Atomadic Forge

io.github.atomadictech由 GitHub 账号 atomadictech 发布v0.87.0更新于 Nov 1, 2026

Architecture compiler for AI code. 11 tools, 92 actions, 872 Lean4 proofs, 100/100 self-cert.

发布方自己的服务：Atomadic MCP

已验证Streamable HTTP可网页运行金融安全与监控AI 与机器学习

概览

AI 生成的概览

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。

可以做什么
  • 初始化控制面板，获取安装指引、可运行示例与一键引导
  • 注册智能体、规划目标、分类意图、计算信誉分、查看群体拓扑，并对智能体输出做语义差异与矛盾检测
  • 执行合规检查与证书：GDPR/CCPA 门禁、EU AI Act、可解释性、公平性、透明度、数据血缘、监督记录与事件上报
  • 评估 DeFi 风险：合约审计、跨链桥与预言机验证、清算与风险评分、收益与 LP 参数优化
  • 创建、争议与释放智能体之间的托管资金
  • 验证模型提交、徽章、排行榜与隔离名单，并生成漂移证书、查询熵预言机
适用场景
当你希望助手在一个端点内完成智能体群体协作、生成合规或审计类证书，或评估 DeFi 与模型提交风险时可以考虑。多数用户未必需要全部功能，建议先确认所需的具体工具组是否匹配你的任务。
运行要求
可作为远程端点连接服务商主机，也可从 PyPI 包 atomadic-forge 本地安装并用 forge 命令运行，因此需要 Python 环境。未声明认证、环境变量或请求头；首个工具描述为免费且无需密钥，其他工具可能有各自的使用条件。
安装前请注意
托管类工具会创建、争议并释放资金，DeFi 工具涉及真实金融头寸，可能牵涉实际资金。合规、公平性、审计与验证结果是该服务出具的证书，并非独立的法务或安全保证。未声明认证机制，使用前应确认访问与付费层级实际如何限制。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Atomadic Forge，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/io.github.atomadictech%2Fatomadic-forge/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-forge": {
      "type": "http",
      "url": "https://forge.atomadic.tech/mcp"
    }
  }
}

README

该仓库没有 README。

工具

68

murmuration

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 Contradiction

[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.

输入参数statements必填

agents_intent_classify

Agents Intent Classify

[agents] Agent intent classification

输入参数text必填

agents_plan

Agents Plan

[agents] Autonomous agent goal planning

输入参数goal必填constraints

agents_register

Agents Register

[agents] Register an agent

输入参数agent_id必填capabilities必填

agents_reputation

Agents Reputation

[agents] Agent reputation and trust score

输入参数agent_id必填

agents_semantic_diff

Agents Semantic Diff

[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.

输入参数contextoutput_a必填output_b必填

agents_topology

Agents Topology

[agents] Live swarm topology

无需输入参数。

compliance_check

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

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

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

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

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

Compliance Incidents

[security] Incident registry

输入参数system_id必填

compliance_lineage

Compliance Lineage

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

输入参数model_id必填dataset_stages必填

compliance_oversight

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

Compliance Oversight History

[security] Oversight history

输入参数system_id必填

compliance_transparency

Compliance Transparency

[security] Transparency report

输入参数period必填include必填system_id必填

defi_bridge_verify

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 Audit

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

输入参数contract_id必填contract_type必填

defi_liquidation_check

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 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 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 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 Optimize

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

输入参数principal_usd必填risk_tolerance必填

drift_certificate

Drift Certificate

[trust] Drift certificate

输入参数id必填

drift_check

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

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

Escrow Dispute

[defi] Open escrow dispute

输入参数reason必填evidenceescrow_id必填

escrow_release

Escrow Release

[defi] Release escrowed funds

输入参数escrow_id必填

forge_badge

Forge Badge

[fuse] Model quality badge

输入参数model必填

forge_delta_submit

Forge Delta Submit

[fuse] Submit a model delta

输入参数delta必填model_id必填description

forge_leaderboard

Forge Leaderboard

[fuse] Model leaderboard

无需输入参数。

forge_quarantine

Forge Quarantine

[fuse] Quarantined models

无需输入参数。

forge_verify

Forge Verify

[fuse] Verify a model submission

输入参数model_id必填verification_type

identity_sybil_check

Identity Sybil Check

[identity] Sybil-resistance check

无需输入参数。

identity_verify

Identity Verify

[identity] Topological identity verification

输入参数agent_id必填

inference

Inference

[inference] Chat inference with hallucination guard

输入参数messages必填

inference_stream

Inference Stream

[inference] Streaming inference with chain-of-thought

输入参数messages必填

oracle_entropy

Oracle Entropy

[trust] Entropy epoch oracle

无需输入参数。

oracle_hallucination

Oracle Hallucination

[trust] Hallucination oracle

输入参数claim必填context

rag_augment

Rag Augment

[inference] Trusted RAG augmentation

无需输入参数。

ratchet_advance

Ratchet Advance

[identity] RatchetGate — advance session

输入参数session_id必填

ratchet_probe

Ratchet Probe

[identity] RatchetGate — health probe

无需输入参数。

ratchet_register

Ratchet Register

[identity] RatchetGate — register session

输入参数session_id必填

reputation_record

Reputation Record

[agents] Record agent interaction

输入参数outcome必填agent_id必填counterparty_idinteraction_type必填

rng_quantum

Rng Quantum

[inference] Quantum random number with proof

无需输入参数。

rng_verify

Rng Verify

[inference] Verify current epoch random value

无需输入参数。

security_zero_day

Security Zero Day

[security] Zero-day threat assessment

输入参数target必填context

sla_register

Sla Register

[agents] Register an SLA

输入参数terms必填consumer_id必填provider_id必填

sla_report

Sla Report

[agents] Report SLA violation

输入参数sla_id必填descriptionviolation_type必填

swarm_inbox

Swarm Inbox

[agents] Poll swarm inbox

无需输入参数。

swarm_relay

Swarm Relay

[agents] Relay message through swarm

输入参数ttlmessage必填target_agent_id必填

text_keywords

Text Keywords

[inference] Keyword extraction

输入参数text必填max_keywords

text_sentiment

Text Sentiment

[inference] Sentiment analysis

输入参数text必填

text_summarize

Text Summarize

[inference] Text summarization

输入参数text必填

threat_score

Threat Score

[security] Multi-vector threat score

输入参数contextagent_id必填

trust_decay

Trust Decay

[trust] Current trust ceiling value

无需输入参数。

trust_history

Trust History

[trust] Trust score history

输入参数agent_id必填

trust_score

Trust Score

[trust] Bounded trust score

输入参数agent_id必填

audit_work_claim

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

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

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

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. Use agents_contradiction instead when comparing free-text agent prose. 3 free calls/day, then entitlement 'ledger'.

输入参数claims必填

enforce_sla

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

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

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

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. v0.87.0最新Sep 16, 2026

评分

已满足适用检查项的 75%

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10 分

    请在仓库或注册中心条目中声明许可证。

其他 Atomadic 集成

Atomadic MCP

tech.atomadic官方发布者

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

Streamable HTTP可网页运行
安全与监控68 个工具Oct 24, 2026

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 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