# sebbi.pro - the proof layer for AI (remote · sebbi.pro)

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

- Trust score: 76/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `sebbi.pro`: 76/100 (this document), [markdown](https://verifymcp.io/servers/pro-sebbi-governance/sebbi.md), [page](https://verifymcp.io/servers/pro-sebbi-governance/sebbi)

## Channel facts

- Endpoint: `https://sebbi.pro/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2775 tokens (~106/item across 26 items; 26 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 48% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 27 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the sebbi.pro - the proof layer for AI MCP server?

sebbi.pro - the proof layer for AI is a hosted endpoint at https://sebbi.pro/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

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

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pro-sebbi-governance": {
      "type": "remote",
      "url": "https://sebbi.pro/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pro-sebbi-governance --url 'https://sebbi.pro/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  pro-sebbi-governance:
    url: "https://sebbi.pro/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "pro-sebbi-governance": {
      "Transport": "http",
      "Url": "https://sebbi.pro/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add pro-sebbi-governance -t streamable-http -u 'https://sebbi.pro/mcp'
```

### Other

```json
{
  "mcpServers": {
    "pro-sebbi-governance": {
      "type": "http",
      "url": "https://sebbi.pro/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 75, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “sebbi_find_checks” rewrote its description, which is the text the model reads

### 2026-10-19 (score 74, +3)

- [security improvement] Judged manipulation: unverified → pass
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “sebbi_check_pack” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_create_account” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_decision_report” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_forever_proof” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_gateway_setup” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_list_packs” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_notarize” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_notary_receipt” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_overview” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_pack_reference” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_publish_pack” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_setup_advice” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_spend_policy” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_spend_request” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_spend_verify” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_terms” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_test_decision” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_verify_chain” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_billing_link” rewrote its description, which is the text the model reads
- [security] Tool “sebbi_check_human_proof” rewrote its description, which is the text the model reads
- [functional improvement] Tool coverage: 42% → 48%
- [functional improvement] Schema quality: 64986 → 2775
- [functional] New tool “sebbi_check_source”
- [functional] New tool “sebbi_find_checks”
- [functional] New tool “sebbi_insurability”
- [functional] New tool “sebbi_run_check”
- [functional] New tool “sebbi_run_framework”
- [functional] New tool “sebbi_verify_insurability”
- [cosmetic] Tool “sebbi_check_pack” changed its title: Check a Signal Pack → Test a Signal Pack
- [cosmetic] Tool “sebbi_create_account” changed its title: Create an account → Open an account
- [cosmetic] Tool “sebbi_decision_report” changed its title: Machine-proof decision report → Proof report for one decision
- [cosmetic] Tool “sebbi_forever_proof” changed its title: Forever proof → Get a Forever Proof
- [cosmetic] Tool “sebbi_gateway_setup” changed its title: Gateway setup → Govern every OpenAI or Anthropic call
- [cosmetic] Tool “sebbi_list_packs” changed its title: List Signal Packs → Browse Signal Packs
- [cosmetic] Tool “sebbi_notarize” changed its title: Notarize → Timestamp anything in Bitcoin (free)
- [cosmetic] Tool “sebbi_notary_receipt” changed its title: Notary receipt → Check a notary receipt
- [cosmetic] Tool “sebbi_overview” changed its title: Overview of sebbi.pro → What sebbi.pro does
- [cosmetic] Tool “sebbi_pack_reference” changed its title: Signal Pack reference → How to write a Signal Pack
- [cosmetic] Tool “sebbi_setup_advice” changed its title: Setup advice for your stack → Setup plan for their stack
- [cosmetic] Tool “sebbi_spend_policy” changed its title: Set or read a spend policy → Set an agent's spending limits
- [cosmetic] Tool “sebbi_spend_request” changed its title: Request a spend sign-off → Ask before an agent pays
- [cosmetic] Tool “sebbi_test_decision” changed its title: Score and seal a test decision → Seal a first decision
- [cosmetic] Tool “sebbi_verify_chain” changed its title: Verify the chain → Verify the whole chain

### 2026-10-18 (score 71, 0)

We did not load change detail this far back for this component, so this day may have recorded more than is shown.

- [security] Tool “sebbi_setup_advice” rewrote its description, which is the text the model reads
- [functional] New tool “sebbi_iso27001_020”
- [functional] New tool “sebbi_sebbisounds_gate_021”
- [functional] New tool “sebbi_normalizer_gate_060”
- [functional] New tool “sebbi_gdpr_002”
- [functional] New tool “sebbi_euaiact_006”
- [functional] New tool “sebbi_sebbisounds_gate_009”
- [functional] New tool “sebbi_dsa_007”
- [functional] New tool “sebbi_soc2_015”
- [functional] New tool “sebbi_hipaa_002”
- [functional] New tool “sebbi_gdpr_009”
- [functional] New tool “sebbi_insurability”
- [functional] New tool “sebbi_ccpa_013”
- [functional] New tool “sebbi_compliance_gate_064”
- [functional] New tool “sebbi_math_gate_052”
- [functional] New tool “sebbi_cra_011”
- [functional] New tool “sebbi_gdpr_003”
- [functional] New tool “sebbi_cra_002”
- [functional] New tool “sebbi_math_gate_020”
- [functional] New tool “sebbi_euaiact_004”
- [functional] New tool “sebbi_compliance_gate_034”
- [functional] New tool “sebbi_osa_009”
- [functional] New tool “sebbi_sebbisounds_gate_018”
- [functional] New tool “sebbi_dsa_013”
- [functional] New tool “sebbi_iso42001_014”
- [functional] New tool “sebbi_iso42001_013”
- [functional] New tool “sebbi_math_gate_005”
- [functional] New tool “sebbi_pcidss_019”
- [functional] New tool “sebbi_sebbisounds_gate_063”
- [functional] New tool “sebbi_normalizer_gate_053”
- [functional] New tool “sebbi_soc2_017”
- [functional] New tool “sebbi_osa_005”
- [functional] New tool “sebbi_sebbisounds_gate_052”
- [functional] New tool “sebbi_normalizer_gate_014”
- [functional] New tool “sebbi_nis2_006”
- [functional] New tool “sebbi_math_gate_017”
- [functional] New tool “sebbi_sebbisounds_gate_041”
- [functional] New tool “sebbi_usstateai_012”
- [functional] New tool “sebbi_normalizer_gate_023”
- [functional] New tool “sebbi_compliance_gate_032”
- [functional] New tool “sebbi_euaiact_029”
- [functional] New tool “sebbi_compliance_gate_008”
- [functional] New tool “sebbi_euaiact_033”
- [functional] New tool “sebbi_modelrisk_003”
- [functional] New tool “sebbi_dsa_009”
- [functional] New tool “sebbi_normalizer_gate_033”
- [functional] New tool “sebbi_sebbisounds_gate_051”
- [functional] New tool “sebbi_euaiact_024”
- [functional] New tool “sebbi_osa_007”
- [functional] New tool “sebbi_iso27001_009”
- [functional] New tool “sebbi_fca_012”
- [functional] New tool “sebbi_pcidss_002”
- [functional] New tool “sebbi_normalizer_gate_020”
- [functional] New tool “sebbi_childrenscode_009”
- [functional] New tool “sebbi_dsa_012”
- [functional] New tool “sebbi_euaiact_012”
- [functional] New tool “sebbi_normalizer_gate_064”
- [functional] New tool “sebbi_iso42001_002”
- [functional] New tool “sebbi_ccpa_002”
- [functional] New tool “sebbi_pcidss_015”
- [functional] New tool “sebbi_sebbisounds_gate_025”
- [functional] New tool “sebbi_math_gate_055”
- [functional] New tool “sebbi_normalizer_gate_009”
- [functional] New tool “sebbi_dora_011”
- [functional] New tool “sebbi_gdpr_027”
- [functional] New tool “sebbi_nistai_013”
- [functional] New tool “sebbi_compliance_gate_006”
- [functional] New tool “sebbi_sebbisounds_gate_008”
- [functional] New tool “sebbi_math_gate_022”
- [functional] New tool “sebbi_sebbisounds_gate_049”
- [functional] New tool “sebbi_dsa_010”
- [functional] New tool “sebbi_normalizer_gate_015”
- [functional] New tool “sebbi_normalizer_gate_021”
- [functional] New tool “sebbi_math_gate_033”
- [functional] New tool “sebbi_normalizer_gate_032”
- [functional] New tool “sebbi_normalizer_gate_004”
- [functional] New tool “sebbi_compliance_gate_009”
- [functional] New tool “sebbi_pcidss_013”
- [functional] New tool “sebbi_compliance_gate_030”
- [functional] New tool “sebbi_sebbisounds_gate_022”
- [functional] New tool “sebbi_math_gate_007”
- [functional] New tool “sebbi_fca_007”
- [functional] New tool “sebbi_iso27001_013”
- [functional] New tool “sebbi_iso42001_006”
- [functional] New tool “sebbi_nistai_007”
- [functional] New tool “sebbi_sebbisounds_gate_050”
- [functional] New tool “sebbi_fca_013”
- [functional] New tool “sebbi_gdpr_008”
- [functional] New tool “sebbi_math_gate_064”
- [functional] New tool “sebbi_euaiact_015”
- [functional] New tool “sebbi_sebbisounds_gate_056”
- [functional] New tool “sebbi_compliance_gate_001”
- [functional] New tool “sebbi_cra_005”
- [functional] New tool “sebbi_euaiact_008”
- [functional] New tool “sebbi_soc2_016”
- [functional] New tool “sebbi_sebbisounds_gate_035”
- [functional] New tool “sebbi_usstateai_008”
- [functional] New tool “sebbi_childrenscode_015”
- [functional] New tool “sebbi_compliance_gate_057”
- [functional] New tool “sebbi_modelrisk_001”
- [functional] New tool “sebbi_gdpr_021”
- [functional] New tool “sebbi_euaiact_035”
- [functional] New tool “sebbi_euaiact_031”
- [functional] New tool “sebbi_iso42001_007”
- [functional] New tool “sebbi_nistai_011”
- [functional] New tool “sebbi_sebbisounds_gate_044”
- [functional] New tool “sebbi_cra_003”
- [functional] New tool “sebbi_normalizer_gate_057”
- [functional] New tool “sebbi_normalizer_gate_001”
- [functional] New tool “sebbi_iso27001_024”
- [functional] New tool “sebbi_ccpa_003”
- [functional] New tool “sebbi_dora_016”
- [functional] New tool “sebbi_compliance_gate_016”
- [functional] New tool “sebbi_osa_014”
- [functional] New tool “sebbi_compliance_gate_056”
- [functional] New tool “sebbi_compliance_gate_028”
- [functional] New tool “sebbi_normalizer_gate_063”
- [functional] New tool “sebbi_compliance_gate_062”
- [functional] New tool “sebbi_nistai_002”
- [functional] New tool “sebbi_iso27001_006”
- [functional] New tool “sebbi_math_gate_008”
- [functional] New tool “sebbi_modelrisk_011”
- [functional] New tool “sebbi_euaiact_030”
- [functional] New tool “sebbi_iso27001_018”
- [functional] New tool “sebbi_soc2_014”
- [functional] New tool “sebbi_iso27001_022”
- [functional] New tool “sebbi_euaiact_013”
- [functional] New tool “sebbi_normalizer_gate_056”
- [functional] New tool “sebbi_iso27001_021”
- [functional] New tool “sebbi_compliance_gate_003”
- [functional] New tool “sebbi_usstateai_009”
- [functional] New tool “sebbi_normalizer_gate_025”
- [functional] New tool “sebbi_ccpa_001”
- [functional] New tool “sebbi_iso27001_001”
- [functional] New tool “sebbi_hipaa_008”
- [functional] New tool “sebbi_normalizer_gate_036”
- [functional] New tool “sebbi_nis2_010”
- [functional] New tool “sebbi_math_gate_029”
- [functional] New tool “sebbi_math_gate_015”
- [functional] New tool “sebbi_hipaa_014”
- [functional] New tool “sebbi_dsa_001”
- [functional] New tool “sebbi_iso27001_007”
- [functional] New tool “sebbi_pcidss_018”
- [functional] New tool “sebbi_euaiact_036”
- [functional] New tool “sebbi_euaiact_037”
- [functional] New tool “sebbi_nistai_003”
- [functional] New tool “sebbi_pcidss_021”
- [functional] New tool “sebbi_modelrisk_010”
- [functional] New tool “sebbi_soc2_008”
- [functional] New tool “sebbi_childrenscode_007”

### 2026-10-17 (score 71, +1)

We did not load change detail this far back for this component, so this day may have recorded more than is shown.

### 2026-10-14 (score 70, +1)

We did not load change detail this far back for this component, so this day may have recorded more than is shown.

### 2026-10-12 (score 69, −1)

We did not load change detail this far back for this component, so this day may have recorded more than is shown.

### 2026-10-08 (score 70)

First indexed and scored.

## MCP tools (26)

### `sebbi_overview` (~42 tokens)

What sebbi.pro does

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_setup_advice` (~159 tokens)

Setup plan for their stack

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.

Input parameters:

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

### `sebbi_terms` (~39 tokens)

Read the terms

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_create_account` (~138 tokens)

Open an 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.

Input parameters:

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

### `sebbi_test_decision` (~96 tokens)

Seal a first 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.

Input parameters:

- `action` (string)
- `amount` (number)
- `api_key` (string, required)
- `country` (string)
- `user_id` (string)

### `sebbi_billing_link` (~62 tokens)

Get a 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.

Input parameters:

- `devices` (integer)
- `email` (string, required)
- `product` (string)

### `sebbi_gateway_setup` (~104 tokens)

Govern every OpenAI or Anthropic call

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.

Input parameters:

- `api_key` (string, required)
- `label` (string)
- `stack` (string): e.g. 'Python OpenAI SDK', 'Node Anthropic SDK', 'LangChain', 'curl'

### `sebbi_decision_report` (~80 tokens)

Proof report for one decision

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.

Input parameters:

- `api_key` (string, required)
- `block` (integer, required)

### `sebbi_verify_chain` (~45 tokens)

Verify the whole chain

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_notarize` (~89 tokens)

Timestamp anything in Bitcoin (free)

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.

Input parameters:

- `api_key` (string)
- `digests` (array, required)
- `label` (string): Optional public label, up to 80 characters

### `sebbi_notary_receipt` (~65 tokens)

Check a 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.

Input parameters:

- `code` (string, required)

### `sebbi_forever_proof` (~74 tokens)

Get a 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.

Input parameters:

- `api_key` (string)
- `block` (integer)
- `code` (string)

### `sebbi_check_human_proof` (~57 tokens)

Check a Human Key

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.

Input parameters:

- `code` (string, required)

### `sebbi_check_source` (~110 tokens)

Check an input against its source

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.

Input parameters:

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

### `sebbi_spend_policy` (~118 tokens)

Set an agent's spending limits

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.

Input parameters:

- `agent` (string, required)
- `api_key` (string, required)
- `currency` (string)
- `daily` (number, required): Max per day, in pounds
- `payees` (array)
- `per_tx` (number, required): Max per payment, in pounds

### `sebbi_spend_request` (~105 tokens)

Ask before an agent pays

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.

Input parameters:

- `agent` (string, required)
- `amount` (number, required): Amount in pounds
- `api_key` (string, required)
- `currency` (string)
- `payee` (string, required)
- `reason` (string)

### `sebbi_spend_verify` (~45 tokens)

Verify a spend token

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

Input parameters:

- `token` (string, required)

### `sebbi_insurability` (~222 tokens)

Rate an AI deployment's 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.

Input parameters:

- `decisions` (boolean): Attest: every AI decision is sealed (Art 12 logging)
- `domain` (string, required): The deployment's domain, e.g. yourapp.com
- `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)
- `name` (string): Display name (optional)
- `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)

### `sebbi_verify_insurability` (~79 tokens)

Verify an insurability certificate

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.

Input parameters:

- `code` (string, required): The certificate code, IC-XXXX-XXXX

### `sebbi_pack_reference` (~46 tokens)

How to write a Signal Pack

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_check_pack` (~39 tokens)

Test a Signal Pack

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

Input parameters:

- `pack` (object, required)

### `sebbi_publish_pack` (~38 tokens)

Publish a Signal Pack

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

Input parameters:

- `pack` (object, required)

### `sebbi_list_packs` (~32 tokens)

Browse Signal Packs

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

Input parameters:

- `vertical` (string)

### `sebbi_find_checks` (~221 tokens)

Find compliance checks

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.

Input parameters:

- `framework` (string): Framework key, e.g. euaiact, gdpr, dora, iso42001. Leave out to list frameworks.
- `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'.

### `sebbi_run_check` (~176 tokens)

Run one compliance check

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.

Input parameters:

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

### `sebbi_run_framework` (~136 tokens)

Run a whole framework

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.

Input parameters:

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

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/pro-sebbi-governance/sebbi#diagnostics

## Score history

- 2026-10-23: 76
- 2026-10-22: 75
- 2026-10-21: 75
- 2026-10-20: 75
- 2026-10-19: 74
- 2026-10-18: 71
- 2026-10-17: 71
- 2026-10-16: 70
- 2026-10-15: 70
- 2026-10-14: 70
- 2026-10-13: 69
- 2026-10-12: 69
- 2026-10-10: 70
- 2026-10-08: 70

## Common questions

### What is the sebbi.pro - the proof layer for AI MCP server?

sebbi.pro - the proof layer for AI is an MCP server listed in the public MCP registry as pro.sebbi/governance. Score, seal and prove AI decisions in Bitcoin, plus 739 compliance checks, free to verify. This page covers its hosted endpoint (https://sebbi.pro/mcp).

### Is the sebbi.pro - the proof layer for AI MCP server safe to use?

sebbi.pro - the proof layer for AI scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the sebbi.pro - the proof layer for AI MCP server expose?

sebbi.pro - the proof layer for AI exposes 26 tools: sebbi_overview, sebbi_setup_advice, sebbi_terms, sebbi_create_account, sebbi_test_decision, and 21 more. Their descriptions and schemas cost roughly 2,417 tokens of context every time the server is loaded.

### Does the sebbi.pro - the proof layer for AI MCP server require authentication?

No. We connected to sebbi.pro - the proof layer for AI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the sebbi.pro - the proof layer for AI MCP server still maintained?

sebbi.pro - the proof layer for AI is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://sebbi.pro/mcp
- Website: https://sebbi.pro/
- Changelog RSS feed: https://verifymcp.io/servers/pro-sebbi-governance/sebbi.xml
- Changelog JSON feed: https://verifymcp.io/servers/pro-sebbi-governance/sebbi.json
- HTML version of this page: https://verifymcp.io/servers/pro-sebbi-governance/sebbi