# query_natural_language

Decompose a natural language query into a structured search plan and return matching entities

Agent View of the PolicyLayer registry record for `query_natural_language`. HTML page: https://policylayer.com/tools/danielsimonjr-memory-mcp/query-natural-language

## Facts

- Tool: `query_natural_language`
- Server: Enhanced Knowledge Graph Memory Server (`danielsimonjr/memory-mcp`) — https://policylayer.com/tools/danielsimonjr-memory-mcp.md
- Homepage: https://github.com/danielsimonjr/memory-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, 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": "query_natural_language",
    "arguments": {}
  }
}
```

## Why query_natural_language is rated Low

This tool performs data retrieval and querying operations only. It decomposes natural language input into search parameters and returns matching entities from the knowledge graph—a read-only operation with no side effects, data modification, code execution, or destructive capabilities. The low severity reflects that misuse would only expose existing data without enabling unauthorized changes or actions.

From the tool's own definition: "Tool name 'query_natural_language' and description 'Decompose a natural language query into a structured search plan and return matching entities' indicate retrieval and search operations with no modification, deletion, or execution capabilities."

## Use case

AI agents call query_natural_language to retrieve information from Enhanced Knowledge Graph Memory Server 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 Enhanced Knowledge Graph Memory Server:

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

## Other tools on Enhanced Knowledge Graph Memory Server (224)

- `adaptive_reduce_memories` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/adaptive-reduce-memories.md
- `cache_clear` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/cache-clear.md
- `clear_expired_memories` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/clear-expired-memories.md
- `clear_heuristics` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/clear-heuristics.md
- `clear_project_context` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/clear-project-context.md
- `delete_entities` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/delete-entities.md
- `delete_observations` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/delete-observations.md
- `delete_relations` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/delete-relations.md
- `delete_saved_search` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/delete-saved-search.md
- `deregister_ref` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/deregister-ref.md
- `forget_memory` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/forget-memory.md
- `forget_weak_memories` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/forget-weak-memories.md
- `invalidate_entity` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/invalidate-entity.md
- `rbac_revoke_role` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/rbac-revoke-role.md
- `remove_exclusion_rule` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/remove-exclusion-rule.md
- `remove_heuristic` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/remove-heuristic.md
- `remove_project_command` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/remove-project-command.md
- `remove_project_convention` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/remove-project-convention.md
- `remove_project_fact` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/remove-project-fact.md
- `remove_project_glossary_term` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/remove-project-glossary-term.md
- `remove_tag_alias` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/remove-tag-alias.md
- `remove_tool_affordance` — Destructive — https://policylayer.com/tools/danielsimonjr-memory-mcp/remove-tool-affordance.md
- `consolidate_session` — Execute — https://policylayer.com/tools/danielsimonjr-memory-mcp/consolidate-session.md
- `dream_run_now` — Execute — https://policylayer.com/tools/danielsimonjr-memory-mcp/dream-run-now.md
- `dream_start` — Execute — https://policylayer.com/tools/danielsimonjr-memory-mcp/dream-start.md
- `dream_stop` — Execute — https://policylayer.com/tools/danielsimonjr-memory-mcp/dream-stop.md
- `end_session` — Execute — https://policylayer.com/tools/danielsimonjr-memory-mcp/end-session.md
- `parse_adr_markdown` — Execute — https://policylayer.com/tools/danielsimonjr-memory-mcp/parse-adr-markdown.md
- `run_consolidation_now` — Execute — https://policylayer.com/tools/danielsimonjr-memory-mcp/run-consolidation-now.md
- `run_decay_cycle` — Execute — https://policylayer.com/tools/danielsimonjr-memory-mcp/run-decay-cycle.md
- …and 194 more: https://policylayer.com/tools/danielsimonjr-memory-mcp.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=danielsimonjr-memory-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/danielsimonjr-memory-mcp