# context_forget

Forget stored memories that are no longer true or wanted. USE WHEN: the user says

Agent View of the PolicyLayer registry record for `context_forget`. HTML page: https://policylayer.com/tools/100xprompt-chitta/context-forget

## Facts

- Tool: `context_forget`
- Server: Chitta (`@100xprompt/chitta`) — https://policylayer.com/tools/100xprompt-chitta.md
- Install: `npx -y @100xprompt/chitta`
- Homepage: https://www.npmjs.com/package/@100xprompt/chitta
- Risk category: Destructive (Critical risk)
- Registry record: grade B, 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": "context_forget",
    "arguments": {}
  }
}
```

## Why context_forget is rated Critical

Forgetting memories implies irreversible deletion of stored data from the knowledge graph and vector memory. There is no indication of a recovery or undo mechanism. Misuse by an AI agent could cause permanent loss of user context, knowledge, or memory entries, making this Destructive with high severity.

From the tool's own definition: "'Forget stored memories that are no longer true or wanted' — permanently removes stored memory entries from the knowledge-graph/vector memory store"

## Use case

AI agents call context_forget to permanently remove resources in Chitta, 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 Chitta:

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

## Other tools on Chitta (10)

- `context_rebuild` — Execute — https://policylayer.com/tools/100xprompt-chitta/context-rebuild.md
- `context_about` — Read — https://policylayer.com/tools/100xprompt-chitta/context-about.md
- `context_graph` — Read — https://policylayer.com/tools/100xprompt-chitta/context-graph.md
- `context_health` — Read — https://policylayer.com/tools/100xprompt-chitta/context-health.md
- `context_profile` — Read — https://policylayer.com/tools/100xprompt-chitta/context-profile.md
- `context_reflect` — Read — https://policylayer.com/tools/100xprompt-chitta/context-reflect.md
- `context_relate` — Read — https://policylayer.com/tools/100xprompt-chitta/context-relate.md
- `context_timeline` — Read — https://policylayer.com/tools/100xprompt-chitta/context-timeline.md
- `get_context` — Read — https://policylayer.com/tools/100xprompt-chitta/get-context.md
- `context_ingest` — Write — https://policylayer.com/tools/100xprompt-chitta/context-ingest.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=100xprompt-chitta · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/100xprompt-chitta