# understand

Query the project knowledge graph. Call this before starting any task to load relevant context about concepts, features, and architecture. Returns matched concepts with their children, edges, and parent context.

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

## Facts

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

## Why understand is rated Low

The `understand` tool retrieves and queries existing data from a persistent knowledge graph without creating, modifying, deleting, or executing external operations. It is explicitly described as loading context for tasks, which is a classic Read operation. No destructive, financial, or code-execution semantics are present.

From the tool's own definition: "Tool description states 'Query the project knowledge graph' and 'Returns matched concepts' — pure data retrieval with no modification or side effects. The verb 'Query' and the mechanism of returning context confirms read-only access."

## Use case

AI agents call understand to retrieve information from MegaMemory 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 MegaMemory:

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

## Other tools on MegaMemory (8)

- `remove_concept` — Destructive — https://policylayer.com/tools/0xk3vin-megamemory/remove-concept.md
- `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
- `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