io.github.daedalusdevelopmentgroup/ddg-agent-services-mcp
Enables AI agents to access DDG's payable services including checkout/payment conformance, MCP/tool security audits, agent-discovery repair, and buyer-agent smoke probes, with structured payment challenges.
README
<!-- mcp-name: io.github.daedalusdevelopmentgroup/ddg-agent-services-mcp -->
DDG Agent-Payable Services
AI-agent-native services from Daedalus Development Group (DDG): checkout/payment conformance, MCP/tool security audits, agent-discovery repair, buyer-agent smoke probes, browser proof, repo context packs, and bounded DDG-operated model/artifact orders.
Production base URL:
https://agents.daedalusdevelopmentgroup.com
Current live payment rails
x402
direct_crypto_auto
MPP / Stripe / Tempo is installed but not advertised live yet. DDG will advertise MPP only after the verifier reports ready, the public 402 challenge includes MPP, a real penny-scale settlement succeeds, idempotency replay passes, and invalid-token failure is verified.
Start here if you are a buyer agent
- Fetch AI discovery:
curl -fsS https://agents.daedalusdevelopmentgroup.com/.well-known/ai | python3 -m json.tool
- Fetch status:
curl -fsS https://agents.daedalusdevelopmentgroup.com/.well-known/ddg-agent-status.json | python3 -m json.tool
- Fetch pricing/catalog:
curl -fsS https://agents.daedalusdevelopmentgroup.com/.well-known/ddg-agent-pricing.json | python3 -m json.tool
curl -fsS https://agents.daedalusdevelopmentgroup.com/.well-known/agent-catalog.json | python3 -m json.tool
- Verify checkout conformance:
curl -fsS https://agents.daedalusdevelopmentgroup.com/.well-known/ddg-agent-checkout-conformance.json | python3 -m json.tool
- Probe the payment gate without spending:
curl -i -X POST https://agents.daedalusdevelopmentgroup.com/v1/tx-smoke-test \
-H 'Content-Type: application/json' \
-H 'X-Agent-Id: your-agent-id' \
-d '{"service":"tx_penny_smoke_test"}'
Expected without payment: 402 payment_required with accepted protocols.
Important endpoints
See also DISCOVERY.md for the agent-radar/distribution map and directory readiness notes.
| Endpoint | Purpose |
|---|---|
/.well-known/ai |
AI-agent discovery surface |
/.well-known/ddg-agent-status.json |
Rail/service/MCP status |
/.well-known/api-catalog |
Linkset API catalog |
/openapi.json |
OpenAPI contract |
/llms.txt |
LLM-facing instructions |
/.well-known/ddg-agent-pricing.json |
Machine-readable pricing |
/.well-known/agent-catalog.json |
Agent service catalog |
/.well-known/agent-skills/index.json |
Agent-skill discovery index |
/.well-known/ddg-agent-checkout-conformance.json |
Checkout conformance profile |
/.well-known/ddg-agent-refund-policy.json |
Strict refund/reversal policy for agent-paid work |
/.well-known/ddg-agent-swarm-mcp-design.md |
MCP design/status doc |
Flagship services
agent_payment_readiness_auditmcp_tool_security_auditagent_service_distribution_packagent_marketplace_listing_packagent_readiness_scorecardbuyer_agent_smoke_probebrowser_proofrepo_context_packai_skill_safety_scanmodel_agent_run
MCP
The local stdio MCP server is in mcp/. It exposes free discovery/status/conformance tools, allowlisted ddg:// resources for public manifests/docs/OpenAPI, agent-radar/x402 Bazaar readiness metadata, and payment-aware paid-service helpers. Paid tools return structured 402 payment_required challenges instead of opaque MCP errors.
Current MCP status: stdio package/source is locally smoke-tested; Streamable HTTP source is locally smoke-tested; public hosted MCP endpoint is planned but not live. See docs/mcp-production-readiness.md.
Security and compliance stance
DDG sells bounded artifacts/results, not raw model-provider account access. DDG never sells, returns, or relays:
- raw OAuth tokens
- provider API keys
- private account/session state
- raw provider seats
- private model IDs when they would reveal account mechanics
- raw payment tokens or verifier sidecar URLs
Provider-backed model capacity is packaged as DDG-operated artifact/result delivery with spend caps, output schemas, redaction, receipts, and operator review where needed.
Repository contents
openapi.json Public OpenAPI contract copy
docs/pricing.json Pricing copy
docs/agent-catalog.json Catalog copy
docs/agent-status.json Status copy
docs/checkout-conformance.json Checkout profile copy
docs/agent-skills/ Agent skill JSON files
mcp/ Local stdio MCP server and metadata
scripts/agent_checkout_conformance_probe.py Probe script
examples/ Curl and Python buyer-agent examples
schemas/ Public JSON schema drafts
Contact
Operator contact: 0xcircuitbreaker@protonmail.com
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。