Claude Cost Audit MCP server
not respondingExact Claude API cost calc with real cache economics, plus a tiktoken-misuse scanner.
0 stars
Reviews
Write oneNobody has reviewed Claude Cost Audit yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Claude Cost Audit tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.10 · 2026-10-28 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote unreachable: HTTP 5000/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityno auth information5/15
- Maintenancelast push 95 days ago8/15
- Maintainer identityregistry namespace matches repository owner6/10
Findings (1)
- highRemote endpoint did not respond
reliability.unreachableHTTP 500
How Claude Cost Audit compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 32/100
- higher than 6% of 48,255 servers
- Uptime
- 21%
- of our recent checks; the typical remote server answers 100%
- Response time
- 687 ms
- faster than 20% of 30,031 servers
Install Claude Cost Audit in Claude Code, Cursor or VS Code
claude mcp add --transport http claude-cost-audit-mcp https://claude-cost-audit-mcp.mcpize.run/mcp
What the publisher says
From the Claude Cost Audit repository's README, as published. We do not edit it. Read it on GitHub
claude-cost-audit-mcp
An MCP server for exact Claude API cost calculation — correct prompt-cache economics (write 1.25x at 5-minute TTL / 2x at 1-hour TTL, read 0.1x), cache break-even analysis, and a scanner for the single most common Claude-cost mistake: estimating tokens with OpenAI's tiktoken.
The mistake this catches
Per Anthropic's own documentation: "Do not use tiktoken. It's OpenAI's tokenizer. It undercounts Claude tokens by ~15-20% on typical text, and by much more on code or non-English input." Any cost estimate or context-budget check built on tiktoken for a Claude model is silently wrong — this scans source for that exact pattern (foreign tokenizer + Claude/Anthropic usage in the same file) and points to the fix (messages.count_tokens).
Cache economics people get wrong
Caching doesn't pay off starting from the second request the way most people assume. The real break-even is 2 reuses at 5-minute TTL, but 3 reuses at 1-hour TTL — because the 1-hour write costs more (2x vs 1.25x). checkcachebreakeven computes this from Anthropic's real multipliers instead of a guessed rule of thumb, and flags prefixes below the model's own minimum-cacheable-token threshold (which is not monotonic across model generations — 512 tokens on the newest models, 4096 on some older ones).
Tools
calculatemessagecost
Exact $ cost from token counts, using Anthropic's real current per-model pricing (including Claude Sonnet 5's time-limited introductory rate, resolved automatically from the date you pass).
checkcachebreakeven
Given expected request volume reusing the same prefix, tells you whether caching saves money and at which TTL.
audittokenizerusage
Scans source for tiktoken/gpt-tokenizer/etc. alongside Claude API usage.
Use it
Hosted (recommended): MCPize — free tier, $7/mo Pro.
Self-host:
npm install
node server.jsPart of a small suite
mcp-schema-audit-mcp, cron-schedule-audit-mcp, regex-safety-audit-mcp.
License
MIT
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-10-28revokeA → Fscore 32: Remote endpoint did not respond
Claude Cost Audit: common questions
- Is Claude Cost Audit MCP server safe?
- No: it is graded F and blocked at the gateway (32/100). Read the Claude Cost Audit safety report
- How do I install Claude Cost Audit?
- It runs remotely at claude-cost-audit-mcp.mcpize.run. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Claude Cost Audit need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Claude Cost Audit maintained?
- The last commit was 102 days ago (2026-07-25). The latest release is v1.0.0.
- Is Claude Cost Audit up?
- 21% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Claude Cost Audit compare with other MCP servers?
- safety score 32/100 (higher than 6% of 48,255 servers); uptime 21% (of our recent checks; the typical remote server answers 100%); response time 687 ms (faster than 20% of 30,031 servers). Full comparison.