C+

npm:agent-costcenter-mcp

Item: npm:agent-costcenter-mcp
Rating: 78
Author: wmcp.sh

https://www.npmjs.com/package/agent-costcenter-mcp

78/100 · MCP Trust Grade · checked 2h ago · MCP 0.1.3

What it offers — 9 tools · Developer Tools

health_check

Returns server health, uptime, version, and usage stats

register_agent

log_llm_call

Log an LLM API call with token counts. Auto-calculates cost from built-in pricing table, or use cost_override_usd.

log_tool_call

Log a tool or API call cost for an agent, with duration and optional cost.

get_cost_report

Get cost breakdown by agent, team, project, or across all agents. Includes per-model breakdowns and percentages.

set_budget_alert

Set a spending threshold for an agent. When exceeded, either warn or block further calls.

check_budget

Check if an agent is within its budget. Returns spend, remaining budget, and percentage used.

get_cost_anomalies

Find agents with unusual spending patterns. Flags agents whose recent per-call average is 2x+ above their historical average.

compare_models

Compare cost efficiency across all models used. Shows cost per 1K tokens, total spend, cheapest and most expensive.

Spec / packaging20%100

✓ depends on an MCP SDK
✓ declares a bin entry (runnable server)
✓ 9 tool(s) detected in source

Security (OWASP MCP)30%70

uses eval/exec/child_process (review for unsanitized input)
scanned 5 source files

Maintenance / popularity20%92

published within 90 days
3 published versions

Tool hygiene15%70

no TypeScript types
4 runtime deps

Transparency / provenance15%55

no repository link
✓ MIT license
10 weekly downloads

Findings

INFO Static analysis of npm package agent-costcenter-mcp@0.1.3 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.

Grade another server

We re-grade npm:agent-costcenter-mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:agent-costcenter-mcp grade C+

Share on X Open card image

https://wmcp.sh/mcp/grade/npm%3Aagent-costcenter-mcp

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade C+](https://wmcp.sh/mcp/grade/npm%3Aagent-costcenter-mcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3Aagent-costcenter-mcp)

HTML

<a href="https://wmcp.sh/mcp/grade/npm%3Aagent-costcenter-mcp"><img src="https://wmcp.sh/mcp/grade/npm%3Aagent-costcenter-mcp/badge.svg" alt="MCP Trust Grade C+ · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.