
입력 스키마
{
"type": "object",
"properties": {
"agent_id": {
"type": "string"
}
},
"required": [
"agent_id"
]
}🟢drift_check(model_id, reference_window, current_window)
[trust] DriftGuard check (DRG-100-DriftBound)
입력 스키마
{
"type": "object",
"properties": {
"model_id": {
"type": "string"
},
"reference_window": {
"type": "object"
},
"current_window": {
"type": "object"
}
},
"required": [
"model_id",
"reference_window",
"current_window"
]
}🟢drift_certificate(id)
[trust] Drift certificate
입력 스키마
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
]
}🟢oracle_hallucination(claim, context)
[trust] Hallucination oracle
입력 스키마
{
"type": "object",
"properties": {
"claim": {
"type": "string",
"example": "Water boils at 100°C at sea level"
},
"context": {
"type": "string",
"example": "physics"
}
},
"required": [
"claim"
]
}🟢audit_work_claim(inputs, claimed_digest)
[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'.
입력 스키마
{
"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"
]
}⚪verify_settlement(inputs, claimed_digest)
[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'.
입력 스키마
{
"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"
]
}🟢detect_contradiction(claims)
[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'.
입력 스키마
{
"type": "object",
"properties": {
"claims": {
"type": "array",
"description": "List of claim objects, each with a 'key' (or 'subject') and a 'value'."
}
},
"required": [
"claims"
]
}🟢render_polyglot_all_pure(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.
입력 스키마
{
"type": "object",
"properties": {
"source_text": {
"type": "string",
"description": ""
},
"atom_name": {
"type": "string",
"description": ""
}
},
"required": [
"source_text",
"atom_name"
]
}커뮤니티
증거