Finance Toolkit
500+ transparent financial methods calculated from raw statements, not third-party endpoints.
Description from the maker (original English)
Free, no key: sourced, dated revenue of real AI-agent businesses. Start with search_businesses.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://mrrledger.com/mcpRun this in your terminal
claude mcp add --transport http mrrledger https://mrrledger.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mrrledger": {
"url": "https://mrrledger.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"mrrledger": {
"type": "http",
"url": "https://mrrledger.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://mrrledger.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
search_businessesUse when the user asks how much revenue, MRR or ARR an AI agent, AI startup or AI tool makes, or wants real examples of AI businesses in a niche (support, coding, voice, sales, automation...). Returns AI-agent businesses with sourced, dated revenue (start here). Example: {"query"
benchmark_businessUse when the user gives their own MRR or asks whether their revenue is good compared with similar AI businesses. Returns where an MRR ranks among fresh same-category MRR peers (rank of N + 1 comparable). Example: {"category":"customer-support","mrr":2000} -> your rank among the c
get_businessUse when the user names one AI company or agent (e.g. Cursor, Lovable) and asks about its revenue, pricing model or growth. Returns one business's full sourced record. Example: {"slug":"cursor"} -> Cursor with every figure and its source. Use it when you already have the slug (fr
leaderboardUse when the user asks which AI agents or AI startups make the most money, or for a top-N revenue ranking. Returns businesses ranked by latest sourced annualized revenue, highest first (same briefs, with verification_label, as search_businesses). Example: {"category":"coding-agen
compare_businessesUse when the user asks to compare two AI companies (X vs Y) on revenue or business model. Returns two businesses side by side (tier, category, annualized revenue + basis, pricing model, founded, top lessons, growth) and a diff with the revenue ratio. Example: {"a":"cursor","b":"l
get_growthUse when the user asks how fast an AI company grew or for its revenue over time. Returns one business's dated revenue series, oldest first (as_of, annualized_usd, label, value_usd, source_url; MRR x12). Example: {"slug":"lovable"} -> Lovable's dated ARR points with sources. Unkno
whats_newUse when the user asks what is new or what changed recently in AI startup revenue figures. Returns the change log, newest first: businesses added and figures added, revised, re-dated or removed, each with source_url; filters since (YYYY-MM-DD), slug, kind, limit (max 100). Exampl
get_categoryReturns one category: count, median annualized revenue (overall, by tier) and members with rank and revenue. Example: {"slug":"customer-support"} -> the customer-support agents with their revenue. Unknown slug -> isError. Cost: free (100 calls/day without a key).
list_categoriesReturns every category with count, median annualized revenue and members (slug, name, rank, revenue). Example: {"limit":3} -> the first 3 categories with their members. Cost: free (100 calls/day without a key).
search_lessonsReturns builder lessons from every business, each with its business and themes; filter by query and/or theme, limit (max 50). Example: {"theme":"pricing","limit":5} -> 5 pricing lessons and their businesses. Cost: free (100 calls/day without a key).
hub_statsReturns dataset totals: business, ranked and lesson counts, counts per category and tier, median annualized revenue, payment-verified share, latest change date. Example: {} -> {business_count, ranked_count, median_annualized_usd, ...}. Cost: free (100 calls/day without a key).
todays_featureReturns today's featured business (rotates daily): one full profile, same shape as get_business. Example: {} -> one business record. Cost: free (100 calls/day without a key).
get_tagReturns one tag: count, median annualized revenue and members with rank and revenue. Example: {"slug":"vibe-coding"} -> every business tagged vibe-coding. Unknown slug -> isError. Cost: free (100 calls/day without a key).
list_tagsReturns every tag with count, median annualized revenue and members, most used first. Example: {"limit":10} -> the 10 most-used tags. Cost: free (100 calls/day without a key).
export_datasetReturns the Reported AI Revenue Tracker in one call: AI businesses whose figures all come from press coverage, company announcements or filings (reported, not payment-verified), every figure with its as-of date and source_url, plus dated readings. format "csv" ($0.25 USDC via x40
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry lists no source repo, so we cannot match the publisher (mrrledger.com) to the code
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 485 ms (HTTP 200)
No sign-in needed
Read 15 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.17.0) reached the registry 9 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Finance Toolkit, SolidInvoice, Korea Tax Calculator
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
500+ transparent financial methods calculated from raw statements, not third-party endpoints.
Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.
Korean tax calculation and tax-audit judgment MCP: 96 tools with statutory citations.
No README found in the repo