sebbi.pro - the proof layer for AI

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Score, seal and prove AI decisions in Bitcoin, plus 739 compliance checks, free to verify.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "sebbi.pro - the proof layer for AI": {
      "url": "https://sebbi.pro/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (26)

• sebbi_overview read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_setup_advice read-only

  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.

  Parameters:

  • stack (required) — string — How they build or what they use, e.g. 'Lovable website', 'Python on AWS', 'Zapier'
  • goal — string — What they want, e.g. 'prove our loan AI is compliant', 'cut our OpenAI bill'
  • device — string — Where they are working from, e.g. 'Android phone', 'Mac'
  • api_key — string

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_terms read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_create_account

  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.

  Parameters:

  • email (required) — string
  • terms_version (required) — string — terms_version from sebbi_terms
  • customer_agreed (required) — boolean — true only if the customer read the terms and said yes
  • name — string
  • company — string
  • devices — integer — Estimated devices; billing uses the real count
  • product — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_test_decision

  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.

  Parameters:

  • api_key (required) — string
  • action — string
  • amount — number
  • country — string
  • user_id — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_billing_link

  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.

  Parameters:

  • email (required) — string
  • devices — integer
  • product — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_gateway_setup

  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.

  Parameters:

  • api_key (required) — string
  • label — string
  • stack — string — e.g. 'Python OpenAI SDK', 'Node Anthropic SDK', 'LangChain', 'curl'

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_decision_report read-only

  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.

  Parameters:

  • api_key (required) — string
  • block (required) — integer

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_verify_chain read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_notarize

  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.

  Parameters:

  • digests (required) — array
  • label — string — Optional public label, up to 80 characters
  • api_key — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_notary_receipt

  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.

  Parameters:

  • code (required) — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_forever_proof

  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.

  Parameters:

  • code — string
  • block — integer
  • api_key — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_check_human_proof read-only

  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.

  Parameters:

  • code (required) — string

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_check_source read-only

  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.

  Parameters:

  • domain (required) — string — The source domain, e.g. example.com
  • data — string — The input text to check
  • hash — string — Or the SHA-256 of the data, instead of the text

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• sebbi_spend_policy

  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.

  Parameters:

  • api_key (required) — string
  • agent (required) — string
  • per_tx (required) — number — Max per payment, in pounds
  • daily (required) — number — Max per day, in pounds
  • payees — array
  • currency — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_spend_request

  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.

  Parameters:

  • api_key (required) — string
  • agent (required) — string
  • amount (required) — number — Amount in pounds
  • payee (required) — string
  • reason — string
  • currency — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_spend_verify read-only

  Checks a Spend Gate token's signature and whether it can still be spent. Anyone can call it; no key needed. Read-only.

  Parameters:

  • token (required) — string

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_insurability

  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.

  Parameters:

  • domain (required) — string — The deployment's domain, e.g. yourapp.com
  • name — string — Display name (optional)
  • human — boolean — Attest: a named human is accountable, actions carry a signed permission
  • mcp_code — string — An MCP-Shield code MS-XXXX-XXXX, to verify the 'Tools guarded' pillar (optional)
  • decisions — boolean — Attest: every AI decision is sealed (Art 12 logging)
  • precleared — boolean — Attest: no autonomous payment fires without a sealed sign-off (Witness-Proof)
  • source_domain — string — A sebbi Verified-Source domain, to verify the 'Inputs sourced' pillar (optional)

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• sebbi_verify_insurability read-only

  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.

  Parameters:

  • code (required) — string — The certificate code, IC-XXXX-XXXX

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• sebbi_pack_reference read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_check_pack read-only

  Checks a Signal Pack with the engine's own validator without publishing it, and explains any problem. Read-only.

  Parameters:

  • pack (required) — object

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_publish_pack

  Publishes a Signal Pack to the open library, sealed, dated and credited to its author. Free.

  Parameters:

  • pack (required) — object

  Hints: read-only no · destructive no · idempotent no · open-world yes

• sebbi_list_packs read-only

  Lists the published Signal Packs, optionally for one sector. Read-only.

  Parameters:

  • vertical — string

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• sebbi_find_checks read-only

  Searches sebbi.pro's 739 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 framework and/or words; returns each check's id, title, what it needs and the framework list. Then run one with sebbi_run_check or a whole framework with sebbi_run_framework. Read-only.

  Parameters:

  • limit — integer — Most checks to return (default 40, max 200).
  • search — string — Words to look for in the check titles, e.g. 'human oversight' or 'retention'.
  • framework — string — Framework key, e.g. euaiact, gdpr, dora, iso42001. Leave out to list frameworks.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• sebbi_run_check read-only

  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 SHA-256 receipt. Nothing is stored.

  Parameters:

  • check (required) — string — The check id, e.g. sebbi_gdpr_002.
  • reason — string — Optional note on why the check is being run.
  • record — object — The governance or decision record (framework checks).
  • input_payload — object — What went into the AI step (agent-output gates).
  • output_payload — object — What the AI step produced (agent-output gates).

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• sebbi_run_framework read-only

  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.

  Parameters:

  • framework (required) — string — Framework key from sebbi_find_checks, e.g. euaiact.
  • record — object — The governance or decision record (framework checks).
  • input_payload — object — For agent-output gate frameworks.
  • output_payload — object — For agent-output gate frameworks.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.