# reset_conversation

Delete stored in-memory chat history for a

Agent View of the PolicyLayer registry record for `reset_conversation`. HTML page: https://policylayer.com/tools/deepseek-mcp-server/reset-conversation

## Facts

- Tool: `reset_conversation`
- Server: DeepSeek MCP Server (`deepseek-mcp-server`) — https://policylayer.com/tools/deepseek-mcp-server.md
- Install: `npx -y deepseek-mcp-server`
- Homepage: https://github.com/DMontgomery40/deepseek-mcp-server
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Hidden

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

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

## Why reset_conversation is rated Critical

This tool permanently removes conversation history, which cannot be recovered. While the blast radius is limited to conversation metadata rather than user data or financial systems, the irreversible nature of deletion places it in the Destructive category rather than Write. Severity is high because an agent could maliciously erase user conversations, though the impact is contained to that specific resource.

From the tool's own definition: "Tool name is 'reset_conversation' and description states 'Delete stored in-memory chat history' — the verb 'Delete' combined with 'chat history' indicates irreversible removal of data."

## Use case

AI agents call reset_conversation to permanently remove resources in DeepSeek MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "reset_conversation"
  ]
}
```

## Other tools on DeepSeek MCP Server (6)

- `chat_completion` — Execute — https://policylayer.com/tools/deepseek-mcp-server/chat-completion.md
- `completion` — Execute — https://policylayer.com/tools/deepseek-mcp-server/completion.md
- `create_response` — Execute — https://policylayer.com/tools/deepseek-mcp-server/create-response.md
- `get_user_balance` — Read — https://policylayer.com/tools/deepseek-mcp-server/get-user-balance.md
- `list_conversations` — Read — https://policylayer.com/tools/deepseek-mcp-server/list-conversations.md
- `list_models` — Read — https://policylayer.com/tools/deepseek-mcp-server/list-models.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=deepseek-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deepseek-mcp-server