# query_rag

Query the elite RAG system with multi-layer retrieval

Agent View of the PolicyLayer registry record for `query_rag`. HTML page: https://policylayer.com/tools/aegntic-aegntic-mcp/query-rag

## Facts

- Tool: `query_rag`
- Server: Obsidian Elite RAG MCP Server (`aegntic/aegntic-mcp`) — https://policylayer.com/tools/aegntic-aegntic-mcp.md
- Homepage: https://github.com/aegntic/aegntic-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_rag",
    "arguments": {}
  }
}
```

## Why query_rag is rated Low

This tool performs semantic search and retrieval across an Obsidian vault knowledge base. While it retrieves potentially sensitive personal notes and knowledge graph data, it does not create, modify, delete, or execute arbitrary operations. The primary function is querying existing data.

From the tool's own definition: "Tool name 'query_rag' combined with description 'Query the elite RAG system with multi-layer retrieval' indicates data retrieval without modification."

## Use case

AI agents call query_rag to retrieve information from Obsidian Elite RAG MCP 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 Obsidian Elite RAG MCP Server:

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

## Other tools on Obsidian Elite RAG MCP Server (134)

- `clear_all_datasets` — Destructive — https://policylayer.com/tools/aegntic-aegntic-mcp/clear-all-datasets.md
- `clear_dataset` — Destructive — https://policylayer.com/tools/aegntic-aegntic-mcp/clear-dataset.md
- `clear_expired_context_cache` — Destructive — https://policylayer.com/tools/aegntic-aegntic-mcp/clear-expired-context-cache.md
- `clear_graph` — Destructive — https://policylayer.com/tools/aegntic-aegntic-mcp/clear-graph.md
- `delete_entity_edge` — Destructive — https://policylayer.com/tools/aegntic-aegntic-mcp/delete-entity-edge.md
- `delete_episode` — Destructive — https://policylayer.com/tools/aegntic-aegntic-mcp/delete-episode.md
- `n8n_delete_execution` — Destructive — https://policylayer.com/tools/aegntic-aegntic-mcp/n8n-delete-execution.md
- `n8n_delete_workflow` — Destructive — https://policylayer.com/tools/aegntic-aegntic-mcp/n8n-delete-workflow.md
- `achieve_mouse_authenticity` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/achieve-mouse-authenticity.md
- `achieve_typing_authenticity` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/achieve-typing-authenticity.md
- `collaborate_with_gemini` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/collaborate-with-gemini.md
- `compile_video` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/compile-video.md
- `execute_custom_analytics_code` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/execute-custom-analytics-code.md
- `n8n_trigger_webhook_workflow` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/n8n-trigger-webhook-workflow.md
- `run_performance_benchmark` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/run-performance-benchmark.md
- `run_test_audience` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/run-test-audience.md
- `start_capture` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/start-capture.md
- `stop_capture` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/stop-capture.md
- `validate_authenticity` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/validate-authenticity.md
- `validate_workflow` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/validate-workflow.md
- `validate_workflow_expressions` — Execute — https://policylayer.com/tools/aegntic-aegntic-mcp/validate-workflow-expressions.md
- `subscribe_tier` — Financial — https://policylayer.com/tools/aegntic-aegntic-mcp/subscribe-tier.md
- `join_community` — Other — https://policylayer.com/tools/aegntic-aegntic-mcp/join-community.md
- `sequential_thinking` — Other — https://policylayer.com/tools/aegntic-aegntic-mcp/sequential-thinking.md
- `analyze_brand_performance` — Read — https://policylayer.com/tools/aegntic-aegntic-mcp/analyze-brand-performance.md
- `analyze_distributions` — Read — https://policylayer.com/tools/aegntic-aegntic-mcp/analyze-distributions.md
- `analyze_project` — Read — https://policylayer.com/tools/aegntic-aegntic-mcp/analyze-project.md
- `calculate_feature_importance` — Read — https://policylayer.com/tools/aegntic-aegntic-mcp/calculate-feature-importance.md
- `compare_datasets` — Read — https://policylayer.com/tools/aegntic-aegntic-mcp/compare-datasets.md
- `crawl_single_page` — Read — https://policylayer.com/tools/aegntic-aegntic-mcp/crawl-single-page.md
- …and 104 more: https://policylayer.com/tools/aegntic-aegntic-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=aegntic-aegntic-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/aegntic-aegntic-mcp