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
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.