mcpField
A
agentcents

agentcents

Local
github.com/labham-llcAI & Agents0Updated 14w ago
Repository

About agentcents

agentcents is a Claude Skill for estimating LLM call and workflow costs, comparing models, and identifying the lowest-cost option that meets a capability threshold. It can use bundled price and capability data or, when the local proxy is running, forecasts and records from its ledger.

Key features

  1. 01Estimate call and workflow costs
  2. 02Compare candidate models against a capability bar
  3. 03Show cost comparisons as Mermaid diagrams
  4. 04Use bundled data or local proxy records

Use cases

  1. 01Estimate daily support-email classification costs
  2. 02Choose models for steps in a research agent workflow

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "labham-llc-agentcents": {
      "command": "uvx",
      "args": [
        "agentcents"
      ]
    }
  }
}
Run commanduvx agentcents

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiagentcents1.1.3

Tools

11

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
tagstringNooptional tag filter
hoursnumberNolookback window, default 24

Details

From the project README

agentcents — LLM cost consulting skill for Claude

A Claude Skill that turns Claude into a neutral LLM cost advisor: estimate what any call or agent workflow will cost across candidate models, get the cheapest model that clears the task's capability bar, and see the comparison as a Mermaid diagram — with honest ranges, never false point estimates.

Works two ways:

  • Consult mode (no install): answers from a bundled, hand-verified snapshot of current model prices and Intelligence Index scores.
  • Live mode: if the agentcents proxy is running locally, the skill uses your real ledger — calibrated forecasts, spend, and accuracy instead of priors.

Install

Claude.ai / Desktop: Settings → Capabilities → Skills → Add → upload this folder (or the packaged .skill).

Claude Code: /plugin marketplace add labham-llc/agentcents-skill then /plugin install agentcents@labham-skills

Then just ask things like:

what would it cost to classify ~500 support emails a day, about 200 tokens each?

I'm building a 5-step research agent — which model should each step use?

What's in the box

SKILL.md                 — the consulting method (measure, range, bar, pick, flag instability)
assets/pricing.json      — price + capability snapshot (see _meta.verified_utc)
references/local-api.md  — live-mode reference for a locally running agentcents

Snapshot verified: 2026-07-15 (see _meta.verified_utc) — refreshed with each agentcents release.

The product behind it

agentcents is a local proxy that meters, forecasts, and budget-enforces LLM API calls — and grades its own forecasting accuracy on a calibration page. pip install agentcents. The skill is free; so is the agentcents free tier.

© Labham LLC · skill instructions and snapshot data may be redistributed with attribution; the agentcents software itself is proprietary (see its LICENSE).

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.