invinoveritas
Anchors signed review proofs to a public Bitcoin-anchored ledger, enabling independent recomputation and verification of verdicts via Bitcoin-backed timestamping and integrity proofs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@invinoveritasreview this code diff before I open the PR"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
invinoveritas — MCP server
An independent review gate for AI agents, as a hosted MCP server. Before your agent takes an
irreversible action — shipping code, running a shell command, signing a transaction — it calls
review for a neutral second opinion from a party that isn't the agent, and gets back a
recomputable, Bitcoin-anchored proof anyone can re-verify without trusting the agent or us.
The one thing an agent can't self-serve is a trustworthy verdict on its own output. This is that verdict — model-agnostic, advisory (it never blocks), and checkable from the bytes.
Hosted, no install. Remote Streamable-HTTP MCP server:
https://api.babyblueviper.com/mcp/verifySign-in: standard MCP OAuth in clients that support it (a free account can be created on the consent screen), or a free API key as a Bearer header:
curl -X POST https://api.babyblueviper.com/register -d '{"label":"mcp"}'verify_proof,ledger, andpayment_receiptare always free / no auth.
Tools
Tool | What it does | Auth |
| Independent verdict ( | Bearer (paid) |
| Recompute and verify a signed invinoveritas proof someone handed you — confirms it without trusting the presenter or us. | free |
| Signed receipt for one verdict-governed payment. | free |
| Anchor a third party's exact claim bytes, unmodified and unjudged — pure notarization (receipt + timestamp + integrity), distinct from | Bearer (paid) |
Also on this endpoint: ledger (free public verdict track record), validate (backtest reality-check), audit_agent_readiness, ledger_submit, conformance_certify. 9 tools in all; the server never moves money or assets for the user.
Related MCP server: Proof Layer MCP
Add it to your agent
Cursor — one-click: Add invinoveritas to Cursor (it signs in with OAuth on the first paid call), or edit ~/.cursor/mcp.json (global) / .cursor/mcp.json (project):
{
"mcpServers": {
"invinoveritas": {
"url": "https://api.babyblueviper.com/mcp/verify",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}Cline — Add via the MCP marketplace, or in cline_mcp_settings.json:
{
"mcpServers": {
"invinoveritas": {
"type": "streamableHttp",
"url": "https://api.babyblueviper.com/mcp/verify",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}Gemini CLI — install as an extension:
gemini extensions install https://github.com/babyblueviper1/invinoveritas-mcpClaude Code:
claude mcp add --transport http invinoveritas https://api.babyblueviper.com/mcp/verify \
--header "Authorization: Bearer YOUR_API_KEY"Devin — Settings → Connections → MCP servers → Add a custom MCP → HTTP (Streamable), URL
https://api.babyblueviper.com/mcp/verify, Auth Header Authorization: Bearer YOUR_API_KEY.
OpenHands — config.toml:
[mcp]
shttp_servers = [{ url = "https://api.babyblueviper.com/mcp/verify", api_key = "YOUR_API_KEY", timeout = 60 }]Any MCP client — point it at https://api.babyblueviper.com/mcp/verify (Streamable HTTP) with header
Authorization: Bearer YOUR_API_KEY. Protocol 2025-06-18; the handshake, tools/list, and
tools/call work out of the box.
Use it
Tell your agent: before opening a PR or running an irreversible command, call review with the
diff/command as artifact, set artifact_type (code_diff / shell_command / onchain_action /
general), and sign: true. On reject, hold and fix; on approve, attach the proof so reviewers
can re-verify it.
Pairing with a fast gate (e.g. Jev)
Fast judgment models such as TypeSafe's Jev (jev_gate in the community
jev-mcp server) screen every tool call in a few hundred
milliseconds and answer allow / confirm / block. They are a good first line. What they don't
give you is an independent verdict someone else can check later. Use both: let the fast gate handle
the routine calls, and escalate only the risky or irreversible ones to invinoveritas.
gate = jev_gate(action=cmd, context=why) # ~0.3 s, every call
if gate.recommendation == "allow" and not gate.touches_prod:
run(cmd) # routine: no second opinion needed
elif gate.recommendation == "block":
stop_and_explain(gate) # clear no
else: # "confirm", or anything touching prod
v = review(artifact=cmd, artifact_type="shell_command", context=why, sign=True)
if v.verdict == "reject": stop_and_explain(v.issues)
else: run(cmd); keep(v.proof) # signed proof anyone can verify_proof laterThe fast gate keeps latency and cost low on the many calls; the signed verdict covers the few that matter, and leaves a record that doesn't depend on trusting either the agent or us.
Why a verdict you can recompute
review with sign: true returns a proof that is a BIP-340-signed Nostr event, published to a
public, Bitcoin-anchored ledger. Verify it offline against our published key — recompute the event
id and check the schnorr signature — or POST it to https://api.babyblueviper.com/verify-proof
(free, no auth). Trust the math, not us. Wins and losses are published; the track record is a
forensic artifact, not a score.
Recompute a proof yourself: zero-dep
pip install invinoveritas-verify/npm i invinoveritas-verifyServer card:
https://api.babyblueviper.com/.well-known/mcp/server-card.json
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Second opinion before an irreversible agent action; signed proofs, free verify, public ledger.
Expert review for AI agents. On-chain proof of human review.
Checks AI agent actions before they run. Signed, RFC 3161 timestamped evidence for audits.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceSecurity layer for AI agents that evaluates transaction intents and returns verdicts (ALLOW/WARN/DENY) using deterministic rules, on-chain checks, and simulation.11 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides cryptographic governance receipts for AI agents, enabling pre-execution evaluation and signed verdicts (EXECUTE/BLOCK/REVIEW/SHADOW) with offline-verifiable audit trails.MIT
- AlicenseNot gradedqualityFmaintenanceEnables verification of AI agent identity, authority, and integrity at transaction time, returning signed verdicts for allow, step-up, review, or block.MIT
- AlicenseAqualityBmaintenanceA self-hosted decision engine that sits between an AI agent and blockchain execution. Agents submit a proposed action, Guardian returns an explainable ALLOW / WARN / BLOCK before anything gets signed or broadcast.268 PyPI1MIT