Atomadic MCP

tech.atomadic由 atomadic.tech 发布官方发布者v0.6.9更新于 Oct 24, 2026

Atomadic MCP：68个确定性工具，用于代理身份、托管、SLA及欧盟AI法案合规。

AI 翻译由 AI 模型根据下方的原文描述翻译，可能有误。

原文描述

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

已验证Streamable HTTP可网页运行安全与监控AI 与机器学习

概览

Atomadic 的托管 MCP 服务（mcp.atomadic.tech），由 atomadic.tech 发布；无需登录；Streamable HTTP；68 个工具。

暂无 AI 概览：以下信息来自注册中心条目和服务本身。

发布者
atomadic.tech
端点
mcp.atomadic.tech
最近检查

安装

在 SourceWeft 中

  1. 打开 控制台中的 Atomadic MCP，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/tech.atomadic%2Fatomadic/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "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.

输入参数agent_id

agents_contradiction

[agents] Detect contradictions in agent outputs

输入参数statements必填

agents_intent_classify

[agents] Agent intent classification

输入参数text必填

agents_plan

[agents] Autonomous agent goal planning

输入参数goal必填constraints

agents_register

[agents] Register an agent

输入参数agent_id必填capabilities必填

agents_reputation

[agents] Agent reputation and trust score

输入参数agent_id必填

agents_semantic_diff

[agents] Semantic diff between agent outputs

输入参数contextoutput_a必填output_b必填

agents_topology

[agents] Live swarm topology

无需输入参数。

compliance_check

[security] GDPR/CCPA compliance gate

输入参数data_type必填operation必填jurisdiction必填

compliance_eu_ai_act

[security] EU AI Act compliance certificate

输入参数system_id必填risk_category必填intended_purpose必填

compliance_explain

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

输入参数model_id必填decision_id必填subject_context必填

compliance_fairness

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

输入参数metric必填model_id必填dataset_id必填protected_attrs必填

compliance_incident

[security] Report compliance incident

输入参数severity必填system_id必填description必填affected_users必填

compliance_incidents

[security] Incident registry

输入参数system_id必填

compliance_lineage

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

输入参数model_id必填dataset_stages必填

compliance_oversight

[security] Log oversight event

输入参数notes必填decision必填system_id必填reviewer_id必填

compliance_oversight_history

[security] Oversight history

输入参数system_id必填

compliance_transparency

[security] Transparency report

输入参数period必填include必填system_id必填

defi_bridge_verify

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

输入参数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)

输入参数contract_id必填contract_type必填

defi_liquidation_check

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

输入参数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)

输入参数position必填protocol必填risk_tolerance必填

defi_oracle_verify

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

输入参数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)

输入参数position必填protocol必填market_conditions必填

defi_yield_optimize

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

输入参数principal_usd必填risk_tolerance必填

drift_certificate

[trust] Drift certificate

输入参数id必填

drift_check

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

输入参数model_id必填current_window必填reference_window必填

escrow_create

[defi] Create agent-to-agent escrow

输入参数amount必填currency必填payee_id必填payer_id必填conditions

escrow_dispute

[defi] Open escrow dispute

输入参数reason必填evidenceescrow_id必填

escrow_release

[defi] Release escrowed funds

输入参数escrow_id必填

forge_badge_{model}

[fuse] Model quality badge

无需输入参数。

forge_delta_submit

[fuse] Submit a model delta

输入参数delta必填model_id必填description

forge_leaderboard

[fuse] Model leaderboard

无需输入参数。

forge_quarantine

[fuse] Quarantined models

无需输入参数。

forge_verify

[fuse] Verify a model submission

输入参数model_id必填verification_type

identity_sybil_check

[identity] Sybil-resistance check

无需输入参数。

identity_verify

[identity] Topological identity verification

输入参数agent_id必填

inference

[inference] Chat inference with hallucination guard

输入参数messages必填

inference_stream

[inference] Streaming inference with chain-of-thought

输入参数messages必填

oracle_entropy

[trust] Entropy epoch oracle

无需输入参数。

oracle_hallucination

[trust] Hallucination oracle

输入参数claim必填context

rag_augment

[inference] Trusted RAG augmentation

无需输入参数。

ratchet_advance

[identity] RatchetGate — advance session

输入参数session_id必填

ratchet_probe

[identity] RatchetGate — health probe

无需输入参数。

ratchet_register

[identity] RatchetGate — register session

输入参数session_id必填

reputation_record

[agents] Record agent interaction

输入参数outcome必填agent_id必填counterparty_idinteraction_type必填

rng_quantum

[inference] Quantum random number with proof

无需输入参数。

rng_verify

[inference] Verify current epoch random value

无需输入参数。

security_zero_day

[security] Zero-day threat assessment

输入参数target必填context

sla_register

[agents] Register an SLA

输入参数terms必填consumer_id必填provider_id必填

sla_report

[agents] Report SLA violation

输入参数sla_id必填descriptionviolation_type必填

swarm_inbox

[agents] Poll swarm inbox

无需输入参数。

swarm_relay

[agents] Relay message through swarm

输入参数ttlmessage必填target_agent_id必填

text_keywords

[inference] Keyword extraction

输入参数text必填max_keywords

text_sentiment

[inference] Sentiment analysis

输入参数text必填

text_summarize

[inference] Text summarization

输入参数text必填

threat_score

[security] Multi-vector threat score

输入参数contextagent_id必填

trust_decay

[trust] Current trust ceiling value

无需输入参数。

trust_history

[trust] Trust score history

输入参数agent_id必填

trust_score

[trust] Bounded trust score

输入参数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'.

输入参数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'.

输入参数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'.

输入参数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'.

输入参数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'.

输入参数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'.

输入参数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.

输入参数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.

输入参数atom_name必填source_text必填

版本历史

1
  1. v0.6.9最新Oct 17, 2026

评分

已满足适用检查项的 83%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库，或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证不适用

    托管服务按其提供方的条款使用，因此这里不要求许可证。此检查项不计入百分比。

其他 Atomadic 集成

Atomadic Nexus

tech.atomadic

Atomadic Nexus 是一个本地 MCP 服务器，自称代理经济的信任层，提供 32 个工具，涵盖信任门控、x402、溯源和群体协作。

STDIO仅桌面
金融尚未验证Oct 24, 2026

Atomadic Forge

由 GitHub 账号 atomadictech 发布

Atomadic Forge 是一个远程或本地运行的 MCP 服务器，提供 68 个工具，涵盖智能体编排、合规证书、DeFi 风险检查、托管与模型验证。

Streamable HTTP可网页运行
金融68 个工具Nov 1, 2026

Atomadic starter MCP (50 tools)

由 GitHub 账号 atomadictech 发布

Atomadic 托管 MCP 端点，提供 50 个入门工具，涵盖 AI 合规、代理信任、身份、托管与推理，需付费 API 密钥解锁。

Streamable HTTP可网页运行
金融50 个工具Oct 29, 2026