# edit

A write tool on the TeXFlow MCP server.

Agent View of the PolicyLayer registry record for `edit`. HTML page: https://policylayer.com/tools/aaronsb-texflow-mcp/edit

## Facts

- Tool: `edit`
- Server: TeXFlow (`aaronsb/texflow-mcp`) — https://policylayer.com/tools/aaronsb-texflow-mcp.md
- Homepage: https://github.com/aaronsb/texflow-mcp
- Risk category: Write (Medium risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why edit is rated Medium

The 'edit' tool is invoked on a platform designed for document composition and collaborative authoring. Given the server's focus on transforming Markdown/LaTeX into PDFs, this tool almost certainly modifies document content reversibly (Write category). An agent misusing edit could corrupt documents or inject malicious content into shared projects, hence medium severity.

From the tool's own definition: "Tool named 'edit' on a document authoring server (TeXFlow) with sibling tools including 'document', 'render', and 'reference'. The server explicitly supports 'collaborative document authoring' and 'multi-agent editing'. Empty description limits certainty."

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on TeXFlow (5)

- `render` — Execute — https://policylayer.com/tools/aaronsb-texflow-mcp/render.md
- `document` — Other — https://policylayer.com/tools/aaronsb-texflow-mcp/document.md
- `queue` — Other — https://policylayer.com/tools/aaronsb-texflow-mcp/queue.md
- `reference` — Other — https://policylayer.com/tools/aaronsb-texflow-mcp/reference.md
- `layout` — Write — https://policylayer.com/tools/aaronsb-texflow-mcp/layout.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=aaronsb-texflow-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/aaronsb-texflow-mcp