Skip to main content
Glama

Agent Feedback Loop πŸ“Š

Community-driven quality signals for MCP tools. Agents report tool results, building a quality database that helps all agents pick better tools.

The Problem

Agents don't know which MCP tools are reliable. They try tools blindly and hope for the best.

The Solution

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.

Installation

pip install agent-feedback-mcp-server
{
  "mcpServers": {
    "feedback": {
      "command": "uvx",
      "args": ["agent-feedback-mcp-server"]
    }
  }
}

Tools

Tool

Description

report_tool_result

Report success/failure and quality score

get_tool_quality

Get quality metrics for a specific tool

get_best_tools

Find highest-rated tools (optionally by task)

get_trending_tools

See what's trending recently

Network Effect

More agents reporting β†’ Better quality data β†’ Better tool choices β†’ More agents using β†’ More reports. The database gets better with every user.

License

MIT

-
security - not tested
F
license - not found
-
quality - not tested

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AiAgentKarl/agent-feedback-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server