Metrx MCP Server — AI agent cost intelligence tools for LLM agents. Track spend, optimize models, manage budgets, detect waste, and prove ROI.
Metrx MCP Server — AI agent cost intelligence tools for LLM agents. Track spend, optimize models, manage budgets, detect waste, and prove ROI. That is what the metrxbots mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
This starts the server with sample data so you can explore all 23 tools instantly.
The server publishes 14 tools. What each one is for:
metrx_get_cost_summary — Comprehensive cost summary — total spend, call counts, error rates, and optimization opportunitiesmetrx_list_agents — List all agents with status, category, cost metrics, and health indicatorsmetrx_get_agent_detail — Detailed agent info including model, framework, cost breakdown, and performance historymetrx_get_optimization_recommendations — AI-powered cost optimization recommendations per agent or fleet-widemetrx_apply_optimization — One-click apply an optimization recommendation to an agentmetrx_route_model — Model routing recommendation for a specific task based on complexitymetrx_compare_models — Compare LLM model pricing and capabilities across providersmetrx_get_budget_status — Current status of all budget configurations with spend vs. limitsmetrx_set_budget — Create or update a budget with hard, soft, or monitor enforcementmetrx_update_budget_mode — Change enforcement mode of an existing budget or pause/resume itmetrx_get_alerts — Active alerts and notifications for your agent fleetmetrx_acknowledge_alert — Mark one or more alerts as read/acknowledgedInstallation goes through your MCP client rather than a global install: point it at @metrxbot/mcp-server on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Configuration is passed through the environment: METRX_API_KEY, METRX_API_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Metrxbots MCP's toolset — metrx_get_cost_summary, metrx_list_agents, metrx_get_agent_detail and 11 more — is a fair guide to whether it matches your workflow. It is maintained by metrxbots; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| metrx_get_cost_summary | Comprehensive cost summary — total spend, call counts, error rates, and optimization opportunities |
| metrx_list_agents | List all agents with status, category, cost metrics, and health indicators |
| metrx_get_agent_detail | Detailed agent info including model, framework, cost breakdown, and performance history |
| metrx_get_optimization_recommendations | AI-powered cost optimization recommendations per agent or fleet-wide |
| metrx_apply_optimization | One-click apply an optimization recommendation to an agent |
| metrx_route_model | Model routing recommendation for a specific task based on complexity |
| metrx_compare_models | Compare LLM model pricing and capabilities across providers |
| metrx_get_budget_status | Current status of all budget configurations with spend vs. limits |
| metrx_set_budget | Create or update a budget with hard, soft, or monitor enforcement |
| metrx_update_budget_mode | Change enforcement mode of an existing budget or pause/resume it |
| metrx_get_alerts | Active alerts and notifications for your agent fleet |
| metrx_acknowledge_alert | Mark one or more alerts as read/acknowledged |
| metrx_get_failure_predictions | Predictive failure analysis — identify agents likely to fail before it happens |
| metrx_create_model_experiment | Start an A/B test comparing two LLM models with traffic splitting |
{
"mcpServers": {
"metrxbots": {
"command": "npx",
"args": ["-y", "@metrxbot/mcp-server"],
"env": {
"METRX_API_KEY": "your-value",
"METRX_API_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| METRX_API_KEY | Credential the server authenticates with. | Yes |
| METRX_API_URL | Endpoint or connection string the server talks to. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.