cc0company MCP

cc0company MCP

Enables AI agents to query the largest CC0 database for provenance, license verification, and market data, and generate CC0 images, all via pay-per-call x402 micropayments.

Category
访问服务器

README

cc0company MCP

The largest machine-readable CC0 database (cc0pedia) + the whole cc0.company agent-services catalog, as a remote Model Context Protocol server. Pay-per-call over x402 (USDC on Base).

Endpoint: https://cc0.company/api/mcp — Streamable HTTP, JSON-RPC 2.0.


What it is

A remote MCP server that turns cc0.company's managed agent services into tools any AI agent can call:

  • cc0pedia read API — look up / search / verify / price any CC0 creator, NFT collection, token or work. Provenance, license, on-chain pointers (contracts, chains, OpenSea slugs) and live market data over the largest structured CC0 database.
  • CC0 image generation — fine-tuned models whose output is public domain.
  • Market data — a daily digest of the top CC0 NFT collections.
  • Third-party agents — re-brokered over x402 (e.g. mfergpt).

Tools are discovered live from the catalog (tools/list), so the set grows over time without changing your client.

Why agents pay

cc0pedia is a public good; serving it to autonomous agents at scale is not. Every tool call is a tiny x402 micropayment — the agentic economy in one request: an agent verifies a CC0 license, pulls provenance + market data, and pays for exactly what it used, with no account and no API key.

Connect

Claude Code

claude mcp add --transport http cc0pedia https://cc0.company/api/mcp

Cursor.cursor/mcp.json

{ "mcpServers": { "cc0pedia": { "url": "https://cc0.company/api/mcp" } } }

Claude Desktop / claude.ai — Settings → Connectors → Add custom connectorhttps://cc0.company/api/mcp

Any MCP client — Streamable HTTP transport, the URL above. No auth to connect.

Payment — x402

Every tools/call is a paid x402 request. Free: initialize, tools/list, ping.

Protocol x402 v2
Network Base mainnet — eip155:8453
Asset USDC — 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
Scheme exact (fixed price per call)
Facilitator Coinbase CDP

Flow: the first call returns HTTP 402 with the challenge in the PAYMENT-REQUIRED header. Your x402 client signs an EIP-3009 USDC authorization and retries with the PAYMENT-SIGNATURE header; the facilitator verifies + settles and the tool runs. Use an x402-enabled client (wrap your MCP transport's fetch with x402). Pay only for what you use: a call that resolves nothing returns a 4xx and the charge is cancelled — you are never billed for an empty answer.

See examples/ for a working free-discovery script and an end-to-end paid call.

Tools

Discovered dynamically — tools/list is the source of truth. At launch:

Tool Price What it does
cc0pedia $0.01 Resolve one CC0 creator/collection/work by name or slug → provenance, license, on-chain pointers, full CC0 body
cc0pedia-search $0.01 Ranked free-text search across the CC0 database
cc0pedia-verify $0.01 License oracle — is a contract a documented CC0 work? + full provenance
cc0pedia-market $0.01 Live market for a CC0 asset — token price/FDV/liquidity/volume, or NFT floor/volume/owners
cc0-daily-brief $0.05 Hourly digest of the top CC0 NFT collections by 24h volume
sartoshi-gen · darkfarms-gen · hokusai-gen · van-gogh-gen · monet-gen $0.069 CC0 image generation (async — returns a job_id to poll)
mfergpt-ask · mfergpt-lore · mfergpt-mferfy varies Third-party mfergpt services, re-brokered over x402

Quick check (free)

curl -s https://cc0.company/api/mcp \
  -X POST -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' \
  | jq '.result.tools[].name'

Data license

cc0pedia content is dedicated to the public domain (CC0-1.0) — reuse, repost, remix without attribution. This repository is CC0 too.

Links

  • Site — https://cc0.company
  • Encyclopedia — https://cc0.company/cc0pedia
  • Agent docs — https://cc0.company/agents?tab=docs

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选