ReportProof MCP Server
Accepts Google Ads API search/searchStream responses and Google Ads CSV exports to recompute campaign metrics and verify report numbers against Google Ads data.
Accepts raw GA4 Data API runReport responses and GA4 CSV exports so the server can compute exact metrics and verify numbers in draft reports against Google Analytics data.
Accepts Meta Ads CSV exports and Meta Insights API rows as input for metric computation and report verification.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ReportProof MCP Server check my draft GA4 report against the raw data and flag wrong numbers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ReportProof MCP server
Stop your AI agent from putting wrong numbers in client reports.
LLMs write good marketing reports, but they get numbers wrong. A rise becomes "down", 25.58% becomes "25%", a total gets invented. This MCP server gives Claude, Cursor or any MCP client three tools that do the maths in code and check every number:
Tool | What it does |
| Data + draft report → PASS, or FAIL listing each wrong number, its line, the problem (not in the data / wrong direction) and the closest real value |
| Data → exact totals, % change (month-on-month or year-on-year), CTR / CPC / CPA / ROAS recomputed from totals, goal progress, top movers, anomalies, with ready-to-print strings (incl. Indian lakh/crore) |
| Draft + metrics from |
There's no LLM inside: the same input always gives the same answer.
It pairs with the official Google Analytics MCP and Google Ads MCP servers. Pass their raw run_report / search output straight in.
Data it accepts
CSV exports from GA4, Google Ads, Meta Ads, Search Console, LinkedIn Ads, or any CSV with a date column:
files: [{name, content}]Plain JSON rows (Meta Insights API rows work as-is):
data: [{name, rows: [...]}]GA4 Data API
runReportresponse, unchanged:data: [{name, ga4_report: {...}}]Google Ads API
search/searchStreamresponse, unchanged:data: [{name, google_ads: {...}}]
Related MCP server: Agent Reliability MCP Server
Install
Try it first, no sign-up: https://reportproof-api.onrender.com/try
You need a ReportProof API key. The free plan (50 calls/month) is at rapidapi.com/VikyathJ/api/reportproof.
Claude Desktop / Cursor / any MCP client (needs uv):
{
"mcpServers": {
"reportproof": {
"command": "uvx",
"args": ["--from", "git+https://github.com/vikyathhj-ui/reportproof-mcp", "reportproof-mcp"],
"env": { "RAPIDAPI_KEY": "your-rapidapi-key" }
}
}
}Without uv: clone this repo and use "command": "python", "args": ["-m", "reportproof_mcp"] with "cwd" set to the clone. Python 3.9+, no dependencies.
Example agent instruction
Pull last month's GA4 and Google Ads data, write the client report, then call
check_reportwith the raw data and your draft. If it says FAIL, fix only the flagged numbers using the closest real values and check again until it passes.
How it works / privacy
This package is a thin client. The calculation and verification run in the ReportProof API.
The API processes each request in a temporary folder that is deleted afterwards. It stores nothing and doesn't log request contents.
The first call after a quiet period can take up to about a minute while the server wakes.
Known limit: verification checks that each number exists in the data with the right direction. It doesn't check that it's used in the right context. In a planted-error test it caught 37 of 40 errors.
Development
python tests/test_mcp.py # protocol tests (offline)
REPORTPROOF_URL=http://localhost:8080 REPORTPROOF_KEY=... python tests/test_mcp.py # + API testsMIT licensed.
Available Tools
3 toolscheck_reportA
Check every number in a draft marketing report against the source data. Returns PASS, or FAIL with each wrong number, its line, the problem (not in data / wrong direction) and the closest real value. Use after writing a report from GA4, Google Ads, Meta Ads or Search Console data; rewrite only the flagged sentences and check again.
Inputs: report (required), end, data, files, +5 more.
compute_metricsA
Compute exact report metrics from marketing data: totals, % change vs previous period or last year, CTR, CPC, CPA, ROAS and rates recomputed from totals (never averaged), blended ad totals, goal progress, top movers and anomalies, with ready-to-print display strings. Use these numbers when writing a report.
Inputs: end, data, files, goals, +4 more.
verify_reportB
Verify a draft report against a metrics object previously returned by compute_metrics.
Inputs: report (required), metrics (required), allow.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
check_report and verify_report both validate a draft report and differ only in data source (raw source data vs. a metrics object from compute_metrics), which is a subtle boundary an agent can easily cross. The descriptions do state when to use each, but the near-synonymous names 'check' and 'verify' increase misselection risk. compute_metrics is clearly distinct.
All three tools follow a clean verb_noun snake_case pattern: check_report, verify_report, compute_metrics. The convention is uniform and predictable, even if check/verify are semantically close.
Three tools is a tight, well-scoped surface for a narrow report-proofing purpose. However, check_report and verify_report are close enough that one could arguably be folded into the other, making the set feel slightly redundant rather than minimal.
The compute-then-verify/check lifecycle covers the core workflow: derive exact metrics, then validate a draft against either raw data or computed metrics. Minor gaps exist (e.g., no way to fetch or inspect the source data itself, or to re-check only flagged lines), but agents can work around these.
Maintenance
Related MCP Connectors
AI marketing agent for Google Ads, Meta, GA4, TikTok, LinkedIn, Shopify, HubSpot and more.
Paid deterministic data-quality and execution-verification tools for AI agents.
Marketing data and actions for AI agents: GA4, Search Console, ads, social, SEO and WordPress.
Independent signed math checks for AI agents: PASS or FAIL plus a link anyone can open. Free beta.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides accurate SaaS metrics calculations (LTV, CAC, runway, health score, etc.) with formulas and interpretations for AI agents and founders, ensuring no hallucinated numbers.MIT
- FlicenseNot gradedqualityDmaintenanceComputes AI agent reliability metrics like success rates, latency statistics, and failure patterns from provided numbers, with zero external API cost.-
- AlicenseNot gradedqualityBmaintenanceProvides exact, deterministic tools for math, dates, units, validation, and more to AI agents, returning precise answers with explicit assumptions and warnings instead of model guesses.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to verify claims deterministically by computing arithmetic, ratios, and dates and matching statements against provided sources, returning a confidence ladder of certain, source-backed, or unverifiable.MIT