# update_entity

Update an entity in the knowledge graph

Agent View of the PolicyLayer registry record for `update_entity`. HTML page: https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/update-entity

## Facts

- Tool: `update_entity`
- Server: Daniel LightRAG MCP Server (`desimpkins/daniel-lightrag-mcp`) — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp.md
- Homepage: https://github.com/desimpkins/daniel-lightrag-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, 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": "update_entity",
    "arguments": {}
  }
}
```

## Why update_entity is rated Medium

The tool modifies an entity within the knowledge graph, which is a Write operation (creates or modifies data reversibly). The severity is medium because incorrect updates could corrupt or mislead knowledge graph data, but the operation is reversible and does not delete or irreversibly overwrite data. It is not Destructive (no deletion), not Execute (no arbitrary code execution), not Financial, and not Read-only.

From the tool's own definition: "Tool name is 'update_entity' and description states 'Update an entity in the knowledge graph'. Update is a reversible modification operation that changes existing data."

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on Daniel LightRAG MCP Server (20)

- `delete_document` — Destructive — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/delete-document.md
- `delete_entity` — Destructive — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/delete-entity.md
- `delete_relation` — Destructive — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/delete-relation.md
- `check_entity_exists` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/check-entity-exists.md
- `get_document_status_counts` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/get-document-status-counts.md
- `get_documents` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/get-documents.md
- `get_documents_paginated` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/get-documents-paginated.md
- `get_graph_labels` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/get-graph-labels.md
- `get_health` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/get-health.md
- `get_knowledge_graph` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/get-knowledge-graph.md
- `get_pipeline_status` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/get-pipeline-status.md
- `get_track_status` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/get-track-status.md
- `hello` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/hello.md
- `query_text` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/query-text.md
- `query_text_stream` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/query-text-stream.md
- `scan_documents` — Read — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/scan-documents.md
- `insert_text` — Write — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/insert-text.md
- `insert_texts` — Write — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/insert-texts.md
- `update_relation` — Write — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/update-relation.md
- `upload_document` — Write — https://policylayer.com/tools/desimpkins-daniel-lightrag-mcp/upload-document.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=desimpkins-daniel-lightrag-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/desimpkins-daniel-lightrag-mcp