Skip to content
MCP server

Mandate Law: legal counsel for AI products

Remote MCP server for ordering fixed-fee legal review of AI apps and agents

Verified workingStatus and history

Answered our tool-list check 3 of 3 times in the last 7 days; last seen working yesterday.

Install
Pricing
Paid
Platforms
Web, API
Runs
Remotely
Version
0.2.3
Listing updated
5 days ago

Similar MCP servers

About Mandate Law: legal counsel for AI products

Mandate Law: legal counsel for AI products is a paid MCP server for legal and government. It runs as a hosted remote server, so there is nothing to install locally.

Mandate Law is a legal practice, admitted in DC, that lets a coding agent act as the intake channel. Instead of founders relaying questions to developers and back, the agent answers counsel's questions by reading the codebase and quoting the code, for example whether an agent can spend money without a fresh confirmation, or what user data reaches the model provider and whether it is retained.

The firm splits AI products into three layers: AI features, agents that act for users, and the app around them, covering privacy policies, terms, consent flows and app store rules. Fees are fixed and stated before you engage, nothing is paid up front, and the fee is confirmed in the engagement letter.

Deliverables come in paired forms: final documents such as terms and privacy policies, a privileged memo kept out of the repository, a build spec, a verification checklist and a counsel-triggers file listing changes that need review first. The server is at mandatelaw.ai/mcp, with /llms.txt and a REST API as alternatives.

Install

Run in a terminal

claude mcp add --transport http counsel https://mandatelaw.ai/mcp

Add to Settings → Connectors → Add custom connector

https://mandatelaw.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "counsel": {
      "url": "https://mandatelaw.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "counsel": {
      "serverUrl": "https://mandatelaw.ai/mcp"
    }
  }
}

Add to Grok Bot desktop app → Connect apps → Add a custom connector

https://mandatelaw.ai/mcp

Enter a Name (for example "Mandate Law: legal counsel for AI products"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

Full Grok Bot setup guide

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "counsel": {
      "type": "http",
      "url": "https://mandatelaw.ai/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (9)

Read directly from the server.

check_scope
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.
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.
request_engagement
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
submit_intake
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).
answer_open_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.
feature_check
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.
get_matter
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.
get_counsel_triggers
Free. The template list of product changes that need legal review before shipping.
check_change
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.

What it does

Code-based answers
The agent answers counsel's questions by quoting the code that enforces each behaviour.
Fixed fees
Fees are stated up front and confirmed in the engagement letter.
Paired deliverables
Final documents plus a privileged memo, build spec and checklist.
Verification checklist
Each row tests a statement in the published documents against the shipping build.
Counsel triggers file
A repo file listing changes, such as a new model provider, that need legal review first.

Good for

  • Get a privacy policy that matches what the code does
  • Draft agent authorization terms
  • Review AI disclosures and consent flows
  • Flag code changes that need legal review

Pricing

Paid

Fixed-fee services; prices not published on the page

Prices change. Check mandatelaw.ai before you buy.

Mandate Law: legal counsel for AI products FAQ

How is the work priced?

Fixed fees with a stated turnaround, nothing paid up front; the exact fee is given before you engage.

Why is the memo kept out of the repo?

The site says keeping the privileged memo out of the repository protects privilege.

Is there a non-MCP route?

Yes, the site points agents to /llms.txt and a REST API.

What does the verification checklist do?

Each row tests one statement in the published documents against the build; a failing row means a document says something false.

Is Mandate Law: legal counsel for AI products free?

No. Mandate Law: legal counsel for AI products is a paid product.

How do I add Mandate Law: legal counsel for AI products to Claude Code?

Run this command in your terminal: claude mcp add --transport http counsel https://mandatelaw.ai/mcp

What are the best alternatives to Mandate Law: legal counsel for AI products?

The closest alternatives to Mandate Law: legal counsel for AI products are Pharma, Healthcare, Scope (Legal), Wanhe AI Compliance Checker and Legal HQ: Legal AI Help for Lawsuits.

Where this comes from

  • Description: written from the project's website.
  • Status and tools: checked automatically by AIPoweredBot on 18 November 2026.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers