# generate_manifest_draft

Generate a first-draft agent manifest (CLAUDE.md / AGENTS.md / GEMINI.md) grounded in the repository README and description. Uses your ANTHROPIC_API_KEY. Claims the model cannot ground are marked as TODO comments.

Agent View of the PolicyLayer registry record for `generate_manifest_draft`. HTML page: https://policylayer.com/tools/ai-clarx-mcp/generate-manifest-draft

## Facts

- Tool: `generate_manifest_draft`
- Server: Mcp (`@clarxai/mcp`) — https://policylayer.com/tools/ai-clarx-mcp.md
- Install: `npx -y @clarxai/mcp`
- Homepage: https://github.com/Gernika-Labs/clarx-cloud
- Risk category: Write (Medium risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 4 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `filename` | string | yes | Manifest filename to draft. |
| `repo_name` | string | no |  |
| `repo_readme` | string | no | README content for grounding (max ~6000 chars used). Required unless repo_description is present. |
| `repo_description` | string | null | no |  |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "generate_manifest_draft",
    "arguments": {
      "filename": "<filename>"
    }
  }
}
```

## Why generate_manifest_draft is rated Medium

The tool creates or generates new manifest files (CLAUDE.md, AGENTS.md, GEMINI.md) based on repository metadata. This is a reversible Write operation—generated drafts can be edited, deleted, or replaced. It does not execute code, delete data, move money, or trigger external operations with uncontrolled side effects.

From the tool's own definition: "Tool 'generates' a 'first-draft' manifest file with 'TODO comments', explicitly creating new structured content in a repository without destructive overwrite semantics."

Risk signals: Accepts file system path (filename)

## Use case

AI agents use generate_manifest_draft to create or update resources in Mcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Mcp:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_manifest_draft": {
      "limits": [
        {
          "counter": "generate_manifest_draft_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Mcp (4)

- `analyze_clarx_manifest` — Read — https://policylayer.com/tools/ai-clarx-mcp/analyze-clarx-manifest.md
- `analyze_manifest` — Read — https://policylayer.com/tools/ai-clarx-mcp/analyze-manifest.md
- `get_ci_workflow` — Write — https://policylayer.com/tools/ai-clarx-mcp/get-ci-workflow.md
- `suggest_manifest_fix` — Write — https://policylayer.com/tools/ai-clarx-mcp/suggest-manifest-fix.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=ai-clarx-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/ai-clarx-mcp