tctc-mcp
Exposes ERC-7303 token-controlled roles to AI agents, enabling permission checks and on-chain role management via control tokens.
README
tctc-mcp
An MCP server exposing ERC-7303 (Token-Controlled Token Circulation) roles to AI agents: agents check their own on-chain permissions, and human principals grant/revoke them by minting/burning control tokens — no permission server required.
Status: v1 implemented — unit-tested and verified end-to-end against the Sepolia demo deployment (grant → check → revoke → check through a real MCP client).
Quick start
npm install && npm run build
# read-only mode (agent side): only query tools are registered
ALCHEMY_API_KEY=... node dist/index.js --config examples/config.sepolia.json
# admin mode (principal side): grant_role / revoke_role also registered
ALCHEMY_API_KEY=... TCTC_ADMIN_PRIVATE_KEY=0x... \
node dist/index.js --config examples/config.sepolia.json
MCP client registration: see
examples/claude.mcp.json. The admin private
key is only ever read from the TCTC_ADMIN_PRIVATE_KEY environment
variable; configs containing anything that looks like a private key are
rejected at startup.
Tools
| Tool | Mode | Purpose |
|---|---|---|
list_roles |
both | Configured roles and their control tokens |
check_role |
both | Does an account hold a role? (live balanceOf, with evidence) |
check_all_roles |
both | Session-start self-assessment across all roles |
resolve_agent |
both* | ERC-8004 agentId → owner / agentURI / agentWallet / ERC-6551 TBA |
grant_role |
admin | Mint the control token to a subject |
revoke_role |
admin | Burn the subject's control token — the kill switch |
* registered only when the config has an identity section.
Subjects can be given as a raw address, as an ERC-8004 agentId
(resolved to its ERC-6551 Token Bound Account, the recommended binding
target), or omitted to use the config's self.
Documents
- docs/CONCEPT.md — background and rationale: TCTC as the authorization layer for AI agents, its relationship to ERC-8004 (Trustless Agents) and ERC-6551 (Token Bound Accounts), recommended ERC-7303 spec updates, and the adoption strategy.
- docs/MCP_SERVER_SPEC.md — v1 design specification (architecture, config, tools, security, roadmap).
- docs/TEST_REPORT.md — v1 test report: 24 unit tests and the live Sepolia E2E (on-chain kill-switch cycle through a real MCP client).
- examples/config.sepolia.json —
concrete config for the Sepolia demo deployment (primary roles) and
the original TCTC reference deployment (
COMPLEX_*roles). - examples/contracts/ — sources of the demo
contracts deployed on Sepolia (
AgentControlTokens,TCTCDemoToken,ERC7303).
Demo deployment (Sepolia, Etherscan-verified)
AgentControlTokens(soulbound, issuer-burnable ERC-1155):0x12342A7F0190B3AF3F4b47546D34006EDA54eE0BTCTCDemoToken(ERC-721 + ERC-7303 target):0xa52fe39D0de852e88488faa34e723E861D0b09BD
Development
npm test # unit tests (vitest)
node scripts/e2e-live.mjs # live E2E: spawns the server via MCP stdio client
# (needs ALCHEMY_API_KEY; admin phase additionally
# TCTC_ADMIN_PRIVATE_KEY and E2E_SUBJECT)
Related
- TCTC reference implementation: https://github.com/kofujimura/TCTC
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。