ZCode Image Search MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ZCode Image Search MCPSearch for 5 cute puppy pictures using search_image, count=5, gl=us, rank=true"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ZCode Image Search MCP
在 Claude Code、Codex 或 Pi 中调用 ZCode 的 search_image:搜索现有图片,不生成图片。服务通过本地 stdio 运行,请求转发到 ZCode 搜图接口。
使用前
需要 Node.js ≥ 20,以及可使用搜图服务的 Z.ai 或 BigModel 账号。Pi 本身需要 Node.js ≥ 22.19。
在运行客户端的同一台机器、同一用户环境下完成以下任一项:
已登录 ZCode:服务启动时会尝试读取并同步本地登录凭据;或
在终端单独登录(将
zai换成bigmodel可使用 BigModel):
npx -y @umineko987/zcode-image-search-mcp@latest login zaiRelated MCP server: webfetch
接入客户端
Claude Code
claude mcp add zcode-image-search -- npx -y @umineko987/zcode-image-search-mcp@latest默认仅对当前项目生效;如果希望所有项目可用,在 zcode-image-search 前加 --scope user。
Codex
codex mcp add zcode-image-search -- npx -y @umineko987/zcode-image-search-mcp@latestPi
Pi 需要先安装第三方 pi-mcp-adapter:
pi install npm:pi-mcp-adapter重启 Pi,并在 ~/.config/mcp/mcp.json 中加入以下配置(如已有配置,将 zcode-image-search 合并到现有 mcpServers):
{
"mcpServers": {
"zcode-image-search": {
"command": "npx",
"args": ["-y", "@umineko987/zcode-image-search-mcp@latest"]
}
}
}在 Pi 中运行 /mcp 可查看连接状态。
使用
让客户端调用 search_image,传入 query(关键词)、count(数量)、gl(地区代码,如 us)、rank(是否排序);这四项均为必填。示例:“用 search_image 搜索布偶猫图片,count=3、gl=us、rank=true。”
Available Tools
1 toolsearch_imageSearch ImageB
Search the web for existing images matching a query. Results are not content-moderated.
| Name | Required | Description | Default |
|---|---|---|---|
| gl | Yes | ||
| rank | Yes | ||
| count | Yes | ||
| query | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| query | Yes | |
| ranked | Yes | |
| results | Yes | |
| success | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that results are not content-moderated, which is a meaningful safety trait, but it does not state whether the operation is read-only, what permissions or network access are required, or any rate limits. This is a partial but not comprehensive behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences, front-loads the core purpose, and adds the moderation caveat without waste. Every sentence earns its place given the limited information provided.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has four required parameters with no schema descriptions and no annotations, yet the description explains only the query and a moderation caveat. An output schema exists, so return values need not be explained, but the input semantics and usage context remain largely incomplete for a four-parameter search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for undocumented parameters. It only implies the meaning of 'query' and says nothing about 'count', 'gl', or 'rank', leaving three of four required parameters semantically opaque. The schema provides types only, so this is a significant gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a clear verb and resource: searching the web for images matching a query. There are no sibling tools to distinguish from, so the only gap is that it does not explicitly contrast with other search types. The purpose is nonetheless immediately understandable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says what the tool does but provides no when-to-use guidance, no exclusions, and no alternatives. An agent can infer that it is for image search, but there is no explicit routing information or conditions under which this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
search_image
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of confusion or overlapping purpose with another tool.
The single tool name 'search_image' follows a clear verb_noun pattern, and with only one tool there is no inconsistency to evaluate.
A single tool is borderline thin for an image search server; while search is the core operation, additional tools for filtering, pagination, or image details could reasonably be expected.
The tool covers the primary search operation, but there are minor potential gaps such as result pagination, filtering, or retrieving image details that would enhance completeness.
Maintenance
Related MCP Connectors
Search over 1.85 million captioned images using text, a reference image, or both. Upload a JPEG, PNG, or WebP image as base64, or provide a public HTTPS image URL. Find similar images from a Lightdrift asset ID and retrieve hosted file URLs, source licenses, and attribution. Connect with OAuth or an API key. Searches cost $0.005 ($5 per 1,000); image details are free. Setup: https://docs.lightdrift.ai/guides/images-mcp
Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar
Image Search: Fast and Simple Image Search API. You can get 100+ search results in one query!.
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA search service based on multiple image APIs and icon generation capabilities, specifically designed for integration with Cursor MCP service. Supports image search, download, and AI-generated icons.16MIT
- AlicenseAqualityCmaintenanceLicense-first federated image search for AI agents and humans. Exposes MCP tools for concise, attribution-aware image discovery, license probing, and guarded downloads across open, platform, and editorial sources.75 npm3MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to search, download, and analyze Google images via SerpAPI.35 npm19ISC
- AlicenseBqualityCmaintenanceMCP server for Claude Code that provides Google text search, web content extraction, and image search with dual-platform (Google Images + Pinterest) and AI visual analysis with quality scoring.5MIT