Drafts a short AI use policy for a small business from eight questions. Free, answers not stored.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Builds a short AI use policy draft in Markdown (ten sections, about two pages) from the answers to get_policy_questions: purpose, scope, approved tools, data rules (what never goes into free or unapproved AI tools), allowed and prohibited uses, human review of AI output, approval of new tools, incident reporting and a review date. It is a fixed template filled with the answers: no AI model is called, there is no network access, and this server does not store or log the answers. Only company_name is required. Every other answer left out becomes a bracketed placeholder in the draft, and the result lists them. Ask the person for the answers, do not invent them. Optional effective_date (YYYY-MM-DD) defaults to today (UTC). The output is a draft for internal use, not legal advice.
What is the company's name?
Which AI tools does the team use or plan to use? Name the product and, if you know it, the plan.
Who approves new AI tools and receives incident reports? A role or a name.
What industry or kind of work is it?
What may people use AI for? One use per entry.
What kinds of non-public data does the team handle? The policy already covers client confidential information, personal data and credentials; add anything else.
Date the policy takes effect, YYYY-MM-DD. Defaults to today (UTC).
How often will the policy be reviewed?
What is off limits beyond the standard rules? One item per entry.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http ai-use-policy https://igdigi.com/mcp/ai-policy
Builds a short AI use policy draft in Markdown (ten sections, about two pages) from the answers to get_policy_questions: purpose, scope, approved tools, data rules (what never goes into free or unapproved AI tools), allowed and prohibited uses, human review of AI output, approval of new tools, incident reporting and a review date. It is a fixed template filled with the answers: no AI model is called, there is no network access, and this server does not store or log the answers. Only company_name is required. Every other answer left out becomes a bracketed placeholder in the draft, and the result lists them. Ask the person for the answers, do not invent them. Optional effective_date (YYYY-MM-DD) defaults to today (UTC). The output is a draft for internal use, not legal advice.
| Argument | Type | Description |
|---|---|---|
| ai_tools | array | Which AI tools does the team use or plan to use? Name the product and, if you know it, the plan. |
| approver | string | Who approves new AI tools and receives incident reports? A role or a name. |
| industry | string | What industry or kind of work is it? |
| allowed_uses | array | What may people use AI for? One use per entry. |
| company_name* | string | What is the company's name? |
| data_handled | array | What kinds of non-public data does the team handle? The policy already covers client confidential information, personal data and credentials; add anything else. |
| effective_date | string | Date the policy takes effect, YYYY-MM-DD. Defaults to today (UTC). |
| review_cadence | string | How often will the policy be reviewed? |
| prohibited_uses | array | What is off limits beyond the standard rules? One item per entry. |
{
"type": "object",
"required": [
"company_name"
],
"properties": {
"ai_tools": {
"type": "array",
"items": {
"type": "string",
"maxLength": 80
},
"maxItems": 15,
"description": "Which AI tools does the team use or plan to use? Name the product and, if you know it, the plan."
},
"approver": {
"type": "string",
"maxLength": 100,
"description": "Who approves new AI tools and receives incident reports? A role or a name."
},
"industry": {
"type": "string",
"maxLength": 100,
"description": "What industry or kind of work is it?"
},
"allowed_uses": {
"type": "array",
"items": {
"type": "string",
"maxLength": 120
},
"maxItems": 10,
"description": "What may people use AI for? One use per entry."
},
"company_name": {
"type": "string",
"maxLength": 100,
"minLength": 1,
"description": "What is the company's name?"
},
"data_handled": {
"type": "array",
"items": {
"type": "string",
"maxLength": 120
},
"maxItems": 12,
"description": "What kinds of non-public data does the team handle? The policy already covers client confidential information, personal data and credentials; add anything else."
},
"effective_date": {
"type": "string",
"pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",
"description": "Date the policy takes effect, YYYY-MM-DD. Defaults to today (UTC)."
},
"review_cadence": {
"enum": [
"every three months",
"every six months",
"once a year"
],
"type": "string",
"description": "How often will the policy be reviewed?"
},
"prohibited_uses": {
"type": "array",
"items": {
"type": "string",
"maxLength": 120
},
"maxItems": 10,
"description": "What is off limits beyond the standard rules? One item per entry."
}
},
"additionalProperties": false
}Returns the short questionnaire behind draft_ai_use_policy: eight questions for a small business (company name, industry, AI tools in use, kinds of data the team handles, allowed uses, prohibited uses, who approves new tools, review cadence). Each question has an id, plain wording, type, limits and an example. Call this first, ask the person the questions, then pass their answers to draft_ai_use_policy. Takes no arguments, makes no network calls, stores nothing.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 8, 2026.