# archive_memory

Archive (soft delete) a memory by ID

Agent View of the PolicyLayer registry record for `archive_memory`. HTML page: https://policylayer.com/tools/0xrelogic-cognio/archive-memory

## Facts

- Tool: `archive_memory`
- Server: Cognio (`0xrelogic/cognio`) — https://policylayer.com/tools/0xrelogic-cognio.md
- Homepage: https://github.com/0xReLogic/Cognio
- Risk category: Write (Medium risk)
- Registry record: grade D, 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": "archive_memory",
    "arguments": {}
  }
}
```

## Why archive_memory is rated Medium

Although archiving removes a memory from active use, it is classified as Write rather than Destructive because soft deletion is inherently reversible—the data persists and can typically be restored.

From the tool's own definition: "Tool name 'archive_memory' and description 'Archive (soft delete) a memory by ID' indicate a reversible modification of memory state."

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on Cognio (11)

- `delete_memory` — Destructive — https://policylayer.com/tools/0xrelogic-cognio/delete-memory.md
- `export_memories` — Read — https://policylayer.com/tools/0xrelogic-cognio/export-memories.md
- `get_active_project` — Read — https://policylayer.com/tools/0xrelogic-cognio/get-active-project.md
- `get_memory` — Read — https://policylayer.com/tools/0xrelogic-cognio/get-memory.md
- `get_memory_stats` — Read — https://policylayer.com/tools/0xrelogic-cognio/get-memory-stats.md
- `list_memories` — Read — https://policylayer.com/tools/0xrelogic-cognio/list-memories.md
- `list_projects` — Read — https://policylayer.com/tools/0xrelogic-cognio/list-projects.md
- `search_memory` — Read — https://policylayer.com/tools/0xrelogic-cognio/search-memory.md
- `summarize_text` — Read — https://policylayer.com/tools/0xrelogic-cognio/summarize-text.md
- `save_memory` — Write — https://policylayer.com/tools/0xrelogic-cognio/save-memory.md
- `set_active_project` — Write — https://policylayer.com/tools/0xrelogic-cognio/set-active-project.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=0xrelogic-cognio · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0xrelogic-cognio