# get_recent_tool_calls

Get recent tool call history with their arguments and outputs. Returns chronological list of tool calls made during this session. Useful for: - Onboarding new chats about work already done - Recovering context after chat history loss - Debugging tool call sequences Note: Does not track its own calls or other meta/query tools. History kept in memory (last 1000 calls, lost on restart). ${CMD_PREFIX_DESCRIPTION}

Agent View of the PolicyLayer registry record for `get_recent_tool_calls`. HTML page: https://policylayer.com/tools/desktop-commander/get-recent-tool-calls

## Facts

- Tool: `get_recent_tool_calls`
- Server: Desktop Commander (`wonderwhy-er/DesktopCommanderMCP`) — https://policylayer.com/tools/desktop-commander.md
- Homepage: https://github.com/wonderwhy-er/DesktopCommanderMCP
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- 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_recent_tool_calls",
    "arguments": {}
  }
}
```

## Why get_recent_tool_calls is rated Low

This tool retrieves historical information about prior tool invocations. While it provides access to potentially sensitive information (arguments and outputs from previous tool calls, which may contain file paths, configuration values, or other sensitive data), it is fundamentally a read-only query operation.

From the tool's own definition: "Tool description states it 'Get[s] recent tool call history' and 'Returns chronological list of tool calls made during this session.' These are data retrieval operations with no modification or side effects."

## Use case

AI agents call get_recent_tool_calls to retrieve information from Desktop Commander 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 Desktop Commander:

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

## Other tools on Desktop Commander (10)

- `force_terminate` — Destructive — https://policylayer.com/tools/desktop-commander/force-terminate.md
- `get_config` — Read — https://policylayer.com/tools/desktop-commander/get-config.md
- `get_file_info` — Read — https://policylayer.com/tools/desktop-commander/get-file-info.md
- `get_usage_stats` — Read — https://policylayer.com/tools/desktop-commander/get-usage-stats.md
- `kill_process` — Read — https://policylayer.com/tools/desktop-commander/kill-process.md
- `list_processes` — Read — https://policylayer.com/tools/desktop-commander/list-processes.md
- `list_searches` — Read — https://policylayer.com/tools/desktop-commander/list-searches.md
- `create_directory` — Write — https://policylayer.com/tools/desktop-commander/create-directory.md
- `move_file` — Write — https://policylayer.com/tools/desktop-commander/move-file.md
- `set_config_value` — Write — https://policylayer.com/tools/desktop-commander/set-config-value.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=desktop-commander · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/desktop-commander