# Compliance Registry (remote · complianceregistry.net)

First A2A registry where AI agents discover & transact with compliance firms - audits, permits.

- Trust score: 63/100 (medium)
- Change this week: +33
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `complianceregistry.net`: 63/100 (this document), [markdown](https://verifymcp.io/servers/net-complianceregistry-mcp-server/complianceregistry.md), [page](https://verifymcp.io/servers/net-complianceregistry-mcp-server/complianceregistry)

## Channel facts

- Endpoint: `https://complianceregistry.net/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-08-03.

- **Endpoint Security**: 60/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 646 tokens (~107/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http net-complianceregistry-mcp-server https://complianceregistry.net/mcp/
```

### Codex

```toml
[mcp_servers.net-complianceregistry-mcp-server]
url = "https://complianceregistry.net/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "net-complianceregistry-mcp-server": {
      "type": "remote",
      "url": "https://complianceregistry.net/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add net-complianceregistry-mcp-server --url https://complianceregistry.net/mcp/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  net-complianceregistry-mcp-server:
    url: "https://complianceregistry.net/mcp/"
```

### Other

```json
{
  "mcpServers": {
    "net-complianceregistry-mcp-server": {
      "type": "http",
      "url": "https://complianceregistry.net/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.

### 2026-08-03 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 62, +23)

- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional regression] Schema quality: unverified → fail
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Schema quality: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Stability: fail → 0.23
- [functional] New tool “request_quote”
- [functional] New tool “request_introduction”
- [functional] New tool “get_wcag_audit”
- [functional] New tool “get_firm_profile”
- [functional] New tool “find_compliance_firm”
- [functional] New tool “claim_listing”

### 2026-07-31 (score 39, −20)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 59, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 58, +28)

- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional regression] Schema quality: unverified → fail
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Schema quality: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Stability: fail → 0.07
- [functional] New tool “request_quote”
- [functional] New tool “request_introduction”
- [functional] New tool “get_wcag_audit”
- [functional] New tool “get_firm_profile”
- [functional] New tool “find_compliance_firm”
- [functional] New tool “claim_listing”

### 2026-07-27 (score 30, −27)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 57)

First indexed and scored.

## MCP tools (6)

### `find_compliance_firm` (~124 tokens)

Search the Compliance Registry for vetted compliance and regulatory firms.

        sub_vertical: 'environmental_compliance' | 'accessibility' (or free-text keyword)
        region:       city or state name (case-insensitive contains)
        capability:   keyword to match against firm descriptions and service names
                      (e.g., 'phase i esa', 'wcag', 'permits', 'inspections')
        limit:        max results

Input parameters:

- `capability`
- `limit` (integer)
- `region`
- `sub_vertical`

### `get_firm_profile` (~66 tokens)

Full dossier for a single firm in the Compliance Registry:
        description, headquarters, founded year, employee band, services,
        locations, sub-vertical, taxonomy, and directory meta (publisher,
        claim URL, takedown URL).

Input parameters:

- `slug` (string, required)

### `get_wcag_audit` (~83 tokens)

Structured offering for TESSA's WCAG 2.2 AA Accessibility Audit:
        scope, deliverables, timeline, pricing bands (hourly + engagement
        range), paired service-type slugs, and TESSA's profile URL in the
        Compliance Registry. Use when a buyer agent wants accessibility audit
        details in structured form.

### `request_introduction` (~116 tokens)

Request a warm introduction to a Compliance Registry firm.
        target_firm_slug is required (this tool routes leads to listed firms,
        not to TESSA directly). TESSA logs the lead and forwards a warm intro
        email to the firm with TESSA Cc'd. No calendar booking.

Input parameters:

- `project_brief`
- `prospect_email` (string, required)
- `prospect_name`
- `prospect_org`
- `requested_window`
- `target_firm_slug` (string, required)

### `claim_listing` (~107 tokens)

Record a firm's intent to claim its directory listing.

        Pre-OAuth, TESSA logs the claim and a representative reaches out
        via email within one business day to verify the claimant and switch
        the listing's verification status to 'claimed'. Full self-service
        OAuth-2.1 claim flow lands in a follow-up plan.

Input parameters:

- `claim_email` (string, required)
- `claimant_name`
- `claimant_role`
- `firm_slug` (string, required)

### `request_quote` (~150 tokens)

Request a quote from a Compliance Registry firm.

        firm_slug:       directory slug for the target firm
        prospect_email:  caller's email for the firm's reply
        scope_summary:   one-paragraph description of the work
        budget_band:     'under_5k' | '5k_25k' | '25k_100k' | '100k_plus' |
                         'open' — or any free-text dollar figure

Input parameters:

- `budget_band`
- `firm_slug` (string, required)
- `prospect_email` (string, required)
- `prospect_name`
- `prospect_org`
- `requested_window`
- `scope_summary` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/net-complianceregistry-mcp-server/complianceregistry#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 62
- 2026-08-01: 39
- 2026-07-31: 39
- 2026-07-30: 59
- 2026-07-29: 59
- 2026-07-28: 58
- 2026-07-27: 30
- 2026-07-26: 57

## Links

- Remote endpoint: https://complianceregistry.net/mcp/
- Repository: https://github.com/globalpart/tessa-aios
- Changelog RSS feed: https://verifymcp.io/servers/net-complianceregistry-mcp-server/complianceregistry/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-complianceregistry-mcp-server/complianceregistry/changelog.json
- HTML version of this page: https://verifymcp.io/servers/net-complianceregistry-mcp-server/complianceregistry