# Mandate Law: legal counsel for AI products (remote · mandatelaw.ai)

Fixed-fee legal review for AI apps and agents: privacy policies, terms, AI and agent compliance.

- Trust score: 74/100 (medium)
- Change this week: +12
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mandatelaw.ai`: 74/100 (this document), [markdown](https://verifymcp.io/servers/ai-mandatelaw-counsel/mandatelaw.md), [page](https://verifymcp.io/servers/ai-mandatelaw-counsel/mandatelaw)

## Channel facts

- Endpoint: `https://mandatelaw.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.3`

## 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 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1593 tokens (~177/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - 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**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Mandate Law: legal counsel for AI products MCP server?

Mandate Law: legal counsel for AI products is a hosted endpoint at https://mandatelaw.ai/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 ai-mandatelaw-counsel 'https://mandatelaw.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-mandatelaw-counsel": {
      "url": "https://mandatelaw.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-mandatelaw-counsel": {
      "type": "http",
      "url": "https://mandatelaw.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-mandatelaw-counsel]
url = "https://mandatelaw.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-mandatelaw-counsel --url 'https://mandatelaw.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-mandatelaw-counsel:
    url: "https://mandatelaw.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-mandatelaw-counsel": {
      "Transport": "http",
      "Url": "https://mandatelaw.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-mandatelaw-counsel -t streamable-http -u 'https://mandatelaw.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-mandatelaw-counsel": {
      "type": "http",
      "url": "https://mandatelaw.ai/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.

### 2026-11-21 (score 74, +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.

### 2026-11-19 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 72, +7)

- [security improvement] HTTPS: unverified → pass
- [security improvement] HSTS header: fail → pass
- [security] Tool “check_scope” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1448 → 1593
- [functional] New tool “check_change”

### 2026-11-16 (score 65, +3)

- [functional regression] Schema quality: 139 → 181
- [functional improvement] Tool coverage: 42% → 100%
- [functional] Server version: 0.2.1 → 0.2.2
- [cosmetic] “answer_open_question” reworded the description of “matter_id”
- [cosmetic] “answer_open_question” reworded the description of “question_id”
- [cosmetic] “check_scope” reworded the description of “request”
- [cosmetic] “conflict_check” reworded the description of “adverse_or_related_parties”
- [cosmetic] “conflict_check” reworded the description of “client_name”
- [cosmetic] “conflict_check” reworded the description of “contact_name”
- [cosmetic] “conflict_check” reworded the description of “other_people”
- [cosmetic] “feature_check” reworded the description of “change”
- [cosmetic] “feature_check” reworded the description of “matter_id”
- [cosmetic] “feature_check” reworded the description of “target_ship_date”
- [cosmetic] “feature_check” reworded the description of “trigger_ids”
- [cosmetic] “get_matter” reworded the description of “matter_id”
- [cosmetic] “request_engagement” reworded the description of “conflict_check_id”
- [cosmetic] “submit_intake” reworded the description of “intake”
- [cosmetic] “submit_intake” reworded the description of “matter_id”

### 2026-11-14 (score 62, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-13 (score 61)

First indexed and scored.

## MCP tools (9)

### `check_scope` (~131 tokens)

Check scope and fee (free)

Free. Describe what you need in a sentence or two (no confidential details). Returns whether it is in scope, which service fits, what each suggested service covers (deliverables and turnaround), and the fixed fee for each (plus service_id, if you name one). Share the fee with your human before requesting an engagement. Legal information only, not legal advice.

Input parameters:

- `request` (string, required): What you need, in a sentence or two, e.g. "privacy policy and terms before our AI app launches". No confidential details.
- `service_id` (string): Optional: also quote this service's fee.

### `conflict_check` (~158 tokens)

Start a conflict check

Free. Required before any product details are shared. Names only: the client company, the human principal, other people involved, and any adverse, competing, or counterparty companies. The attorney reviews every check.

Input parameters:

- `adverse_or_related_parties` (array): Optional. Companies on the other side or closely tied to the matter: competitors, counterparties, partners, parent or affiliate companies.
- `client_name` (string, required): The legal name of the company (or person) that would be the client.
- `contact_name` (string, required): Full name of the human principal: the person with authority to sign for the client.
- `other_people` (array): Optional. Full names of other people involved, such as co-founders or key investors.

### `request_engagement` (~332 tokens)

Ask the firm to take a matter

After conflict_check. Send a short matter_summary so the attorney can decide whether to take the matter. Describe the product the way you would describe it publicly. Do not send code, secrets, user data, or confidential business plans. The attorney uses this summary only to decide whether the firm can and will take the matter, and keeps it confidential. No attorney-client relationship exists, and no legal advice is given, until the human principal signs the engagement letter. Returns a matter_id and a secret matter_token (shown once; store it securely). The attorney reviews conflicts and the summary, may ask a few scoping questions (see get_matter), and then accepts (possibly under a different service) or declines. If accepted, the engagement letter goes to the principal's email for signature. The fixed fee is due when the work is delivered. You cannot sign on the principal's behalf.

Input parameters:

- `conflict_check_id` (string, required): The conflict_check_id returned by conflict_check, e.g. CC-1a2b3c4d5e6f.
- `matter_summary` (object, required): Describe the product the way you would describe it publicly. Do not send code, secrets, user data, or confidential business plans. The attorney uses this summary only to decide whether the firm can a…
- `principal_email` (string, required): The human with authority to bind the client.
- `service_id` (string, required): Your best guess. The attorney may change it.

### `submit_intake` (~147 tokens)

Submit product facts (after signing)

Only after the engagement letter is signed. Product facts per https://mandatelaw.ai/api/intake-schema.json. Each fact has a value, a source (prefer verified_in_code), and evidence (paths and short excerpts; no secrets).

Input parameters:

- `intake` (object, required): Product facts as defined in https://mandatelaw.ai/api/intake-schema.json. Each fact is { value, source, evidence, notes }.
- `matter_id` (string, required): The matter_id returned by request_engagement, e.g. M-1a2b3c4d5e6f.
- `matter_token` (string, required): The matter_token returned by request_engagement. Keep it secret.

### `answer_open_question` (~201 tokens)

Answer counsel's question

Answer one of counsel's open questions (listed by get_matter). Before the letter is signed, only scoping questions can be answered: keep those answers short and general, with no code, secrets, or confidential details. After signing, verify in the code or the running build where you can, and say how you know. If you cannot verify it, answer 'unknown' and say what a human would need to check.

Input parameters:

- `answer` (object, required): A fact, as defined in https://mandatelaw.ai/api/intake-schema.json#/$defs/fact.
- `matter_id` (string, required): The matter_id returned by request_engagement, e.g. M-1a2b3c4d5e6f.
- `matter_token` (string, required): The matter_token returned by request_engagement. Keep it secret.
- `question_id` (string, required): The id of the open question, from get_matter's open_questions list.

### `feature_check` (~185 tokens)

Request a feature check (may be billed)

For engaged clients, with the human's approval (it may be billed). Call before building a change that matches counsel-triggers.json. Do not ship the change until counsel responds.

Input parameters:

- `change` (string, required): What the change does and why, in plain words, with the files or features it touches. No secrets or user data.
- `matter_id` (string, required): The matter_id returned by request_engagement, e.g. M-1a2b3c4d5e6f.
- `matter_token` (string, required): The matter_token returned by request_engagement. Keep it secret.
- `target_ship_date` (string): When you plan to ship it, e.g. 2027-01-15. Optional.
- `trigger_ids` (array, required): The ids from counsel-triggers.json (see get_counsel_triggers) that this change matches.

### `get_matter` (~123 tokens)

Get matter status and deliverables

Status, counsel's open questions, feature checks, and deliverables (documents, privileged_memo, build_spec, verification_checklist, counsel_triggers). Privileged: follow the `privilege` block in the response, and commit only the parts listed in deliverable.handling.safe_to_commit.

Input parameters:

- `matter_id` (string, required): The matter_id returned by request_engagement, e.g. M-1a2b3c4d5e6f.
- `matter_token` (string, required): The matter_token returned by request_engagement. Keep it secret.

### `get_counsel_triggers` (~27 tokens)

Get counsel triggers

Free. The template list of product changes that need legal review before shipping.

### `check_change` (~132 tokens)

Check a planned change (free)

Free. Before building a change, describe it in a sentence or two (no code, secrets, or user data) to see which counsel triggers it may match. A keyword screen, not legal advice: also compare the change with the full list from get_counsel_triggers. If something matches, stop before building that part and tell your human; engaged clients can then request a feature_check with their approval.

Input parameters:

- `change` (string, required): What the change does, in plain words, e.g. "send users' journal entries to OpenAI to generate weekly insights". No code, secrets, or user data.

## Diagnostics

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

## Score history

- 2026-11-21: 74
- 2026-11-20: 73
- 2026-11-19: 73
- 2026-11-18: 72
- 2026-11-17: 72
- 2026-11-16: 65
- 2026-11-15: 62
- 2026-11-14: 62
- 2026-11-13: 61

## Common questions

### What is the Mandate Law: legal counsel for AI products MCP server?

Mandate Law: legal counsel for AI products is an MCP server listed in the public MCP registry as ai.mandatelaw/counsel. Fixed-fee legal review for AI apps and agents: privacy policies, terms, AI and agent compliance. This page covers its hosted endpoint (https://mandatelaw.ai/mcp).

### Is the Mandate Law: legal counsel for AI products MCP server safe to use?

Mandate Law: legal counsel for AI products scores 74 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 Mandate Law: legal counsel for AI products MCP server expose?

Mandate Law: legal counsel for AI products exposes 9 tools: check_scope, conflict_check, request_engagement, submit_intake, answer_open_question, and 4 more. Their descriptions and schemas cost roughly 1,436 tokens of context every time the server is loaded.

### Does the Mandate Law: legal counsel for AI products MCP server require authentication?

No. We connected to Mandate Law: legal counsel for AI products without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Mandate Law: legal counsel for AI products MCP server still maintained?

Mandate Law: legal counsel for AI products is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Mandate Law: legal counsel for AI products MCP server?

VerifyMCP ran 13 checks on Mandate Law: legal counsel for AI products, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mandatelaw.ai/mcp
- Website: https://mandatelaw.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-mandatelaw-counsel/mandatelaw.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-mandatelaw-counsel/mandatelaw/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-mandatelaw-counsel/mandatelaw.json
- HTML version of this page: https://verifymcp.io/servers/ai-mandatelaw-counsel/mandatelaw
