AI & Machine Learning

metrxbot.com

Manages and optimizes costs for AI agent fleets by providing cost summaries, agent details, and optimization recommendations.

1 endpoint37 known toolsFirst detected May 29, 2026Last detected September 6, 2026

ENDPOINT 1

https://metrxbot.com/api/mcp

No auth detected

MCP server metadata

Name: metrx-mcp-server
Version: 0.4.0

Capabilities

tools.listChangedprompts.listChanged

Server instructions

37 MCP tools across 14 domains. Response contract note: every loop-metrics-domain tool (metrx_get_signal_readiness, metrx_get_dashboard_headline, metrx_get_report_snapshot, metrx_get_verdicts, metrx_get_trials, metrx_get_proposals, metrx_get_actuations, metrx_get_decision_queue) returns measured-value envelopes (numeric leaves are {value, ci_low, ci_high, method, data_through}; CIs never fabricated). All other (legacy) Metrx MCP responses are envelope-PENDING: plain numbers, not yet envelope-shaped.

Known tools 37

metrx_get_cost_summary

Get a comprehensive cost summary for your AI agent fleet.

Inferred read-only

metrx_list_agents

List all AI agents in your organization with their status, category, and cost.

Inferred read-only

metrx_get_agent_detail

Get detailed information about a specific agent including its model, framework, category, outcome configuration, and failure risk score.

Inferred read-only

metrx_get_optimization_recommendations

Get AI-powered cost optimization recommendations for a specific agent or your entire fleet.

Inferred read-only

metrx_apply_optimization

Apply a one-click optimization recommendation to an agent.

Inferred read-only

metrx_route_model

Get a model routing recommendation for a specific task based on complexity.

Inferred read-only

metrx_compare_models

Compare LLM model pricing and capabilities across providers.

Inferred read-only

metrx_get_budget_status

Get the current status of all budget configurations.

Inferred read-only

metrx_set_budget

Create or update a budget configuration for an agent or the entire organization.

Potential side effects

metrx_update_budget_mode

Change the enforcement mode of an existing budget or pause/resume it.

Inferred read-only

metrx_get_alerts

Get active alerts and notifications for your agent fleet.

Inferred read-only

metrx_acknowledge_alert

Mark one or more alerts as read/acknowledged.

Inferred read-only

metrx_get_failure_predictions

Get predictive failure analysis for your agents.

Inferred read-only

metrx_create_model_experiment

Start an A/B test comparing two LLM models for a specific agent.

Inferred read-only

metrx_get_experiment_results

Get the current results of a model routing experiment.

Inferred read-only

metrx_stop_experiment

Stop a running model routing experiment.

Inferred read-only

metrx_run_cost_leak_scan

Run a comprehensive cost leak audit across your entire agent fleet.

Inferred read-only

metrx_attribute_task

Link an agent task/event to a business outcome for ROI tracking.

Inferred read-only

metrx_get_task_roi

Calculate return on investment for an agent.

Inferred read-only

metrx_get_attribution_report

Get attribution report showing which agent actions led to business outcomes.

Inferred read-only

metrx_get_upgrade_justification

Generate an ROI report explaining why paying for Metrx makes sense based on current usage.

Inferred read-only

metrx_configure_alert_threshold

Set up cost or operational alert thresholds for a specific agent or org-wide.

Inferred read-only

metrx_generate_roi_audit

Generate a comprehensive ROI audit report for your AI agent fleet.

Inferred read-only

metrx_get_upgrade_business_case

Generate a personalized ROI business case for paying for Metrx.

Inferred read-only

metrx_get_health_scores

Returns health score, grade, and data completeness for all agents in the organization.

Inferred read-only

metrx_get_rankings

Returns agents sorted by health score with percentile ranking.

Inferred read-only

metrx_get_balance

Check how many verifications your organization has remaining.

Inferred read-only

metrx_buy_verification

Purchase one verification (a causal verdict on whether a model switch holds quality on YOUR production traffic).

Potential side effects

metrx_verify_switch

Start a purchased verification: would candidate_model hold quality vs prod_model on your production traffic?

Inferred read-only

metrx_get_signal_readiness

Org-scoped signal-readiness diagnostics: per-agent event coverage, label lag, join rate, volume-vs-power (days to trial-ready), estimator eligibility, and blocked_on_signal proposals cross-linked to the failing readiness dimension.

Inferred read-only

metrx_get_dashboard_headline

The three-number headline regime: measured spend, attributed (modeled) savings, and verified savings-with-CI — each with basis, provenance, and tone.

Inferred read-only

metrx_get_report_snapshot

Fetch one frozen executive-report snapshot by its public share token (the token IS the capability).

Inferred read-only

metrx_get_verdicts

Org-scoped CURRENT causal-verdict summaries: per (agent, prod_model, candidate_model, task_category) — verdict, evidence mode/regime, pair counts, non-inferiority, savings CI, judge model, expiry.

Inferred read-only

metrx_get_trials

Org-scoped pre-registered trial plans: regime, primary metric, margin, the frozen sample plan (pre-registration), models, status (registered/concluded/voided) and the concluding verdict id.

Inferred read-only

metrx_get_proposals

Org-scoped CURRENT candidate proposals: action type/class, D-class, status with blocked_reason (blocked_on_signal proposals name the failing dimension), estimated impact, taxonomy axes.

Inferred read-only

metrx_get_actuations

Org-scoped actuation records: action class, authority, who/when, rollback state with reason, acknowledgement state.

Inferred read-only

metrx_get_decision_queue

The operator decision queue, derived from real loop objects (approvable verdicts, blocked proposals, breaker events, expiring evidence).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.metrx-mcp-server]
url = "https://metrxbot.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "metrx-mcp-server": {
      "type": "http",
      "url": "https://metrxbot.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: metrx-mcp-server
Remote MCP URL: https://metrxbot.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "metrx-mcp-server": {
      "url": "https://metrxbot.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "metrx-mcp-server": {
      "type": "http",
      "url": "https://metrxbot.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "metrx-mcp-server",
  "transport": "streamable-http",
  "url": "https://metrxbot.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for metrxbot.com was fetched 2026-08-03T21:37:48.854Z and is being refreshed.

Trust status Trusted

metrxbot.com is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.