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., "@Agent Feedback Loop find the most reliable tools for web searching"
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.
Community-driven quality signals for MCP tools. Agents report tool results, building a quality database that helps all agents pick better tools.
Agents don't know which MCP tools are reliable. They try tools blindly and hope for the best.
Related MCP server: hive-exp
Automated feedback: agents report success/failure and quality after each tool call. Over time, a quality database emerges that helps every agent make better decisions.
pip install agent-feedback-mcp-server{
"mcpServers": {
"feedback": {
"command": "uvx",
"args": ["agent-feedback-mcp-server"]
}
}
}Tool | Description |
| Report success/failure and quality score |
| Get quality metrics for a specific tool |
| Find highest-rated tools (optionally by task) |
| See what's trending recently |
More agents reporting → Better quality data → Better tool choices → More agents using → More reports. The database gets better with every user.
Category | Servers |
🔗 Blockchain | |
🌍 Data | Weather · Germany · Agriculture · Space · Aviation · EU Companies |
🔒 Security | |
🤖 Agent Infra | Memory · Directory · Hub · Reputation |
🔬 Research |
MIT
Get the highest-rated MCP tools, optionally filtered by task type.
Shows the best tools based on community feedback data.
Args: task: Filter by task description keyword (optional) limit: Max results (default: 10)
Inputs: task, limit.
Get quality metrics for a specific MCP tool.
Shows success rate, average quality score, and recent feedback.
Args: tool_name: Name of the tool to check
Inputs: tool_name (required).
Get trending MCP tools based on recent usage and feedback.
Shows which tools are being used most and rated highest recently.
Args: days: Look back period in days (default: 7) limit: Max results (default: 10)
Inputs: days, limit.
Report the result of using an MCP tool.
Helps build a quality database so agents can discover which tools work best for which tasks.
Args: tool_name: Name of the tool used (e.g. "get_weather") success: Whether the tool call was successful quality_score: Quality rating 1-10 (10 = perfect) task_description: What you were trying to do server_name: Which MCP server the tool belongs to response_time_ms: How long the call took in milliseconds error_message: Error message if the call failed
Inputs: tool_name (required), success (required), quality_score, task_description, +3 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a clearly distinct purpose: get_best_tools retrieves top-rated tools, get_tool_quality provides metrics for a specific tool, get_trending_tools shows recent trends, and report_tool_result submits feedback. There is no overlap in functionality, making tool selection unambiguous.
All tool names follow a consistent verb_noun pattern with underscores (e.g., get_best_tools, get_tool_quality, get_trending_tools, report_tool_result). The naming is predictable and readable throughout the set.
With 4 tools, the count is reasonable for a feedback loop server, covering core operations like querying and reporting. It might feel slightly thin if advanced features like analytics or bulk operations are needed, but it's well-scoped for basic functionality.
The tool set covers key aspects of a feedback system: retrieving best tools, checking specific tool quality, viewing trends, and submitting reports. A minor gap is the lack of tools for managing or aggregating feedback data, but agents can work around this with the provided operations.
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Independent trust scores, tool surfaces and change history for MCP servers.
Analytics for MCP servers. Find out which of your tools agents get wrong. MCPulse shows you which tools AI agents retry, which come back empty, and which they never call at all. Two lines inside your own server. It never sees your arguments or your results. getmcpulse.com
Analytics for MCP servers. Query your tool calls, first-call success, retries and schema cost.
