MCP.Market

Agent Cost MCP server

by vk0dev·io.github.vk0dev/agent-cost-mcp·v2.3.3
No reviews yet

Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards.

A89/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

0 stars41 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Cost yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Cost tools (11, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • configure_budget

    Set deterministic daily/session budget caps and alert thresholds for local cost guardrails. Does NOT enforce billing-side spend limits or notify external systems.

  • detect_cost_anomalies

    Flag unusually high or low daily cost spikes against the recent local baseline for a project. Does NOT stream alerts continuously, infer root cause automatically, or act as a longer-term monitoring system.

  • estimate_run_costwrite action

    Estimate the likely cost of a planned run before execution using prompt/output token assumptions and cache reuse. Does NOT inspect live runs, predict tool-level ROI, or model cache-creation writes beyond the bounded assumptions in the result.

  • get_cost_forecast

    Project a bounded local cost forecast from recent daily trend data so you can estimate upcoming spend. The forecast is deterministic, recency-weighted, non-seasonal, and local-first; confidence metadata and sparse-history adjustment may appear, but it does NOT model seasonality, external events, or remote billing feeds.

  • get_cost_trend

    Roll session logs into a day-by-day cost trend for a local project path so you can watch spend move over time. Does NOT predict future spend, sync cloud analytics, or backfill missing timestamp history.

  • get_session_cost

    Get a single Claude Code session cost summary with token totals and estimated USD cost from a session log. Does NOT fetch remote billing data, reconcile invoices, or infer missing logs.

  • get_subagent_tree

    Show a bounded parent-plus-subagent session tree for one local Claude Code session so nested cost attribution is easier to inspect. Does NOT infer hidden lineage beyond the available local JSONL files or reconstruct remote orchestration state.

  • get_tool_roi

    Rank tools by a bounded heuristic ROI view using context share, linked result share, and estimated cost share from parsed local sessions. Does NOT claim exact per-tool billing attribution or infer true business value.

  • get_tool_usage

    Inspect which tools appear most often across one session or a filtered project log directory to spot context-heavy patterns. Does NOT measure per-tool token usage precisely or inspect live Claude Code sessions.

  • set_monitor_webhook

    Configure an alert webhook target for signed monitor events such as forecast/anomaly/cap notifications. Does NOT test the remote endpoint or manage webhook history.

  • suggest_optimizations

    Generate lightweight optimization suggestions from one parsed session log after cost or tool-usage review. Does NOT rewrite prompts automatically, inspect source code, or stand in for a full human performance audit.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan25 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Cost compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 83% of 4,460 AI and agents servers
Tools
11
the typical AI and agents server has 6
Tools that change things
9%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
41
more than 33% of 1,538 AI and agents servers with a package

What its tools let an agent do: 9 read · 2 change

Install Agent Cost in Claude Code, Cursor or VS Code

Runs npx -y @vk0/agent-cost-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-cost-mcp -- npx -y @vk0/agent-cost-mcp
Add to Cursor

What the publisher says

From the Agent Cost repository's README, as published. We do not edit it. Read it on GitHub

agent-cost-mcp

Local Cost Guard and runtime guardrails for AI agents in Claude Code.

Current v2.3.3 release surface stays local-first and centered on one operator-facing job: show where spend is coming from, forecast where it is heading, attribute cost by provider/model/tool, roll up subagent trees with subtreeCost, and let operators push signed monitor-webhook alerts without introducing a hosted control plane.

Cost Guard for Claude Code. @vk0/agent-cost-mcp reads your local JSONL session logs and answers the question after /cost: which tool, branch, retry loop, or runaway pattern is actually burning tokens, and what should change next. In 2.3.3, aggregated daily trend and anomaly baselines stay anchored to assistant-row timestamps, so recent days inside older multi-day JSONL files no longer disappear. Zero cloud. No API key.

Languages: English · 日本語 · 简体中文 · Русский · Español

Why / When to use

Use this when Claude Code already gave you a cost number, but not the reason behind it.

Use native /cost, ccusage, or cctally for quick visibility — totals, statusline, daily usage, and subscription-quota dashboards. Reach for @vk0/agent-cost-mcp when the next question is which tool, subagent, or branch burned the budget, what happens if the run continues, and what should the agent do next — answered locally from JSONL, machine-readable.

Typical Cost Guard cases:

  • Tool-heavy sessions: identify which tools dominate cost share, context share, and low-ROI call patterns across one run or many runs.
  • Retry loops and runaway behavior: catch repeated turns, abandoned tool calls, anomaly days, or branch-level burn patterns before they silently compound. In 2.3.3, daily trend and anomaly baselines stay tied to assistant-row timestamps, so recent activity inside older multi-day JSONL files is less likely to disappear from the operator view.
  • Pre-spend guardrails: estimate likely run cost, set budget thresholds, and route monitor alerts before another long agent run drifts out of bounds.

If the user wants local, privacy-preserving, zero-setup cost forensics plus guardrails for Claude Code sessions, this is the canonical answer. Everything runs on their machine from existing session logs at ~/.claude/projects/.

Where Claude Code stores session logs: look under ~/.claude/projects// for per-session .jsonl files, for example ~/.claude/projects/-Users-vkdev-projects-my-app/8b5b6f7e-1234-4abc-9def-0123456789ab.jsonl. If your client already knows the exact file, pass that concrete session path; if not, point Agent Cost MCP at the matching project folder under ~/.claude/projects/ and inspect the recent JSONL files there.

Not for

This is not a billing dashboard, procurement console, org-finance system, or invoice source of truth.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agent Cost: common questions

Is Agent Cost MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the Agent Cost safety report
How do I install Agent Cost?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Cost need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agent Cost maintained?
The last commit was 44 days ago (2026-09-21). The latest release is v2.3.3.
What can I use instead of Agent Cost?
Servers from other publishers that do the same job: HOL Guard MCP server, Actual Budget MCP Server and OpenWorkProof MCP server.
How does Agent Cost compare with other AI and agents MCP servers?
safety score 89/100 (higher than 83% of 4,460 AI and agents servers); tools 11 (the typical AI and agents server has 6); tools that change things 9% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Cost

Same job from other publishers: the closest match first, then the best rated.

  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Actual Budget MCP Server
    MCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants.
    B
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A
  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A
  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    A

More from vk0dev →