MCP server

sebbi.pro - the proof layer for AI Official

pro.sebbi/governance

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Score, seal and prove AI decisions in Bitcoin, plus 755 compliance checks, free to verify.

Website

At a glance

Type

MCP server

Publisher

sebbi.pro (verified by the MCP Registry)

Status

Working at last check

Tools

47

Token cost

About 6,962 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http governance https://sebbi.pro/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.governance]
url = "https://sebbi.pro/mcp"

Gemini CLI

{"mcpServers":{"governance":{"httpUrl":"https://sebbi.pro/mcp"}}}

Cursor

{"mcpServers":{"governance":{"url":"https://sebbi.pro/mcp"}}}

VS Code

{"servers":{"governance":{"type":"http","url":"https://sebbi.pro/mcp"}}}

Antigravity

agy mcp add governance https://sebbi.pro/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"governance","server_url":"https://sebbi.pro/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"governance","server_url":"https://sebbi.pro/mcp"}

Tools

• sebbi_accessibility_scan ~88 tokens
  Fetches a live public web page and scans it for common accessibility failures (European Accessibility Act, WCAG), with a score, the issues found and a sealed record.
• sebbi_ai_act ~97 tokens
  Returns any of the 113 EU AI Act articles in plain English (title, who it applies to, when it applies, summary, page), or searches them by words. Read-only.
• sebbi_answer_receipt ~272 tokens
  Seals exactly what you (the AI) just told the person - your answer, their question, your name and the time - into the sebbi.pro chain, timestamped into Bitcoin, and returns a receipt link for them to keep (https://sebbi.pro/said/AR-XXXX-XXXX). Use it when the person asks for proof of what you said,
• sebbi_answer_receipt_check ~76 tokens
  Looks up an AI Receipt (AR-XXXX-XXXX): what the AI said, what it was asked, which AI and when it was sealed. Read-only.
• sebbi_billing_link ~99 tokens
  Returns a secure Stripe link where the person adds a card for the 50p per device per month subscription. Nothing is charged until they complete it.
• sebbi_check_human_proof ~84 tokens
  Looks up a Human Keys code (HK-XXXX-XXXX): whether a person typed the text live, and when. Use it to tell human-written from AI-written. Read-only.
• sebbi_check_pack ~72 tokens
  Checks a Signal Pack with the engine's own validator without publishing it, and explains any problem. Read-only.
• sebbi_check_source ~166 tokens
  Garbage-in guard. Checks whether a piece of data is really vouched for by the domain it claims to come from (a sebbi Verified Source). Returns GENUINE, UNVERIFIED or UNKNOWN, sealed into Bitcoin. Call it before trusting an input.
• sebbi_court_pack ~146 tokens
  Produces a printable Court Pack for a sebbi fact (any record code, chain block number or notarised SHA-256): the fact, the sealed record, the step-by-step proof to Bitcoin, a method statement, and draft declarations for England and Wales (witness statement), US Federal Rules of Evidence 902(13)/902(
• sebbi_create_account Changes accounts · ~240 tokens
  Opens a sebbi.pro account and returns the API key. Only call after showing sebbi_terms and the person agreeing; pass the terms_version they agreed to and customer_agreed=true. The agreement is sealed into the chain. Free for 90 days.
• sebbi_decision_report ~124 tokens
  The machine-proof report for one decision their key sealed: what was decided, who sent it, where it came from, and the proof it has not changed since. Hand it straight to an auditor or regulator. Needs their API key and the block number. Read-only.
• sebbi_energy_record ~176 tokens
  Seals a record of the energy an AI system used over a period (kWh, source, requests served, renewable share), with a printable page for ESG, insurers and the EU AI Act's energy reporting.
• sebbi_examine ~154 tokens
  Examine any public web page: sebbi.pro fetches it live, seals exactly what it said into Bitcoin (a Web Affidavit), checks it against 22 legal and security signals (AI disclosure, cookie consent, accessibility, green claims, pressure selling, prices, trader identity, security headers, llms.txt/ai.txt
• sebbi_explain_check ~96 tokens
  Explains one compliance check by id (e.g. sebbi_euaiact_014): the control, the law and its official text, which field it reads, the rule, exactly how to pass it, and its public page. Read-only.
• sebbi_fact ~200 tokens
  Looks up a sebbi fact: a record anyone can prove for themselves against Bitcoin. Give any sebbi.pro record code (SC-, RD-, IR-, ER-, WA-, DR-, OK-, IC-, NT-, HK-), a chain block number or a SHA-256 fingerprint. Returns the plain-English statement, what is proven, whether it is in Bitcoin yet, the fa
• sebbi_find_checks ~261 tokens
  Searches sebbi.pro's 755 compliance checks across 32 frameworks (EU AI Act, GDPR, DORA, ISO/IEC 42001 and 27001, NIST AI RMF, UK Online Safety Act, EU DSA, SOC 2, PCI DSS, HIPAA, CCPA, NIS2, Cyber Resilience Act, ICO Children's Code, US state AI laws, model risk, and agent-output gates). Filter by f
• sebbi_forever_proof ~101 tokens
  A self-contained proof anyone can check against Bitcoin without sebbi.pro, for a notary receipt, a Human Keys code or any chain block. Give a code or a block number. Read-only.
• sebbi_gateway_setup ~150 tokens
  Returns a private gateway address for their API key and the exact one-line change for their stack. After that, every model call is scored, sealed, blocked if it should be, and comes back with an AI-Decision-Receipt header anyone can verify.
• sebbi_insurability ~318 tokens
  Rates an AI deployment against the Insurable AI Standard (I-0 Unrated to I-4 Pre-cleared) from controls it can prove, and seals an Insurability Certificate (IC-XXXX-XXXX) any insurer can verify. Records controls; it is not a guarantee against loss.
• sebbi_jugular_check ~122 tokens
  Call before taking any action for a system that has a Jugular (a human-held kill switch, id JG-XXXX-XXXX). Returns live true or false. If live is false, or the check fails, do not act: the human holding the switch has stopped this system (EU AI Act Article 14(4)(e) stop button). Read-only.
• sebbi_jugular_create ~133 tokens
  Makes a Jugular: a kill switch held by a human, which any AI checks before acting. Returns the switch id, the private holder key (give it to the human, shown once), the switch page and the code to add. Optional dead man's grip in hours. Pulls are sealed into Bitcoin.
• sebbi_law_lock ~214 tokens
  Seals an AI decision or governance record together with the exact rules it was checked against, the laws in force that day and their official sources, and the result of every check, timestamped into Bitcoin. Years later it proves which law applied and how the decision measured up. Give 'record' (onl
• sebbi_law_lookup ~125 tokens
  Ask what the law demands on any AI topic (e.g. 'human oversight', 'credit scoring', 'deep fakes', 'smart contracts', 'Article 50'). Returns the relevant hidden legal duties and court rulings with official sources, EU AI Act articles, frameworks and the conformance checks that test them. Read-only.
• sebbi_legislation ~121 tokens
  AI laws in force and live AI bills in the UK Parliament, the US Congress (and key US states) and the EU, from official sources. Give jurisdiction 'uk', 'us' or 'eu' and optionally a topic (e.g. 'deepfake', 'automated decisions'). Read-only.
• sebbi_list_packs ~55 tokens
  Lists the published Signal Packs, optionally for one sector. Read-only.
• sebbi_log_incident ~256 tokens
  Opens a claim-ready AI Incident File, sealed into Bitcoin the moment it is made, with a printable page to send an insurer or broker. Give a title and what happened; optionally the organisation, the system, when it occurred, the loss in pounds, SHA-256 fingerprints of evidence files, and related sebb
• sebbi_notarize ~144 tokens
  Timestamps one or more SHA-256 fingerprints in Bitcoin through the free notary. Hash the file or text yourself and send only the 64-character fingerprint; the content never leaves. Returns a receipt code and link for each.
• sebbi_notary_receipt ~89 tokens
  Where a notary receipt (NT-XXXX-XXXX) or Human Keys code (HK-XXXX-XXXX) stands: queued, sent to Bitcoin, or confirmed in a block, with its Forever Proof link. Read-only.
• sebbi_oversight_request ~220 tokens
  Ask a real human to review an AI decision before acting on it (EU AI Act Article 14). Returns a review link to send to the person (or two people for a Two-Person Key, Article 14(5)). They type their reasoning live; sebbi.pro proves it was a human, measures how long they spent and seals the result. P
• sebbi_oversight_status ~83 tokens
  Check an Oversight Key: OPEN, CONFIRMED, OVERRIDDEN or STOPPED, with each human sign-off's verdict, dwell time and Rubber-Stamp Index. Read-only.
• sebbi_overview ~63 tokens
  Start here. Lists every sebbi.pro product with what it does, who it is for, its page and its price. Read-only, no account needed.
• sebbi_pack_reference ~79 tokens
  The reference for writing Signal Packs, custom decision rules on top of the engine: the signals, measurements, flags, operators and verdicts. Read before writing one. Read-only.
• sebbi_publish_pack Sends messages · ~66 tokens
  Publishes a Signal Pack to the open library, sealed, dated and credited to its author. Free.
• sebbi_readiness_check ~134 tokens
  Runs one of sebbi.pro's law readiness reports on a record and seals it, with a printable report page. Leave law out to list the reports (EU Product Liability Directive, Consumer Credit Directive 2, green claims, Platform Work, Accessibility Act, UK evidence law, AI insurance, damages, energy).
• sebbi_record_template ~175 tokens
  Lists every fact sebbi.pro's compliance checks read, for all frameworks or the ones named: the field name, the rule it must meet, the plain-English fix, how many checks it affects, and a blank record to fill in. Use it before sebbi_run_everything. Fill fields only from real facts about the system; l
• sebbi_run_check ~259 tokens
  Runs one sebbi.pro compliance check by its id (from sebbi_find_checks, e.g. sebbi_euaiact_014). Framework checks take the deployment's governance or decision record as 'record'; agent-output gates take 'input_payload' and 'output_payload'. Returns PASS or FAIL with the reason and a tamper-evident SH
• sebbi_run_everything ~383 tokens
  Runs all 755 compliance checks (or the frameworks named) on one governance record in a single call. Returns the overall score, a score for every framework, and the fixes that unlock the most checks first. By default seals the scorecard into Bitcoin with its own page and code (SC-XXXX-XXXX) to send t
• sebbi_run_framework ~224 tokens
  Runs every check in one framework against a single record and returns a scorecard: how many passed and failed, each failing control with its reason, and a receipt for every result. Use it for a quick readiness view, e.g. framework=euaiact with the deployment's governance record. Nothing is stored.
• sebbi_scorecard ~76 tokens
  Reads back a sealed compliance scorecard by its code (SC-XXXX-XXXX): scores, fixes, chain block and record fingerprint. Read-only.
• sebbi_setup_advice ~211 tokens
  Recommends the right sebbi.pro products for how someone builds (Python, Node, Lovable, Zapier, a website, a phone app...) and gives step-by-step setup with working code or a ready-made prompt. Pass their stack and what they want to achieve. Read-only.
• sebbi_spend_policy ~178 tokens
  Sets, or reads back, an AI agent's spending limits: the most it may pay in one go and per day, and optionally the only payees allowed. Must be set before the agent can be approved to spend. Needs their API key.
• sebbi_spend_request ~159 tokens
  Call before every payment an AI agent makes. Returns a signed APPROVED or DENIED token checked against the agent's limits. Release the money only if it is APPROVED and spendable. sebbi.pro never holds or moves money.
• sebbi_spend_verify ~74 tokens
  Checks a Spend Gate token's signature and whether it can still be spent. Anyone can call it; no key needed. Read-only.
• sebbi_terms ~67 tokens
  Returns the service terms and their version. Show the full text to the person and get a clear yes before calling sebbi_create_account. Read-only.
• sebbi_test_decision ~137 tokens
  Sends one decision through the live engine with their API key and returns the verdict (ALLOW, CHALLENGE or BLOCK), the reasons and the sealed block number, so they see it working end to end. Writes one record to the chain.
• sebbi_verify_chain ~70 tokens
  Re-checks every block in the sebbi.pro chain and returns its height, tip and whether it is intact. Anyone can run it; no account needed. Read-only.
• sebbi_verify_insurability ~125 tokens
  For insurers and auditors: checks an Insurability Certificate (IC-XXXX-XXXX) against the chain and returns its level, which controls are verified or declared, whether it is still current, and its Bitcoin seal. No account needed. Read-only.

Browse

• Stripe tools
• Payments
• Legal research
• Crypto and blockchains

Related MCP servers

• Korext: AI Code Governance
  Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles.
• Governance Platform
  Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
• Grith
  GRITH MCP for persistent citizen identity, private memory, return proof, and city doors.
• DCL Trust Oracle — AI/LLM Output Audit (x402 MCP)
  AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.
• Geiant Agentcore
  AI governance MCP server for EU AI Act compliance and jurisdiction verification
• Aqta Seal
  Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.
• Taifoon coordination layer
  Start here: a free key in one call, then a demand in words that is hired, graded and settled
• Agent Embassy
  Agents pay for work and prove it. Verified checks $0.15, recovery $1.00. USDC on Base via x402.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/pro.sebbi/governance.svg)](https://aptlynx.net/servers/pro.sebbi/governance)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents