Manage the AI agents your company employs: workforce review, contracts, bill checks. 42 MCP tools.
Scored across 4 tools
The four tools have largely distinct purposes: bill reconciliation, per-resolution cost calculation, contract drafting, and workforce review. The two billing tools overlap in domain and could be confused at first glance, but their descriptions clearly distinguish computation of vendor-reported metrics from ledger-based reconciliation.
All names use the same metrx_ prefix and snake_case style, which is predictable. Three tools use verb-led names (check, draft, get), while cost_per_resolution is noun-led, a minor deviation from an otherwise consistent pattern.
Four tools is a small but reasonable surface for a focused AI workforce/billing assistant, and each tool has a substantive role. The set is slightly thin given the breadth of billing, contracts, and workforce review, but not problematically so.
The tools cover bill checking, cost calculation, contract drafting, and weekly review, but the drafting workflow dead-ends because publishing via set_job_contract is referenced as a separate step and is not included. There is also no tool for listing or managing agents/contracts, leaving notable gaps in the lifecycle.
Reconcile an AI vendor's per-resolution bill against your own records: which billed units your ledger shows as resolved, rejected, reopened, outside coverage, or unknown, and the disputed amount. A pure function over the lines you pass: reads nothing, stores nothing, needs no key. Paste the bill lines and your ledger events.
Inputs: billed (required), period (required), ledger, rejected_ids, +3 more.
The two numbers on a per-resolution AI bill (Intercom Fin, Zendesk AI, Sierra, Decagon): the effective price per billed resolution and, given total conversations, the billed-resolution share. The vendor's definition of resolved is echoed back verbatim as the vendor definition, not verified. Both numbers are the vendor's own count and come back labelled vendor-reported, not Verified. A pure function over your input: reads nothing, stores nothing, needs no key. It always ends with the next step: send one export (bill lines with ticket ids plus your ticket export for the same period) to check_vendor_bill, which recounts it.
Inputs: period (required), bill_total (required), billed_resolutions (required), vendor, +3 more.
Draft a job contract for an AI agent from a template (support_triage, sdr_qualification, internal_assistant, coding_patch): objective, unit of work, acceptance criteria, budget, and the human baseline for ROI. Returns the draft to publish plus validation errors and warnings. A pure function over your input: reads nothing, stores nothing, needs no key. Publishing the draft is a separate step (set_job_contract, 'admin' scope).
Inputs: owner (required), template (required), notes, workload, +6 more.
The weekly workforce review: every AI agent in the org as a line manager would read it (job, cost this window, outcomes, scorecard state, the candidate decision and why). org=demo reads the public Northwind sample and needs no key; org=me reads your own org and needs an API key with the 'read' scope. Paged by cursor. Numbers are the same the review page shows.
Inputs: org, limit, cursor.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
The first portfolio AI agents can hire. Profile, products, pricing and briefs over MCP.
Work management where AI agents are first-class members: tasks, projects, memory over hosted MCP
Atomadic MCP: 68 deterministic tools for agent identity, escrow, SLA, EU AI Act compliance.
AI project management for any team: agents write plans, deliver and report. You accept the work.
Add one secure layer between your agents and this server.