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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.