Atomadic MCP

tech.atomadic由 atomadic.tech 發布官方發布者v0.6.9更新於 Oct 24, 2026

Atomadic MCP：68個確定性工具，用於代理身份、託管、SLA及歐盟AI法案合規。

AI 翻譯由 AI 模型根據下方的原文描述翻譯，可能有誤。

原文描述

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

已驗證Streamable HTTP可網頁執行安全與監控AI 與機器學習

概覽

Atomadic 的託管 MCP 服務（mcp.atomadic.tech），由 atomadic.tech 發布；無需登入；Streamable HTTP；68 個工具。

暫無 AI 概覽：以下資訊來自註冊中心條目和服務本身。

發布者
atomadic.tech
端點
mcp.atomadic.tech
最近檢查

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Atomadic MCP，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/tech.atomadic%2Fatomadic/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

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

工具

68

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-check.

輸入參數agent_id

agents_contradiction

[agents] Detect contradictions in agent outputs

輸入參數statements必填

agents_intent_classify

[agents] Agent intent classification

輸入參數text必填

agents_plan

[agents] Autonomous agent goal planning

輸入參數goal必填constraints

agents_register

[agents] Register an agent

輸入參數agent_id必填capabilities必填

agents_reputation

[agents] Agent reputation and trust score

輸入參數agent_id必填

agents_semantic_diff

[agents] Semantic diff between agent outputs

輸入參數contextoutput_a必填output_b必填

agents_topology

[agents] Live swarm topology

無需輸入參數。

compliance_check

[security] GDPR/CCPA compliance gate

輸入參數data_type必填operation必填jurisdiction必填

compliance_eu_ai_act

[security] EU AI Act compliance certificate

輸入參數system_id必填risk_category必填intended_purpose必填

compliance_explain

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

輸入參數model_id必填decision_id必填subject_context必填

compliance_fairness

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

輸入參數metric必填model_id必填dataset_id必填protected_attrs必填

compliance_incident

[security] Report compliance incident

輸入參數severity必填system_id必填description必填affected_users必填

compliance_incidents

[security] Incident registry

輸入參數system_id必填

compliance_lineage

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

輸入參數model_id必填dataset_stages必填

compliance_oversight

[security] Log oversight event

輸入參數notes必填decision必填system_id必填reviewer_id必填

compliance_oversight_history

[security] Oversight history

輸入參數system_id必填

compliance_transparency

[security] Transparency report

輸入參數period必填include必填system_id必填

defi_bridge_verify

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

輸入參數token必填amount必填bridge_id必填dest_chain必填source_chain必填

defi_contract_audit

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

輸入參數contract_id必填contract_type必填

defi_liquidation_check

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

輸入參數debt_value必填position_id必填collateral_value必填collateral_factor必填

defi_optimize

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

輸入參數position必填protocol必填risk_tolerance必填

defi_oracle_verify

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

輸入參數asset必填price_feed必填tvl_at_risk必填oracle_address必填reference_price必填

defi_risk_score

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

輸入參數position必填protocol必填market_conditions必填

defi_yield_optimize

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

輸入參數principal_usd必填risk_tolerance必填

drift_certificate

[trust] Drift certificate

輸入參數id必填

drift_check

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

輸入參數model_id必填current_window必填reference_window必填

escrow_create

[defi] Create agent-to-agent escrow

輸入參數amount必填currency必填payee_id必填payer_id必填conditions

escrow_dispute

[defi] Open escrow dispute

輸入參數reason必填evidenceescrow_id必填

escrow_release

[defi] Release escrowed funds

輸入參數escrow_id必填

forge_badge_{model}

[fuse] Model quality badge

無需輸入參數。

forge_delta_submit

[fuse] Submit a model delta

輸入參數delta必填model_id必填description

forge_leaderboard

[fuse] Model leaderboard

無需輸入參數。

forge_quarantine

[fuse] Quarantined models

無需輸入參數。

forge_verify

[fuse] Verify a model submission

輸入參數model_id必填verification_type

identity_sybil_check

[identity] Sybil-resistance check

無需輸入參數。

identity_verify

[identity] Topological identity verification

輸入參數agent_id必填

inference

[inference] Chat inference with hallucination guard

輸入參數messages必填

inference_stream

[inference] Streaming inference with chain-of-thought

輸入參數messages必填

oracle_entropy

[trust] Entropy epoch oracle

無需輸入參數。

oracle_hallucination

[trust] Hallucination oracle

輸入參數claim必填context

rag_augment

[inference] Trusted RAG augmentation

無需輸入參數。

ratchet_advance

[identity] RatchetGate — advance session

輸入參數session_id必填

ratchet_probe

[identity] RatchetGate — health probe

無需輸入參數。

ratchet_register

[identity] RatchetGate — register session

輸入參數session_id必填

reputation_record

[agents] Record agent interaction

輸入參數outcome必填agent_id必填counterparty_idinteraction_type必填

rng_quantum

[inference] Quantum random number with proof

無需輸入參數。

rng_verify

[inference] Verify current epoch random value

無需輸入參數。

security_zero_day

[security] Zero-day threat assessment

輸入參數target必填context

sla_register

[agents] Register an SLA

輸入參數terms必填consumer_id必填provider_id必填

sla_report

[agents] Report SLA violation

輸入參數sla_id必填descriptionviolation_type必填

swarm_inbox

[agents] Poll swarm inbox

無需輸入參數。

swarm_relay

[agents] Relay message through swarm

輸入參數ttlmessage必填target_agent_id必填

text_keywords

[inference] Keyword extraction

輸入參數text必填max_keywords

text_sentiment

[inference] Sentiment analysis

輸入參數text必填

text_summarize

[inference] Text summarization

輸入參數text必填

threat_score

[security] Multi-vector threat score

輸入參數contextagent_id必填

trust_decay

[trust] Current trust ceiling value

無需輸入參數。

trust_history

[trust] Trust score history

輸入參數agent_id必填

trust_score

[trust] Bounded trust score

輸入參數agent_id必填

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 entitlement 'ledger'.

輸入參數inputs必填claimed_digest

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'.

輸入參數inputs必填claimed_digest

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'.

輸入參數receipts必填

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'.

輸入參數claims必填

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'.

輸入參數inputs必填obligationclaimed_digest

route_capability

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

輸入參數intent必填

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.

輸入參數languageatom_name必填source_text必填

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.

輸入參數atom_name必填source_text必填

版本歷史

1
  1. v0.6.9最新Oct 17, 2026

評分

已滿足適用檢查項的 83%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分

    請宣告包含 README 的 GitHub 儲存庫，或在 OAuth 受保護資源後設資料中提供 resource_documentation。

  • 授權條款不適用

    託管服務按其提供方的條款使用，因此這裡不要求授權條款。此檢查項不計入百分比。

其他 Atomadic 整合

Atomadic Nexus

tech.atomadic

Atomadic Nexus 是一個本機 MCP 伺服器，自稱代理經濟的信任層，提供 32 個工具，涵蓋信任閘門、x402、溯源與群體協作。

STDIO僅桌面
金融尚未驗證Oct 24, 2026

Atomadic Forge

由 GitHub 帳號 atomadictech 發布

Atomadic Forge 是可遠端或本機執行的 MCP 伺服器，提供 68 個工具，涵蓋代理程式協作、合規憑證、DeFi 風險檢查、託管與模型驗證。

Streamable HTTP可網頁執行
金融68 個工具Nov 1, 2026

Atomadic starter MCP (50 tools)

由 GitHub 帳號 atomadictech 發布

Atomadic 託管 MCP 端點，提供 50 個入門工具，涵蓋 AI 合規、代理信任、身分、託管與推論，需付費 API 金鑰解鎖。

Streamable HTTP可網頁執行
金融50 個工具Oct 29, 2026