# remove_concept

Soft-delete a concept from the knowledge graph. The concept and its removal reason are preserved in history.

Agent View of the PolicyLayer registry record for `remove_concept`. HTML page: https://policylayer.com/tools/0xk3vin-megamemory/remove-concept

## Facts

- Tool: `remove_concept`
- Server: MegaMemory (`0xk3vin/megamemory`) — https://policylayer.com/tools/0xk3vin-megamemory.md
- Homepage: https://github.com/0xK3vin/MegaMemory
- Risk category: Destructive (Critical risk)
- Registry record: grade D, 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": "remove_concept",
    "arguments": {}
  }
}
```

## Why remove_concept is rated Critical

This tool modifies the accessible state of the knowledge graph in an irreversible manner (within the active graph scope). Even though historical preservation exists, the concept is deleted from active use—an agent cannot recover it for ongoing reasoning without explicit recovery actions.

From the tool's own definition: "Tool name 'remove_concept' and description 'Soft-delete a concept from the knowledge graph' indicates deletion of data."

## Use case

AI agents call remove_concept to permanently remove resources in MegaMemory, 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 MegaMemory:

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

## Other tools on MegaMemory (8)

- `get_concept` — Read — https://policylayer.com/tools/0xk3vin-megamemory/get-concept.md
- `list_conflicts` — Read — https://policylayer.com/tools/0xk3vin-megamemory/list-conflicts.md
- `list_roots` — Read — https://policylayer.com/tools/0xk3vin-megamemory/list-roots.md
- `understand` — Read — https://policylayer.com/tools/0xk3vin-megamemory/understand.md
- `create_concept` — Write — https://policylayer.com/tools/0xk3vin-megamemory/create-concept.md
- `link` — Write — https://policylayer.com/tools/0xk3vin-megamemory/link.md
- `resolve_conflict` — Write — https://policylayer.com/tools/0xk3vin-megamemory/resolve-conflict.md
- `update_concept` — Write — https://policylayer.com/tools/0xk3vin-megamemory/update-concept.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=0xk3vin-megamemory · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0xk3vin-megamemory