# read_image

Analyze an image using GLM-4.5V model

Agent View of the PolicyLayer registry record for `read_image`. HTML page: https://policylayer.com/tools/2234839-mcpserver/read-image

## Facts

- Tool: `read_image`
- Server: Martin MCP Toolbox (`2234839/mcpserver`) — https://policylayer.com/tools/2234839-mcpserver.md
- Homepage: https://github.com/2234839/mcpserver
- Risk category: Read (Low risk)
- Registry record: grade C, 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": "read_image",
    "arguments": {}
  }
}
```

## Why read_image is rated Low

This tool retrieves and processes image data through a vision model to extract information. It performs analysis only, with no capability to modify, delete, execute code, or affect external systems. This is a classic Read operation with minimal risk even if misused—the worst outcome is extracting unintended information from an image.

From the tool's own definition: "Tool name is 'read_image' and description states it 'Analyze an image using GLM-4.5V model'. The verb 'analyze' indicates data retrieval and inspection with no side effects or modifications."

## Use case

AI agents call read_image to retrieve information from Martin MCP Toolbox 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 Martin MCP Toolbox:

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

## Other tools on Martin MCP Toolbox (13)

- `pollinations_generate_text` — Execute — https://policylayer.com/tools/2234839-mcpserver/pollinations-generate-text.md
- `siyuan_query_sql` — Execute — https://policylayer.com/tools/2234839-mcpserver/siyuan-query-sql.md
- `advanced_web_search` — Read — https://policylayer.com/tools/2234839-mcpserver/advanced-web-search.md
- `analyze_video` — Read — https://policylayer.com/tools/2234839-mcpserver/analyze-video.md
- `get_block_kramdown` — Read — https://policylayer.com/tools/2234839-mcpserver/get-block-kramdown.md
- `pollinations_analyze_image` — Read — https://policylayer.com/tools/2234839-mcpserver/pollinations-analyze-image.md
- `siyuan_database_query` — Read — https://policylayer.com/tools/2234839-mcpserver/siyuan-database-query.md
- `siyuan_search_blocks` — Read — https://policylayer.com/tools/2234839-mcpserver/siyuan-search-blocks.md
- `web_search` — Read — https://policylayer.com/tools/2234839-mcpserver/web-search.md
- `generate_image` — Write — https://policylayer.com/tools/2234839-mcpserver/generate-image.md
- `pollinations_generate_audio` — Write — https://policylayer.com/tools/2234839-mcpserver/pollinations-generate-audio.md
- `pollinations_generate_image` — Write — https://policylayer.com/tools/2234839-mcpserver/pollinations-generate-image.md
- `update_block` — Write — https://policylayer.com/tools/2234839-mcpserver/update-block.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=2234839-mcpserver · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/2234839-mcpserver