In Visual Novels und Galgames ist ein "Flag" (フラグ) der Moment, in dem eine Entscheidung einen neuen Handlungsstrang auslöst. Eine Entscheidung ändert alles.
Flag MCP bringt dieselbe Kraft in das KI-gestützte Programmieren. Wenn dein KI-Assistent an eine Weggabelung kommt, rät er nicht — er setzt eine Flagge und wartet darauf, dass du die Route wählst.
🎮 Du bist der Protagonist. Die KI wartet an jedem Verzweigungspunkt.
💎 Jede Flagge bestimmt die Route. Keine spekulativen Umschreibungen mehr.
🚀 Reiche Interaktion. Text, Screenshots, Anmerkungen — dein volles Arsenal.
Dies verwandelt KI-Programmierung von "Hoffentlich funktioniert es" in eine Erzählung, bei der du den Controller in der Hand hältst.
Anwendungsbereich:
Coding-Pläne, die pro Anfrage abgerechnet werden.
Entwickler, die das KI-Verhalten kontrollieren möchten.
Related MCP server: Human-In-the-Loop MCP Server
❌ Ohne Flag MCP | ✅ Mit Flag MCP |
KI rät → falscher Code → mühsame Nacharbeit | KI setzt Flagge → du wählst → korrekter Code |
Mehrere Runden von "Warte, was meintest du?" | Ein strukturierter Dialog, glasklar |
Ängstlich: "Was macht die KI als Nächstes?!" | Zuversichtlich: jede Aktion von dir bestätigt |
Hilfloser Passagier | Du bist der Routenplaner |
🖥️ Dark-Theme-UI — Ein eleganter nativer Desktop-Dialog, der sich in deinen Workflow einfügt
✅ Routenentscheidungen — Strukturierte vordefinierte Optionen (Checkbox-Stil)
💬 Freitext — Wenn die vordefinierten Routen nicht ausreichen, schreibe dein eigenes Skript
📷 Rich-Media-Arsenal
Bilder aus der Zwischenablage einfügen
Lokale Dateien auswählen
Screenshot + Integrierter Annotator (Rechteck, Kreis, Pfeil, Stift, Text, Zuschneiden)
🖼️ Prompt-Bilder — Die KI kann dir Bilder zeigen (lokale Pfade, file://, http(s)://)
🔒 Sicherheit zuerst — Remote-Bilder validiert, größenbegrenzt, asynchron geladen
🎨 macOS-optimiert — Korrekte Icon-Handhabung und visueller Feinschliff
Python >= 3.11
uv (empfohlen) oder pip
git clone https://github.com/pauoliva/interactive-feedback-mcp.git
cd interactive-feedback-mcp
uv syncFüge dies zu deiner MCP-Client-Konfiguration hinzu:
Cursor (mcp.json) / Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"interactive-feedback": {
"command": "uv",
"args": [
"--directory",
"/path/to/interactive-feedback-mcp",
"run",
"server.py"
],
"timeout": 900000,
"autoApprove": ["interactive_feedback"]
}
}
}⚠️ Hinweis: Das Timeout ist in Millisekunden für Cursor (
900000= 15 Min.). Einige Clients verwenden Sekunden — passe dies entsprechend an.
interactive_feedback ToolParameter | Typ | Beschreibung |
|
| Die Frage/Aufforderung, die angezeigt werden soll |
|
| Optional. Routenentscheidungen für schnelle Entscheidungen |
|
| Optional. Bilder, die angezeigt werden sollen (lokale/Remote-URLs) |
Text-Feedback vom Benutzer
Optionale Bildanhänge (als MCP-Bild-Inhaltsblöcke)
Füge dies zu den benutzerdefinierten Anweisungen deines KI-Assistenten hinzu:
If requirements are unclear, call interactive_feedback before implementing.
Present predefined options whenever possible — give the user clear route choices.
Before finishing a task, call interactive_feedback once more for final confirmation.Variable | Standard | Beschreibung |
|
| Maximale Lebensdauer des UI-Prozesses |
| — | Pfad zum benutzerdefinierten App-Icon |
|
| Timeout für das Abrufen von Remote-Bildern |
|
| Maximale Remote-Bildgröße (10MB) |
✅ Remote-Bilder validiert durch Content-Type (image/*)
✅ Große Payloads durch Größenbeschränkung abgelehnt
✅ Asynchrones Abrufen hält die UI reaktionsfähig
✅ Lokale Dateien werden nur gelesen, wenn sie explizit referenziert werden
MIT-Lizenz — forke es, flagge es, liefere es.
🚩 Setze deine Flagge. Schreibe deine eigene Route.
Mit 💜 gemacht für Entwickler, die sich weigern, NPCs in ihrer eigenen Codebasis zu sein.
Request interactive feedback from the user. Supports text and image attachments. 使用方式:
当你通过此工具询问用户时,务必说明需要用户确定的内容。
请在完成用户布置的工作后调用该工具时,提供"结束"的选项,如果用户选择,则本次请求结束. 使用技巧:
请给出可选项,让用户选择,选项中请包涵你最推荐的选项,并说明理由.
针对每个选项,请给出对应的描述,让用户了解每个选项的含义. 什么时候使用:
每当你全部工作完成时，请调用此工具，而非直接结束流程.
每当你遇到需要用户确定的点时(例如进行需求讨论,或者执行任务中遇到重要分岔路口时),务必调用此工具.
| Name | Required | Description | Default |
|---|---|---|---|
| message | No | The specific question for the user | |
| predefined_options | No | Predefined options for the user to choose from (optional) | |
| message_images | No | Image paths to render in the prompt area (optional) |
| 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 explains the interaction pattern (blocking request for user input, option-based responses) but lacks technical behavioral traits such as timeout behavior, session persistence, or data handling. It covers 'how to use' but omits 'what happens under the hood' details expected for a user-input tool.
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 uses clear structural headers (Usage method, Usage tips, When to use) but is verbose due to extensive bilingual content. The Chinese examples, while helpful for behavior modeling, make the description longer than necessary for agent consumption, and the language mixing reduces structural coherence.
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 presence of an output schema, the description appropriately focuses on behavioral guidance rather than return values. It comprehensively covers invocation patterns and option structuring, though it would benefit from mentioning timeout handling or error conditions for full completeness.
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 coverage is 100%, establishing a baseline of 3. The description adds semantic value beyond the schema by specifying in the Chinese text that predefined_options should include a recommended choice with rationale and an 'end' option, providing substantive usage guidance for parameter population that the raw schema lacks.
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 opening sentence clearly states the tool requests interactive feedback and supports text/image attachments. However, the extensive Chinese instructions, while useful, create a bilingual structure that slightly reduces immediate clarity for agents parsing primarily English content.
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 Chinese text under '什么时候使用' (when to use) provides explicit when/when-not guidance, specifically stating to invoke this tool when work is completed instead of directly ending the process, and when encountering decision points requiring user confirmation. It also explicitly references '使用方式' (usage method) and '使用技巧' (usage tips) for detailed alternatives.
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.
v0.1.1interactive_feedbackScored across 1 tool
With only one tool available, there is no ambiguity or risk of tool misselection. The single tool has a clear, distinct purpose that does not overlap with any other tools.
The single tool follows a clear snake_case naming convention. While 'interactive' is an adjective rather than a verb, there are no other tools to create inconsistency, so the naming pattern is uniform.
A single tool is insufficient for the apparent 'Flag' domain suggested by the server name. Even for a minimal utility server, one generic feedback tool represents a severely undersized tool surface that likely cannot fulfill the server's intended purpose.
The server named 'Flag MCP' implies a feature flag or flagging domain, yet provides only a generic user feedback tool with no flag creation, management, querying, or lifecycle operations. This represents a severely incomplete surface for the stated purpose.
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.
Build and edit app screen mockups and clickable prototypes from your AI assistant.
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
