MCP server for AI agent cost intelligence — 23 tools to track spend, optimize mo
MCP server for AI agent cost intelligence — 23 tools to track spend, optimize models, manage budgets, detect waste, and prove ROI
active Production-safe Score 88/100 http no auth
At a glance
| Endpoint | https://metrxbot.com/api/mcp |
|---|---|
| Source | https://github.com/metrxbots/mcp-server |
| Transport | http |
| Tools | 4 |
| Auth | none |
| First seen | 2026-03-16 11:01:10 |
| Last checked | 2026-11-17 21:42:11 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 973 / 2347 ms |
| Last successful check | 2026-11-17 21:42:11 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (4)
metrx_get_workforce_review— The weekly workforce review: every AI agent in the org as a line manager would read it (job, cost this window, outcomes, scorecard state, thmetrx_draft_job_contract— Draft a job contract for an AI agent from a template (support_triage, sdr_qualification, internal_assistant, coding_patch): objective, unitmetrx_check_vendor_bill— Reconcile an AI vendor's per-resolution bill against your own records: which billed units sort into matched, disputed (your ledger shows itmetrx_cost_per_resolution— The two numbers on a per-resolution AI bill (Intercom Fin, Zendesk AI, Sierra, Decagon): the effective price per billed resolution and, give
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:42:11 | ✓ | ✓ | 656 ms | 90 | active |
| 2026-11-17 20:57:20 | ✓ | ✓ | 923 ms | 90 | active |
| 2026-11-17 20:34:26 | ✓ | ✓ | 7535 ms | 86 | active |
| 2026-11-17 19:48:16 | ✓ | ✓ | 713 ms | 90 | active |
| 2026-11-17 19:26:03 | ✓ | ✓ | 791 ms | 90 | active |
| 2026-11-17 18:42:19 | ✓ | ✓ | 691 ms | 90 | active |
| 2026-11-17 18:01:42 | ✓ | ✓ | 829 ms | 90 | active |
| 2026-11-17 17:34:45 | ✓ | ✓ | 789 ms | 90 | active |
| 2026-11-17 16:43:32 | ✓ | ✓ | 1065 ms | 86 | active |
| 2026-11-17 16:10:28 | ✓ | ✓ | 650 ms | 90 | active |
| 2026-11-17 15:25:42 | ✓ | ✓ | 961 ms | 90 | active |
| 2026-11-17 14:40:47 | ✓ | ✓ | 989 ms | 90 | active |
| 2026-11-17 13:56:11 | ✓ | ✓ | 736 ms | 90 | active |
| 2026-11-17 13:25:52 | ✓ | ✓ | 656 ms | 90 | active |
| 2026-11-17 12:42:17 | ✓ | ✓ | 3068 ms | 86 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://metrxbot.com/api/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/metrxbot-com-api-mcp # JSON