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., "@MCP Feedback Enhanced collect feedback on my new UI design with image uploads"
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.
感谢f的反馈项目，本版本修复了以下问题并新增功能：
超时设置问题：修复了超时时间永远是 600s 的问题，现已修复默认 24 小时超时 ，可以长时间等待反馈啦
图片上传问题：修复了无法上传图片报错序列号错误的问题，现已支持更多类型图 片 😁🎉
断网重连功能：新增断网不断链接功能，现在可以离线同一个会话等待（适合使用 手机热点为电脑提供互联网的场景）
Fork 本项目到本地，在 Cursor 中配置：
{
"mcpServers": {
"mcp-shouji-local": {
"command": "uv",
"args": [
"run",
"--directory",
"C:\\Users\\Administrator\\Desktop\\project\\mcp-shouji-main",
"python",
"-m",
"mcp_shouji"
],
"timeout": 86400,
"env": {
"MCP_DEBUG": "false",
"MCP_WEB_HOST": "127.0.0.1",
"MCP_WEB_PORT": "8765",
"MCP_DESKTOP_MODE": "false",
"MCP_LANGUAGE": "zh-CN"
},
"autoApprove": ["interactive_feedback"]
}
}
}注意：请将
"C:\\Users\\Administrator\\Desktop\\project\\mcp-shouji-main"改 为您本地的项目位置，这样可以实现本地高自由度的定制。
獲取系統環境資訊
Returns: str: JSON 格式的系統資訊
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the return format ('JSON 格式的系統資訊'), which adds some value, but fails to describe other traits like whether it's read-only, has side effects, requires permissions, or has rate limits. This is inadequate for a tool with zero annotation coverage.
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 concise with two sentences: one stating the purpose and another specifying the return format. It's front-loaded and wastes no words, though it could be slightly more structured for clarity.
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?
Given the tool's complexity (simple read operation with 0 parameters), an output schema exists, and schema coverage is high, the description is somewhat complete. However, it lacks behavioral context and usage guidelines, making it only minimally adequate for the agent's needs.
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?
The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the inputs. The description doesn't need to add parameter details, and it appropriately avoids redundancy. A baseline of 4 is applied since no parameters exist.
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 clearly states the tool's purpose with '獲取系統環境資訊' (get system environment information), which is a specific verb+resource combination. However, it doesn't differentiate from the sibling tool 'shouji', which might have overlapping functionality, preventing a perfect score.
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 provides no guidance on when to use this tool versus alternatives like the sibling 'shouji'. It lacks context about specific scenarios, prerequisites, or exclusions, leaving the agent with minimal usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
通过 Web 界面收集用户输入。
提供一个交互式界面，用于获取用户的文字输入和图片附件。 当需要用户确认或额外指导时可调用此工具。
Args: project_directory: 项目目录路径，用于上下文定位 summary: 当前工作的摘要说明，供用户参考 timeout: 等待用户输入的超时时间（秒）
Returns: list: 用户输入内容，包含文字和可选的图片
| Name | Required | Description | Default |
|---|---|---|---|
| project_directory | No | 项目目录路径 | . |
| summary | No | 工作摘要说明 | 任务已完成，请查看。 |
| timeout | No | 等待超时时间（秒），可通过 MCP_DEFAULT_TIMEOUT 环境变量设定 |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the interactive nature ('交互式界面'), input types (text and images), and timeout behavior. However, it doesn't disclose important behavioral aspects like whether this blocks execution, what happens on timeout, authentication requirements, rate limits, or error conditions. The description adds value but leaves significant gaps for a tool that creates user interfaces.
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 well-structured with purpose first, then usage guidelines, followed by parameter and return value sections. It's appropriately sized for the tool's complexity. The only minor inefficiency is repeating parameter names that are already documented in the schema, but overall it's concise and front-loaded with essential information.
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?
Given the tool's interactive nature and 3 parameters with 100% schema coverage plus an output schema, the description provides reasonable completeness. It explains what the tool does, when to use it, and what it returns. The main gap is insufficient behavioral transparency for a UI tool, but with output schema handling return values, the description covers most essential aspects adequately.
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 100%, so the schema already documents all three parameters thoroughly. The description lists the parameters but adds minimal semantic value beyond what's in the schema. It mentions '用于上下文定位' (for context positioning) for project_directory and '供用户参考' (for user reference) for summary, which provides slight additional context. This meets the baseline for high schema coverage.
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 clearly states the tool's purpose: '通过 Web 界面收集用户输入' (collect user input through a web interface) and specifies it's for '获取用户的文字输入和图片附件' (obtaining user text input and image attachments). It distinguishes from the sibling tool 'get_system_info' by focusing on user input collection rather than system information retrieval. However, it doesn't explicitly contrast with the sibling tool in the description text itself.
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 provides clear context for when to use the tool: '当需要用户确认或额外指导时可调用此工具' (can be called when user confirmation or additional guidance is needed). This gives practical guidance about appropriate use cases. However, it doesn't specify when NOT to use it or mention explicit alternatives beyond the implied distinction from the sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0interactive_feedbackshoujiget_system_infointeractive_feedbackScored across 2 tools
The two tools have clearly distinct purposes: get_system_info retrieves system environment information, while shouji provides an interactive web interface for collecting user input and attachments. There is no overlap in functionality, making it easy for an agent to choose the correct tool for each task.
The naming is inconsistent: get_system_info follows a clear verb_noun pattern, but shouji uses a non-English term (Chinese for 'collect') without a descriptive verb, breaking the pattern. This mix of conventions could confuse agents expecting a uniform naming style.
With only 2 tools, the server feels thin for a general-purpose feedback system, as it lacks tools for processing, analyzing, or managing feedback beyond collection. However, the count is borderline appropriate if the scope is limited to basic input gathering and system info retrieval.
For a feedback-enhanced server, there are significant gaps: it provides input collection and system info but lacks tools for storing, retrieving, analyzing, or responding to feedback. This incomplete surface will likely cause agent failures when trying to handle feedback workflows beyond simple input capture.
Human feedback for AI agents: share HTML, get a live review link, read anchored notes as markdown.
Comment on AI-generated webpages; feedback flows back to your coding agent. Free, MIT, local-first.
Build, version, review, and export websites, web apps, and games from a conversation.
X feedback discovery, noise-reduced query planning, signal filtering, and AI handoffs.
