Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
Nothing to run from here
MRR Ledger is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
16
tools declared
remote
at its publisher
—
calls last 7d
What it does
Free, no key: sourced, dated revenue of real AI-agent businesses. Start with search_businesses.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http mrr-ledger-mcp https://mrrledger.com/mcp
# 2 — ask your agent for something these tools do
# search_businesses, get_business, leaderboard and 13 more
MRR Ledger costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MRAll 1 server
mrrledger1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http mrr-ledger-mcp https://mrrledger.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
16 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search sourced agentic businesses by keyword, category, or tier. Matches name, slug, one-liner, tags, what_the_agent_does, and lessons (same haystack as /api/v1/search.json). Returns name, slug, one-liner, annualized revenue (USD) and source. Free: 100 tools/call per day, then $0.005 per call via x402. Every figure with full history in one file: export_dataset (CSV $0.25 via x402).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| category | string | no | — |
| tier | string | no | Funding-based, not size-based: venture = raised outside venture money (even if small), indie = bootstrapped/founder-funded, experiment = agent-run or research project. |
| verified_only | boolean | no | Keep only businesses whose headline figure is payment-processor verified (headline_verification not null). |
| limit | number | no | — |
Get the full sourced record for one business by slug. Free: 100 tools/call per day, then $0.005 per call via x402. All businesses at once: export_dataset (JSONL $0.50 via x402).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
Top agentic businesses ranked by most recent publicly reported annualized revenue. Free: 100 tools/call per day, then $0.005 per call via x402. Whole dataset as CSV: export_dataset ($0.25 via x402).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | — |
| verified_only | boolean | no | Keep only businesses whose headline figure is payment-processor verified (headline_verification not null). |
| limit | number | no | — |
Today's featured agentic business with lessons for builders. Free: 100 tools/call per day, then $0.005 per call via x402.
No parameter schema on file.
Dated annualized revenue points (ARR/MRR/Revenue) for one business. Returns empty series if fewer than 2 sourced dates. Free: 100 tools/call per day, then $0.005 per call via x402. Full dated history for every business: export_dataset (CSV $0.25 via x402).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
Search lessons for builders drawn from every business (attributed, with keyword auto-tagged themes). Filter by free-text query (matches lesson text, business name, slug) and/or theme. Returns total matches, the theme rules, and up to limit lessons with profile URLs. Free: 100 tools/call per day, then $0.005 per call via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| theme | string | no | Theme id (pricing, growth, enterprise, trust, product, ops, other); labels like "Trust & sourcing" are accepted too. |
| limit | number | no | Default 10, max 50. |
Dataset change log, newest first: businesses added, new sourced data points (with source_url), revisions and re-dated points. Filter by since (YYYY-MM-DD, inclusive, America/Toronto dates), slug, and kind. Free: 100 tools/call per day, then $0.005 per call via x402. Get each new figure pushed instead: watch_revenue (webhook, $1 per business per 30 days via x402).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | string | no | YYYY-MM-DD |
| slug | string | no | — |
| kind | string | no | — |
| limit | number | no | Default 20, max 100. |
Side-by-side compare of two sourced businesses by slug. Returns briefs (name, tier, category, annualized revenue + basis, pricing model, founded, top lessons, growth series) and a diff (annualized_a/b, ratio, same_category, same_tier). Same slug is allowed. Free: 100 tools/call per day, then $0.005 per call via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| a | string | yes | First business slug |
| b | string | yes | Second business slug |
Compact hub totals: business/ranked/chartable/lesson counts, category and tier counts, source-sync-stale and older-figure counts, median annualized among ranked, payment-verified headline count/share (verified_headline_count, verified_headline_share, by processor), latest changelog date, today's feature slug, MCP tool count. No arguments. Free: 100 tools/call per day, then $0.005 per call via x402
No parameter schema on file.
List every category with count, ranked_count, median_annualized_usd (among ranked members), median_annualized_by_tier (venture/indie/experiment split), and members (slug, name, global rank, annualized_revenue_usd, revenue_disclosed, url_profile). Optional limit caps how many categories are returned (default all). Free: 100 tools/call per day, then $0.005 per call via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max categories to return (default: all). |
List every free-text tag (from business tags[]) with slug, label, count, ranked_count, median_annualized_usd (among ranked members), median_annualized_by_tier (venture/indie/experiment split), and members (slug, name, global rank, annualized_revenue_usd, revenue_disclosed, url_profile). Sorted by count desc then label. Optional limit caps how many tags are returned (default all). Includes n=1 tags
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max tags to return (default: all). |
Get one tag's insights by slug from the built tags.json (count, ranked_count, median_annualized_usd, median_annualized_by_tier, members, url_page). Same shape as one list_tags result. Missing slug → isError. Free: 100 tools/call per day, then $0.005 per call via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Tag slug (e.g. trustmrr, mcp, seo). |
Get one category's insights by slug (or id) from the built categories.json (label, count, ranked_count, median_annualized_usd, median_annualized_by_tier, members with global rank, url_page). Same shape as one list_categories result. Missing slug → isError. Free: 100 tools/call per day, then $0.005 per call via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Category slug (e.g. coding-agents, customer-support, indie-solo). |
The whole MRR Ledger dataset in one call. format "csv" ($0.25 USDC via x402): every sourced revenue figure for every business, superseded ones included (one row per figure, 14 columns, source_url on each). format "jsonl" ($0.50): one full business record per line. Optional slug = one business, same price. Included with Builder (csv) and Team (csv + jsonl) API keys. Call without payment for a free
| Parameter | Type | Required | Notes |
|---|---|---|---|
| format | string | no | — |
| slug | string | no | Optional: one business slug |
Buy an expiring MRR Ledger API key with x402 (USDC on Base). Prices: hobby 1 day $0.50, hobby 30 days $9, builder 30 days $19 (adds CSV export + 5 watches), team 30 days $79 (adds JSONL export + 20 watches). Call without payment for a free preview (what the key unlocks, daily limits) plus the x402 terms, then retry with params._meta["x402/payment"] (x402 v2 or v1 payload).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plan | string | yes | — |
| days | integer | no | — |
Get a signed webhook POST whenever a watched business gets a new or revised revenue figure on MRR Ledger. x402 (USDC on Base): $1 per business per 30 days (at most $5), or $5 for all businesses. Included with Builder and Team API keys (send the key as X-API-Key on the MCP request). Call without payment for a free preview (the latest real revenue changes for those businesses) plus the x402 terms, t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slugs | yes | Business slugs (1-10) or "all" | |
| webhook_url | string | yes | https URL on a public host (port 443) |
| kinds | array | no | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install MRR Ledger or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.17.0 · scanned 30 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest5fe844a5e21dffecd0ac16567ffcc3527d30618c8f06308e266c8b94908a9243
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_businesses | no tags | |
| get_business | no tags | |
| leaderboard | no tags | |
| todays_feature | no tags | |
| get_growth | no tags | |
| search_lessons | no tags | |
| whats_new | no tags | |
| compare_businesses | no tags | |
| hub_stats | no tags | |
| list_categories | no tags | |
| list_tags | no tags | |
| get_tag | no tags | |
| get_category | no tags | |
| export_dataset | no tags | |
| buy_api_pass | state-write | state-write: declares readOnlyHint: false |
| watch_revenue | external-sink | external-sink: keyword "webhook", parameter "webhook", declares readOnlyHint: false, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest5fe844a5e21dffec
Scanned2026-10-30
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.17.0.
1.17.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish MRR Ledger can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.