Agent Cost MCP
Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards.
Connector by vk0dev · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/vk0dev-agent-cost-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 9 read · 2 write · 0 delete
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Node.js package
Tools by what they do 11
Read from the source code; the running server may list different tools.
Read 9 · Look things up without changing anything.
detect_cost_anomaliesestimate_run_costget_cost_forecastget_cost_trendget_session_costget_subagent_treeget_tool_roiget_tool_usagesuggest_optimizations
Write 2 · Create, change, send or run things.
configure_budgetset_monitor_webhook
Tools (11)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
configure_budgetSet 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_anomaliesFlag 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_costEstimate 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_forecastProject 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_trendRoll 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_costGet 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_treeShow 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_roiRank 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_usageInspect 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_webhookConfigure 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_optimizationsGenerate 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.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit
- Oct 11, 2026 (19 days ago)
- Last release
- Jul 5, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.vk0dev/agent-cost-mcp- Version
- 2.3.3
- Auth
- No auth
- Packages
- npm @vk0/agent-cost-mcp
- License
- MIT
- Repository
- github.com/vk0dev/agent-cost-mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from vk0dev
- 0.579score
Agent Claim MCP
vk0dev
File-claim coordination for parallel AI coding agents: claim files before edits, no stomping.
ConnectorAFreshness: ALocalClaude Code +5 - 0.562score
Code Impact MCP
vk0dev
Dependency graph and blast-radius analysis for local TypeScript/JavaScript repos.
ConnectorBFreshness: BLocalRead-only★ 1Claude Code +5
Cite this page
Agent Cost MCP. Agent Mart. https://agentmart.dev/connectors/vk0dev-agent-cost-mcp (last updated 2026-10-24)