hive-mcp-sigr
Enables AI agents to sign and verify actions with ML-DSA-65 digital signatures, providing tamper-proof receipts that can be verified offline without any secrets.
README
hive-mcp-sigr — Signed inference Guarantee Receipt (SiGR™)
A remote MCP server that signs the things AI agents do — runs, billing, SLA bonds, and model-panel verdicts — with ML-DSA-65 (NIST FIPS 204). Every receipt is returned as a self-contained envelope you can verify offline, with no secret and no callback to us.
Most of what an AI agent does today is unsigned. When a run goes wrong, reconstruction takes weeks because nobody has the exact, ordered state the model saw before it acted. SiGR signs that state at the moment of the call. The receipt is the record.
Patent Pending. Hive Civilization.
- Remote endpoint:
https://hive-mcp-sigr.onrender.com/mcp - Transport: Streamable-HTTP, JSON-RPC 2.0, MCP
2024-11-05 - Upstream signer:
https://hive-typed-signer.onrender.com - Signature scheme: ML-DSA-65 (NIST FIPS 204), ~7 ms per signature
- Pricing: Build tier (first 1M receipts) free. Verify is always free. Full ladder at thehiveryiq.com/sigr/
Tools
| Tool | What it signs | Docket | Required input |
|---|---|---|---|
sign_chain |
A multi-step agent run, each step sealed to its causal parents with a causal_root (flagship) |
HC-2026-006 | run |
sign_bill |
An inference cost / billing receipt (tokens, backend, prices) | HC-2026-004 | request |
sign_bond |
An SLA performance bond (latency ceiling, uptime floor, penalty) | HC-2026-005 | terms |
sign_consensus |
A model-panel verdict (member digests, scores, method) | HC-2026-007 | panel, method, members |
verify_receipt |
Verifies any SiGR envelope offline (always free) | — | product, envelope |
get_pubkey |
Returns the ML-DSA-65 public key + issuer metadata | — | — |
Each sign tool returns the full signed envelope (ok, product, patent_pending, envelope, timing_us). The envelope carries the public_key, payload_digest, and envelope_signature needed to verify it later with verify_receipt or directly against the signer.
Endpoints (upstream signer)
| Endpoint | Method | Purpose |
|---|---|---|
/sigr/chain |
POST | Sign an agent run |
/sigr/bill |
POST | Sign a billing receipt |
/sigr/bond |
POST | Sign an SLA bond |
/sigr/consensus |
POST | Sign a panel verdict |
/sigr/{product}/verify |
POST | Verify an envelope (free) |
/pubkey |
GET | ML-DSA-65 public key |
Connect
Claude Desktop / MCP client (remote)
{
"mcpServers": {
"hive-sigr": {
"type": "streamable-http",
"url": "https://hive-mcp-sigr.onrender.com/mcp"
}
}
}
List tools
curl -s -X POST https://hive-mcp-sigr.onrender.com/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Call sign_chain (flagship)
curl -s -X POST https://hive-mcp-sigr.onrender.com/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"sign_chain","arguments":{"run":{"run_id":"run-1","agent_ref":"research-agent-v2","steps":[{"step_id":"s1","kind":"plan","seq":0,"parents":[],"input":{"goal":"compare"},"output":{"plan":["a","b"]}},{"step_id":"s2","kind":"final","seq":1,"parents":["s1"],"input":{"r":"A"},"output":{"answer":"done"}}]}}}}'
Verify a receipt (free)
curl -s -X POST https://hive-mcp-sigr.onrender.com/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"verify_receipt","arguments":{"product":"chain","envelope":{ /* paste the envelope from sign_chain */ }}}}'
Run it yourself
npm install
node server.js
# -> [hive-mcp-sigr] v1.0.0 listening on :3000 -> https://hive-typed-signer.onrender.com
Environment:
| Var | Default | Notes |
|---|---|---|
PORT |
3000 |
HTTP port |
ENABLE |
true |
Set false to run health-only |
HIVE_SIGNER_URL |
https://hive-typed-signer.onrender.com |
Upstream signer base |
Policy
Inbound only. Never takes custody of keys or funds. Signing only — your payload is signed and returned; we do not store it.
Settlement for paid tiers is USDC on Base. Verify is always free.
MIT © 2026 Steve Rotzin / Hive Civilization · thehiveryiq.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。