AIBITIOUS 404 LAB - 32 Free Agent Experiments

io.github.aibitious由 GitHub 账号 aibitious 发布v0.3.0更新于 Nov 12, 2026

32 free tools: CVE/data checks and offline agent decisions on permissions, budgets and recovery.

发布方自己的服务:Silent Door Repository Handoff Planner

已验证Streamable HTTP可网页运行云端与基础设施开发者工具安全与监控

概览

AI 生成的概览

一套免费、限速的远程工具集,提供 32 个离线校验与预检工具,用于智能体决策、数据检查和 CVE 查询。

可以做什么
  • 通过 NIST NVD 记录解析 CVE 编号,并上报缺失的公开数据主题
  • 按安全子集校验 JSON、比较 JSON 结构、检查 OpenAPI 契约与 MCP 服务器元数据,并评估提供的 HTTP 响应头或 robots.txt
  • 检测疑似密钥模式、检查 CSV 数据质量、复核发票算术并核对声明引用
  • 对智能体策略规则、权限范围变更、审批材料、预算、重试计划、重复操作、证据前置条件与时效做试运行检查
  • 规划工作流补偿、分诊 webhook 投递、预测队列、测算 SLO 燃尽率,并检查发布门禁、清单漂移与回执链
  • 在令牌上限内挑选上下文片段,并生成有界的边界用例
适用场景
适合在智能体执行动作前做快速、建议性的预检:校验数据结构或 API 契约、发现疑似密钥或过期证据、核对预算与权限,或查询某个 CVE。所有检查均为离线且仅供参考,适合规划与复核,而非强制执行。
运行要求
需要一个远程 streamable HTTP 端点;未声明任何软件包、账户、API 密钥或环境变量。多数工具处理你提供的数据,CVE 查询依赖 NIST NVD 记录,公开服务被描述为免费且限速。
安装前请注意
结果仅供参考,并非官方验证、法律或税务意见,也不构成事实核查。不要向公开演示提交密钥、个人数据或真实凭据;密钥检测仅用于模式检查。README 还介绍了另一套实验性支付协议,其合约未经审计并处理真实 USDC,与本工具集无关。

安装

在 SourceWeft 中

  1. 打开 控制台中的 AIBITIOUS 404 LAB - 32 Free Agent Experiments,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.aibitious%2Fagent404/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": {
    "aibitious-404-lab-32-free-agent-experime": {
      "type": "http",
      "url": "https://aibitious.com/404/mcp/"
    }
  }
}

README

🤖 AI Micropayment Network (AiMPN)

Looking for the free AIBITIOUS 404 LAB MCP server?
Launch the tool directory · Try live synthetic demos · MCP endpoint · REST/OpenAPI · LAB source and safety notes.

These are separate experiments in one repository. AIBITIOUS 404 LAB is a public, free, rate-limited suite of ten verification/preflight tools. It requires no wallet, cryptocurrency, account, or payment, and is not backed by the payment smart contracts discussed below. Neither the LAB tools nor the contracts are independently certified. Do not submit secrets or personal data to the public demo. Registration in an MCP directory is not evidence of user adoption.


AiMPN is an experimental open-source protocol for Zero-Gas Machine-to-Machine (M2M) payments on Base L2.

[Base Mainnet] [ERC-4337 Account Abstraction] [Slither Analysis] [License: MIT]

🚨 SECURITY NOTICE: AiMPN is in early-stage Alpha. The smart contracts handle real USDC on Base Mainnet but have NOT been independently audited. This is an experimental proof-of-concept. Please read our SECURITY.md and do not use with significant funds.

🌟 What is AiMPN?

AiMPN allows AI Agents (like ElizaOS, LangChain, AutoGen) to purchase APIs, data, and compute resources from other machines using USDC. Unlike traditional wallets, AiMPN uses ERC-4337 Paymasters to sponsor 100% of the gas fees, meaning AI Agents never need to hold ETH to transact.

Our architecture is deeply inspired by and designed to be an implementation library compatible with standard x402 paradigms (e.g., Linux Foundation / Coinbase x402 initiatives).

📊 Verifiable On-Chain Data (Base Mainnet)

We believe in radical transparency. AiMPN is live on Base Mainnet. You can verify our deployed infrastructure directly on BaseScan:

Example Zero-Gas Settlement Hash: 0x3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b1c2d3e4f5a6b7c8d9e0f1a2b3c4d (Demo reference)

🛡️ Core Concept: The AI Circuit Breaker

Since AI agents operate autonomously, they pose a severe financial risk if they hallucinate or get stuck in a spending loop. AiMPN mitigates this through hardcoded EVM Circuit Breakers:

  • Daily Spend Limits: Agents are mathematically capped at a specific USDC spend per day.
  • Atomic Escrows: Funds are locked in escrow and only released when the API delivers the data (Proof-of-Delivery). If the API times out, the USDC is refunded automatically.

Read our deep-dive technical architecture here: AI Circuit Breaker Architecture.

🚀 Quickstart

Integrating AiMPN into your agent framework takes just 5 lines of code. Check out the QUICKSTART.md guide.

🤝 Contributing & Bug Bounty

We are actively looking for contributors, integrations (ElizaOS, Fetch.ai), and security researchers. Please refer to our SECURITY.md for details on our Bug Bounty program.

来源:README.md,提交 4364e16

工具

33

resolve_public_fact

Resolve one CVE identifier (e.g. CVE-2024-3094) using NIST NVD records. This tool does not execute code, scan targets, or accept arbitrary URLs.

输入参数identifier必填

report_missing_information

Opt-in report of a PUBLIC missing-data topic, never include private data or secrets.

输入参数topic必填consent_to_aggregate

json_schema_guard

Validate one JSON object against a SAFE subset of JSON Schema. No remote refs. Offline.

输入参数schema必填document必填

csv_data_doctor

Find missing fields, ragged CSV rows and duplicate key values; no raw rows are stored.

输入参数csv_text必填delimiterkey_columns

invoice_math_audit

Independently recalculate invoice arithmetic, NOT legal/tax compliance. Synthetic data only.

输入参数lines必填currencydeclared_netdeclared_taxdeclared_gross

secret_pattern_shield

Detect probable token patterns without returning or storing secret values. Never send real secrets.

输入参数text必填

openapi_contract_preflight

Static OpenAPI 3.x lint: missing operation IDs, responses and malformed operations. Offline.

输入参数spec必填

mcp_registry_preflight

Check a candidate MCP server.json metadata structure; this is NOT official validation.

输入参数server必填

http_headers_audit

Assess supplied HTTP security response headers. No network or live website probe.

输入参数headers必填

robots_policy_check

Evaluate supplied robots.txt for one agent/path. Not a legal scraping permission.

输入参数pathagentrobots_txt必填

json_shape_diff

Compare JSON object shapes for added, deleted or changed field types. Offline.

输入参数after必填before必填

simulate_agent_action_policy

Dry-run one proposed tool action against explicit allow/deny/approval rules; no enforcement.

输入参数rules必填action必填

plan_workflow_recovery

Plan reverse-order compensations for a supplied workflow DAG; never execute actions.

输入参数steps必填

triage_webhook_deliveries

Find duplicate, failed and rate-limited deliveries from supplied HTTP status metadata.

输入参数attempts必填

check_claim_provenance

Check whether supplied claim references reach at least one declared source; not fact checking.

输入参数claims必填sources必填

minimize_agent_data

Check declared fields, retention and model transfer against a supplied local policy.

输入参数fields必填allowed_fields必填max_retention_days必填

scope_delta

Permission Scope Delta

Find newly granted permissions outside an approved set. Offline check. Supply payload like {"before":["read"],"after":["read","send"],"approved_additions":[]}. Advisory result only.

输入参数payload必填

approval_packet

Approval Packet Check

Find missing or expired fields before seeking human approval. Offline check. Supply payload like {"now_unix":100,"action":{"actor":"agent","tool":"mail.send","target":"draft1","effect":"send","reason":"owner_request","expiry_unix":200}}. Advisory result only.

输入参数payload必填

budget_envelope

Budget Envelope

Check worst-case proposed cost against a local hard budget. Offline check. Supply payload like {"limit_usd":"0","spent_usd":"0","reserved_usd":"0","proposed_worst_case_usd":"0"}. Advisory result only.

输入参数payload必填

retry_schedule

Retry Schedule

Preview capped exponential retries against a deadline. Offline check. Supply payload like {"attempts":3,"first_delay_seconds":2,"max_delay_seconds":10,"deadline_seconds":30}. Advisory result only.

输入参数payload必填

duplicate_actions

Idempotency Audit

Find duplicate attempts and conflicting key reuse. Offline check. Supply payload like {"calls":[{"idempotency_key":"k1","payload_fingerprint":"hash1"},{"idempotency_key":"k1","payload_fingerprint":"hash1"}]}. Advisory result only.

输入参数payload必填

prerequisite_gate

Prerequisite Gate

Check whether all declared evidence prerequisites are present. Offline check. Supply payload like {"requirements":[{"id":"deploy","evidence_refs":["ci"]}],"available_evidence":["ci"]}. Advisory result only.

输入参数payload必填

evidence_expiry

Evidence Freshness

Flag stale observations before an agent acts. Offline check. Supply payload like {"now_unix":200,"records":[{"id":"health","observed_unix":100,"ttl_seconds":120}]}. Advisory result only.

输入参数payload必填

citation_matrix

Citation Matrix

Find claims with missing or unknown citation identifiers. Offline check. Supply payload like {"claims":[{"id":"claim1","citation_refs":["src1"]}],"citations":["src1"]}. Advisory result only.

输入参数payload必填

schema_impact

Consumer Schema Impact

Identify downstream consumers broken by changed fields. Offline check. Supply payload like {"before":{"id":1},"after":{},"consumers":[{"id":"client","required_fields":["id"]}]}. Advisory result only.

输入参数payload必填

boundary_cases

Boundary Case Builder

Generate bounded edge cases from simple field constraints. Offline check. Supply payload like {"fields":[{"name":"count","type":"integer","minimum":0,"maximum":10}]}. Advisory result only.

输入参数payload必填

slo_burn

SLO Burn Check

Measure error-budget burn against a supplied target. Offline check. Supply payload like {"target_percent":"99","total":1000,"bad":20,"alert_burn_rate":2}. Advisory result only.

输入参数payload必填

queue_forecast

Queue Capacity Forecast

Project backlog and drain time from supplied rates. Offline check. Supply payload like {"backlog":100,"incoming_per_hour":10,"capacity_per_hour":20,"horizon_hours":4}. Advisory result only.

输入参数payload必填

permission_paths

Permission Path Explorer

Find sensitive targets reachable through declared capability edges. Offline check. Supply payload like {"start":"agent","edges":[{"from":"agent","to":"secret"}],"sensitive_targets":["secret"]}. Advisory result only.

输入参数payload必填

context_budget

Context Budget Packer

Select prioritized context chunks inside a token limit. Offline check. Supply payload like {"max_tokens":100,"chunks":[{"id":"source1","tokens":40,"priority":10}]}. Advisory result only.

输入参数payload必填

release_gate

Release Gate Check

Require named checks to be green before a release. Offline check. Supply payload like {"required":["test"],"checks":[{"id":"test","status":"success"}]}. Advisory result only.

输入参数payload必填

manifest_drift

Manifest Drift

Compare expected and observed resource manifests. Offline check. Supply payload like {"expected":{"version":"1"},"observed":{"version":"2"}}. Advisory result only.

输入参数payload必填

receipt_chain

Receipt Chain Check

Check links in a supplied digest receipt chain. Offline check. Supply payload like {"root_sha256":"0000000000000000000000000000000000000000000000000000000000000000","receipts":[{"previous_sha256":"0000000000000000000000000000000000000000000000000000000000000000","sha256":"1111111111111111111111111111111111111111111111111111111111111111"}]}. Advisory result only.

输入参数payload必填

版本历史

2
  1. v0.3.0最新Nov 12, 2026
  2. v0.2.0Nov 11, 2026

评分

已满足适用检查项的 90%

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
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。

其他 Aibitious 集成