Mcp Server
Connects Claude and other MCP clients to Metrx's cost intelligence platform for tracking LLM spend in real time. You get 23 tools across dashboards, optimization recommendations, budget enforcement, A/B testing between models, and ROI attribution. The cost leak scanner runs seven checks for retry storms, context bloat, and model mismatches. You can set hard budget limits that auto-pause agents, compare pricing across providers with metrx_compare_models, or spin up experiments to test whether Claude Sonnet saves you money over GPT-4. Also ships a standalone CLI cost leak detector that runs offline against your logs. Useful when you're running multiple agents and need to prove ROI or stop runaway spend before it hits your credit card.
- tools
- 23
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Mar 12, 2026
Tools
23 toolsPublic tool metadata for what this MCP can expose to an agent.
metrx_get_cost_summaryComprehensive cost summary — total spend, call counts, error rates, and optimization opportunities
Comprehensive cost summary — total spend, call counts, error rates, and optimization opportunities
No parameter schema in public metadata yet.
metrx_list_agentsList all agents with status, category, cost metrics, and health indicators
List all agents with status, category, cost metrics, and health indicators
No parameter schema in public metadata yet.
metrx_get_agent_detailDetailed agent info including model, framework, cost breakdown, and performance history
Detailed agent info including model, framework, cost breakdown, and performance history
No parameter schema in public metadata yet.
metrx_get_optimization_recommendationsAI-powered cost optimization recommendations per agent or fleet-wide
AI-powered cost optimization recommendations per agent or fleet-wide
No parameter schema in public metadata yet.
metrx_apply_optimizationOne-click apply an optimization recommendation to an agent
One-click apply an optimization recommendation to an agent
No parameter schema in public metadata yet.
metrx_route_modelModel routing recommendation for a specific task based on complexity
Model routing recommendation for a specific task based on complexity
No parameter schema in public metadata yet.
metrx_compare_modelsCompare LLM model pricing and capabilities across providers
Compare LLM model pricing and capabilities across providers
No parameter schema in public metadata yet.
metrx_get_budget_statusCurrent status of all budget configurations with spend vs. limits
Current status of all budget configurations with spend vs. limits
No parameter schema in public metadata yet.
metrx_set_budgetCreate or update a budget with hard, soft, or monitor enforcement
Create or update a budget with hard, soft, or monitor enforcement
No parameter schema in public metadata yet.
metrx_update_budget_modeChange enforcement mode of an existing budget or pause/resume it
Change enforcement mode of an existing budget or pause/resume it
No parameter schema in public metadata yet.
metrx_get_alertsActive alerts and notifications for your agent fleet
Active alerts and notifications for your agent fleet
No parameter schema in public metadata yet.
metrx_acknowledge_alertMark one or more alerts as read/acknowledged
Mark one or more alerts as read/acknowledged
No parameter schema in public metadata yet.
metrx_get_failure_predictionsPredictive failure analysis — identify agents likely to fail before it happens
Predictive failure analysis — identify agents likely to fail before it happens
No parameter schema in public metadata yet.
metrx_create_model_experimentStart an A/B test comparing two LLM models with traffic splitting
Start an A/B test comparing two LLM models with traffic splitting
No parameter schema in public metadata yet.
metrx_get_experiment_resultsStatistical significance, cost delta, and recommended action
Statistical significance, cost delta, and recommended action
No parameter schema in public metadata yet.
metrx_stop_experimentStop a running model routing experiment and lock in the winner
Stop a running model routing experiment and lock in the winner
No parameter schema in public metadata yet.
metrx_run_cost_leak_scanComprehensive 7-check cost leak audit across your entire agent fleet
Comprehensive 7-check cost leak audit across your entire agent fleet
No parameter schema in public metadata yet.
metrx_attribute_taskLink agent actions to business outcomes for ROI tracking
Link agent actions to business outcomes for ROI tracking
No parameter schema in public metadata yet.
metrx_get_task_roiCalculate return on investment for an agent — costs vs. attributed outcomes
Calculate return on investment for an agent — costs vs. attributed outcomes
No parameter schema in public metadata yet.
metrx_get_attribution_reportMulti-source attribution report with confidence scores and top contributors
Multi-source attribution report with confidence scores and top contributors
No parameter schema in public metadata yet.
metrx_configure_alert_thresholdSet cost or operational alert thresholds with email, webhook, or auto-pause
Set cost or operational alert thresholds with email, webhook, or auto-pause
No parameter schema in public metadata yet.
metrx_generate_roi_auditBoard-ready ROI audit report for your AI agent fleet
Board-ready ROI audit report for your AI agent fleet
No parameter schema in public metadata yet.
metrx_get_upgrade_justificationROI report for tier upgrades based on current usage patterns
ROI report for tier upgrades based on current usage patterns
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
METRX_API_KEY*secretYour Metrx API key (sign up free at https://app.metrxbot.com/sign-up — manage keys at https://app.metrxbot.com/settings/security)
Readme
Metrx MCP Server
The Model Context Protocol (MCP) server for Metrx: how a company manages the AI agents it employs. Each agent gets a job contract, a scorecard against it, and a P&L: what it cost and what it produced. This server exposes those records as tools that any MCP-compatible client (Claude, GPT, Gemini, custom agents) can call. Version 0.6.0.
This package is the single source for both transports: the npm package you run locally over stdio, and the hosted server at https://metrxbot.com/api/mcp. The public repository at https://github.com/metrxbots/mcp-server is a mirror, synced from the monorepo by packages/mcp-server/scripts/publish-mirror.ts. Contributors open pull requests against the monorepo; issues go to https://github.com/metrxbots/mcp-server/issues.
Quick Start
Three ways in.
Details
- Repository
- github.com/metrxbots/mcp-server
- Category
- AI & LLM Tools
- Package
@metrxbot/mcp-server- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
PinRAGndjordjevic/pinragMCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.1stars
Aiglarenugehs/aiglareAudit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.1stars
Prompeteerprompeteer/prompeteer-mcpContextual prompts and agent skills for 140+ AI platforms.1stars
Image Generation MCP Serverpvliesdonk/image-generation-mcpMCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.1stars
Grantdrafavecchi/grantdGrantd MCP server: let your AI agent act on a user's behalf across third-party APIs via OAuth.1stars
Meshimize Mcprenl/meshimize-mcpMeshimize: Q&A groups, messaging, group discovery, and agent-to-agent delegation1stars