Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/AgentOps-AI/agentops-mcp below:

GitHub - AgentOps-AI/agentops-mcp: agentops mcp

The AgentOps MCP server provides access to observability and tracing data for debugging complex AI agent runs. This adds crucial context about where the AI agent succeeds or fails.

Add the following to your MCP configuration file:

{
    "mcpServers": {
        "agentops-mcp": {
            "command": "npx",
            "args": ["agentops-mcp"],
            "env": {
              "AGENTOPS_API_KEY": ""
            }
        }
    }
}

To install agentops-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @AgentOps-AI/agentops-mcp --client claude

To build the MCP server locally:

# Clone and setup
git clone https://github.com/AgentOps-AI/agentops-mcp.git
cd mcp
npm install

# Build the project
npm run build

# Run the server
npm pack

Authorize using an AgentOps project API key and return JWT token.

Parameters:

• api_key (string): Your AgentOps project API key

Retrieve trace information by ID.

Parameters:

• trace_id (string): The trace ID to retrieve

Get span information by ID.

Parameters:

• span_id (string): The span ID to retrieve

Get comprehensive trace information including all spans and their metrics.

Parameters:

• trace_id (string): The trace ID

• Node.js >= 18.0.0
• AgentOps API key (passed as parameter to tools)

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4