# MRR Ledger (remote · mrrledger.com)

Free, no key: sourced, dated revenue of real AI-agent businesses. Start with search_businesses.

- Trust score: 80/100 (high trust)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `mrrledger.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/com-mrrledger-mrrledger/mrrledger.md), [page](https://verifymcp.io/servers/com-mrrledger-mrrledger/mrrledger)

## Channel facts

- Endpoint: `https://mrrledger.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.17.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-06.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2476 tokens (~130/item across 19 items; 15 tools + 4 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability check failed: schema churn in the 18 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% of tool parameters carry a description.
  - Structured output schemas are declared (93% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the MRR Ledger MCP server?

MRR Ledger is a hosted endpoint at https://mrrledger.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-mrrledger-mrrledger 'https://mrrledger.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-mrrledger-mrrledger": {
      "url": "https://mrrledger.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-mrrledger-mrrledger": {
      "type": "http",
      "url": "https://mrrledger.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-mrrledger-mrrledger]
url = "https://mrrledger.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-mrrledger-mrrledger": {
      "type": "remote",
      "url": "https://mrrledger.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-mrrledger-mrrledger --url 'https://mrrledger.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-mrrledger-mrrledger:
    url: "https://mrrledger.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-mrrledger-mrrledger": {
      "Transport": "http",
      "Url": "https://mrrledger.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-mrrledger-mrrledger -t streamable-http -u 'https://mrrledger.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-mrrledger-mrrledger": {
      "type": "http",
      "url": "https://mrrledger.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-06 (score 80, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-11-04 (score 79, +1)

- [functional regression] Prompt “biggest_revenue_jumps” was removed
- [functional regression] Resource “biggest-revenue-jumps” was removed

### 2026-11-02 (score 78, +5)

- [security improvement] HTTPS: unverified → pass
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “export_dataset” rewrote its description, which is the text the model reads

### 2026-11-01 (score 73, 0)

- [security] Tool “export_dataset” rewrote its description, which is the text the model reads

### 2026-10-31 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33.

### 2026-10-29 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 26.

### 2026-10-27 (score 71, +1)

- [functional] New prompt “biggest_revenue_jumps”
- [functional] New resource “biggest-revenue-jumps”

### 2026-10-26 (score 70, 0)

- [security] Tool “get_business” rewrote its description, which is the text the model reads
- [security] Tool “get_tag” rewrote its description, which is the text the model reads
- [security] Tool “leaderboard” rewrote its description, which is the text the model reads
- [security] Tool “search_businesses” rewrote its description, which is the text the model reads
- [functional improvement] Tool coverage: 91% → 97%
- [cosmetic] “get_tag” reworded the description of “slug”
- [cosmetic] “search_businesses” reworded the description of “query”
- [cosmetic] “whats_new” reworded the description of “kind”
- [cosmetic] “whats_new” reworded the description of “since”
- [cosmetic] “whats_new” reworded the description of “slug”

## MCP tools (15)

### `search_businesses` (~390 tokens)

Search businesses (start here)

Use 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":"coding","limit":3} -> 3 coding agents with their sourced revenue. Use it to find or filter businesses (keyword, category, tier, verified_only) when you have no slug; for a pure top-N use leaderboard, for one full record get_business. Each brief: slug, name, category, tier, one_liner, annualized_revenue_usd, basis, confidence, verification_label ("reported, not payment-verified" unless processor-verified), url_profile; + total + next page (offset/cursor, limit max 50). Empty query = all, highest revenue first. Cost: free (100 calls/day without a key).

Input parameters:

- `category` (string): Category slug, e.g. coding-agents, customer-support (see list_categories).
- `cursor` (string): Opaque page token: page.next_cursor from the previous call with the same query and filters.
- `limit` (number): Results per page. Default 10, max 50.
- `offset` (integer): Skip this many matches (page start). Default 0. Use page.next_offset from the previous call.
- `query` (string): Keyword, e.g. "coding", "voice", "sales". Empty = all businesses.
- `tier` (string): 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): Keep only businesses whose headline figure is payment-processor verified (headline_verification not null).

Output parameters:

- `page` (object): Pagination: call again with offset = next_offset (or cursor = next_cursor) while has_more.
- `result` (array)

### `benchmark_business` (~249 tokens)

Benchmark your MRR against category peers

Use 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 customer-support MRR peers + 1 comparable. Also: N, basis, verification date, peer caveat; no growth numbers yet; your MRR is never stored. Cost: free (100 calls/day without a key).

Input parameters:

- `category` (string, required): Category slug, e.g. customer-support, automation-platforms, sales-gtm, indie-solo (see list_categories).
- `full` (boolean): Full answers are paused (paid tier paused while we confirm source permissions); you get the free answer.
- `months_live` (integer): Optional months since launch (0-600). Accepted but ignored for now.
- `mrr` (number, required): Your monthly recurring revenue in USD, e.g. 2000 (greater than 0, at most 100000000). Not stored.
- `report_token` (string): Not used while the paid tier is paused.

Output parameters:

- `result` (object)

### `get_business` (~172 tokens)

Get one business profile

Use 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 (from search_businesses or leaderboard); it is the fullest view: every dated revenue figure (label, value, as_of, source_url), what it does, model, tier, lessons, growth series, related businesses, and the verification_label ("reported, not payment-verified" unless processor-verified). Unknown slug -> isError. Cost: free (100 calls/day without a key).

Input parameters:

- `slug` (string, required): Business slug, e.g. cursor, lovable (from search_businesses or leaderboard).

Output parameters:

- `result` (object)

### `leaderboard` (~184 tokens)

Revenue leaderboard (ranked)

Use 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-agents","limit":5} -> the top 5 coding agents by revenue. Use it for a pure ranking or top-N, optionally per category or verified_only (limit max 50); it has no keyword search, use search_businesses for that. Cost: free (100 calls/day without a key).

Input parameters:

- `category` (string): Category slug, e.g. coding-agents (see list_categories).
- `limit` (number): Default 10, max 50.
- `verified_only` (boolean): Keep only businesses whose headline figure is payment-processor verified (headline_verification not null).

Output parameters:

- `result` (array)

### `compare_businesses` (~118 tokens)

Compare two businesses

Use 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":"lovable"} -> Cursor vs Lovable with the revenue ratio. Cost: free (100 calls/day without a key).

Input parameters:

- `a` (string, required): First business slug
- `b` (string, required): Second business slug

Output parameters:

- `result` (object)

### `get_growth` (~108 tokens)

Revenue over time (one business)

Use 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. Unknown slug -> isError. Cost: free (100 calls/day without a key).

Input parameters:

- `slug` (string, required): Business slug, e.g. lovable.

Output parameters:

- `result` (object)

### `whats_new` (~217 tokens)

What changed in the data

Use 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). Example: {"since":"2026-10-14"} -> every change since Oct 14, 2026. Cost: free (100 calls/day without a key).

Input parameters:

- `kind` (string): Only this kind of change: dataset_created, business_added, business_removed, metric_added, metric_revised, metric_redated, metric_removed. Omit for all kinds.
- `limit` (number): Default 20, max 100.
- `since` (string): Only changes on or after this date, YYYY-MM-DD (e.g. 2026-10-14).
- `slug` (string): Only changes for this business slug, e.g. cursor (slugs come from search_businesses or leaderboard).

Output parameters:

- `result` (object)

### `get_category` (~88 tokens)

Get one category

Returns 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).

Input parameters:

- `slug` (string, required): Category slug (e.g. coding-agents, customer-support, indie-solo).

Output parameters:

- `result` (object)

### `list_categories` (~72 tokens)

List categories with members

Returns 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).

Input parameters:

- `limit` (number): Max categories to return (default: all).

Output parameters:

- `result` (object)

### `search_lessons` (~133 tokens)

Search builder lessons

Returns 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).

Input parameters:

- `limit` (number): Default 10, max 50.
- `query` (string): Free text, e.g. "outcome-based pricing".
- `theme` (string): Theme id (pricing, growth, enterprise, trust, product, ops, other); labels like "Trust & sourcing" are accepted too.

Output parameters:

- `result` (object)

### `hub_stats` (~70 tokens)

Dataset totals and medians

Returns 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).

Output parameters:

- `result` (object)

### `todays_feature` (~46 tokens)

Today's featured business

Returns 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).

Output parameters:

- `result`

### `get_tag` (~84 tokens)

Get one tag

Returns 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).

Input parameters:

- `slug` (string, required): Tag slug (e.g. vibe-coding, cx, enterprise; see list_tags).

Output parameters:

- `result` (object)

### `list_tags` (~66 tokens)

List tags with members

Returns 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).

Input parameters:

- `limit` (number): Max tags to return (default: all).

Output parameters:

- `result` (object)

### `export_dataset` (~152 tokens)

Reported AI Revenue Tracker export (paid, x402)

Returns 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 x402) or "jsonl" ($0.50); optional slug = one business, same price. Unpaid call = free preview + exact terms; nothing is charged without a signed payment. Free 10-row preview: https://mrrledger.com/data/reported/?ref=mcptool

Input parameters:

- `format` (string)
- `slug` (string): Optional: one business slug (tracker businesses only)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-mrrledger-mrrledger/mrrledger#diagnostics

## Score history

- 2026-11-06: 80
- 2026-11-05: 79
- 2026-11-04: 79
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 73
- 2026-10-31: 73
- 2026-10-30: 72
- 2026-10-29: 72
- 2026-10-28: 71
- 2026-10-27: 71
- 2026-10-26: 70
- 2026-10-25: 70
- 2026-10-24: 70
- 2026-10-23: 62
- 2026-10-22: 62
- 2026-10-21: 61
- 2026-10-20: 60
- 2026-10-19: 60

## Common questions

### What is the MRR Ledger MCP server?

MRR Ledger is an MCP server listed in the public MCP registry as com.mrrledger/mrrledger. Free, no key: sourced, dated revenue of real AI-agent businesses. Start with search_businesses. This page covers its hosted endpoint (https://mrrledger.com/mcp).

### Is the MRR Ledger MCP server safe to use?

MRR Ledger scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the MRR Ledger MCP server expose?

MRR Ledger exposes 15 tools: search_businesses, benchmark_business, get_business, leaderboard, compare_businesses, and 10 more. Their descriptions and schemas cost roughly 2,149 tokens of context every time the server is loaded.

### Does the MRR Ledger MCP server require authentication?

No. We connected to MRR Ledger without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the MRR Ledger MCP server still maintained?

MRR Ledger is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the MRR Ledger MCP server?

VerifyMCP ran 13 checks on MRR Ledger, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mrrledger.com/mcp
- Website: https://mrrledger.com/for-agents/
- Changelog RSS feed: https://verifymcp.io/servers/com-mrrledger-mrrledger/mrrledger.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-mrrledger-mrrledger/mrrledger/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-mrrledger-mrrledger/mrrledger.json
- HTML version of this page: https://verifymcp.io/servers/com-mrrledger-mrrledger/mrrledger