# get_current_focus

Frank's active direction / roadmap — what he is building toward right now.

Agent View of the PolicyLayer registry record for `get_current_focus`. HTML page: https://policylayer.com/tools/com-frankponcelet-profile/get-current-focus

## Facts

- Tool: `get_current_focus`
- Server: Profile (`https://frankponcelet.com/api/mcp`) — https://policylayer.com/tools/com-frankponcelet-profile.md
- Homepage: https://github.com/FrankNFT-labs/Portifolio
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_current_focus",
    "arguments": {}
  }
}
```

## Why get_current_focus is rated Low

This tool retrieves and returns information about Frank Poncelet's active direction and roadmap. It performs no modifications, deletions, executions, or financial operations. The server is explicitly read-only, and all sibling tools follow a consistent 'get_*' retrieval pattern. The blast radius of misuse is minimal—an AI agent would only receive information already exposed by the server owner.

From the tool's own definition: "Tool name is 'get_current_focus' (get-prefixed retrieval). Server description explicitly states 'Read-only MCP server' and lists only retrieval operations (get_*). The tool queries Frank's current focus and roadmap — information retrieval with no side effects."

## Use case

AI agents call get_current_focus to retrieve information from Profile without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_current_focus": {}
  }
}
```

## Other tools on Profile (8)

- `get_career` — Read — https://policylayer.com/tools/com-frankponcelet-profile/get-career.md
- `get_engagement` — Read — https://policylayer.com/tools/com-frankponcelet-profile/get-engagement.md
- `get_expertise` — Read — https://policylayer.com/tools/com-frankponcelet-profile/get-expertise.md
- `get_persona` — Read — https://policylayer.com/tools/com-frankponcelet-profile/get-persona.md
- `get_profile` — Read — https://policylayer.com/tools/com-frankponcelet-profile/get-profile.md
- `get_projects` — Read — https://policylayer.com/tools/com-frankponcelet-profile/get-projects.md
- `get_speaking` — Read — https://policylayer.com/tools/com-frankponcelet-profile/get-speaking.md
- `list_articles` — Read — https://policylayer.com/tools/com-frankponcelet-profile/list-articles.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=com-frankponcelet-profile · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-frankponcelet-profile