Skip to content

Leaderboard MCP server

Which MCP servers are Leaderboard's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to Leaderboard

Whose server it is
  • Registry namecom.botsrated/botsratedverified in the MCP registry

The registry name sits under botsrated.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools8
  • Server calls itselfbotsrated
  • Server version0.4.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 223 ms.

Should an agent connect itNot proven either way yet
  • Its tools do check whether a paid tool host is up and priced right, but not watch an MCP server's tool list for changes.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 3 of 9 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 5, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it1 of 2 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer246 ms
  • Space in an agent's context≈ 1,653 tokensthe definitions of all its tools (9), which an agent carries on every turn
  • Tool definitionsA · 94 of 100
  • Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 9

What an agent can do with it

  • can do · check whether a paid tool host is up and priced right
  • not sure · warn or block agent payments that differ from measured prices
  • cannot · watch an MCP server's tool list for changes

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers8 tools · read 2026-10-28
  • preflight

    FREE. Is this x402 seller or remote MCP server covered, and what did its latest unpaid probe show? For MCP server hosts: last handshake state (ok, auth_required, handshake_failed, unreachable, or blocked = not contacted because the URL, a…

  • find

    FREE (uses 1 of the 25 free checks per client per UTC day, shared with /v1/check). Top matching covered x402 sellers and remote MCP servers for what you need, each with a one-line factual reason (text match, recent valid 402s or…

  • coverage

    FREE. How many x402 seller hosts and remote MCP servers BotsRated covers (mcp_servers: servers, hosts, probed, last-state counts), from which discovery sources, the probe schedules and when the last probe runs finished.

  • sample

    FREE. Returns a real sample of a paid response (check, report or best) for a fixed example, so you can see exactly what you would buy.

  • check

    PAID $0.001 USDC on Base mainnet via x402 (the first 25 calls per client per UTC day are free over HTTP GET /v1/check). Measured facts for one host (an x402 seller, or a remote MCP server host: handshake state, protocol version, tools…

  • report

    PAID $0.002 USDC on Base mainnet via x402 (the first 3 calls per client per UTC day are free over HTTP GET /v1/report/{host}). Full receipt history for one host (up to 1000 probes plus all paid test-buys). An unpaid call returns an x402…

  • best

    PAID $0.01 USDC on Base mainnet via x402. Top 3 covered providers for a task, sorted by reliability (default), price or latency, with matching routes and the numbers behind the order. An unpaid call returns an x402 v2 PaymentRequired tool…

  • botsrated_policy_check

    FREE, never charged. Your own pass / warn / block rules applied to BotsRated measurements. Private to your plan or org key: until MCP auth ships this tool checks your arguments and answers bearer_required; call POST /v1/policy/check with…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "botsrated": {
      "type": "http",
      "url": "https://botsrated.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http botsrated https://botsrated.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://botsrated.com/mcp as a custom connector in the settings.

OpenAPI spec

27 paths, read 2026-10-28. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.