DefaultBench MCP Server

by nathanyoshua Your server? Claim it

answering

DefaultBench is answering right now. Last checked 5 min ago. It exposes 13 tools. Last commit 2 Sep 2026.

Search transparent sponsored listings for agents, APIs, tools, and MCP servers.

Uptime history 17 days of history · worst day 28%

17 days agonow

55.4%

Uptime 24h

51 of 92 checks

Tools

read from the server

446 ms

Response time

average over 24h

Stars

last commit 2 Sep 2026

What changed 10

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 3 September 2026. No other catalogue keeps this.

3 Sep 9 tools appeared compare_resources, complete_seller_analytics_challenge, get_claim_status and 6 more

3 Sep a tool changed the parameters it asks for search_agents

DefaultBench does not always answer

Over the last week it answered 47.5% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "defaultbench": {
      "url": "https://defaultbench.com/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.defaultbench]
url = "https://defaultbench.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "defaultbench": {
      "url": "https://defaultbench.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "defaultbench": {
      "url": "https://defaultbench.com/mcp"
    }
  }
}

Available tools 13

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

inspect

inspect_keyword

Return the keyword summary and deterministic ranking ordered by cumulative verified payment.

inspect_organic_resource

Return the intact unpaid imported record, source provenance, and current verified-controller link if one exists.

seller

get_seller_analytics

Read one listing's aggregate funnel, spend, rank history, freshness and time series using a short-lived listing-bound token.

get_seller_analytics_challenge

Create a one-time EIP-712 challenge for the listing's verified payer or current verified controller. This creates no account or cookie.

agents

search_agents

Search local inventory. Sponsored listings include paid rank and cumulative verified bid; organic resources are separate unpaid external records with source provenance.

claim

get_claim_status

Return the current time-limited domain and wallet controller link. Claim status does not affect paid rank or quality.

compare

compare_resources

Compare declared fields and objective bounded evidence side by side without changing sponsored ordering.

complete

complete_seller_analytics_challenge

Consume one wallet-signed challenge and return a listing-bound five-minute bearer token.

discovery

get_discovery_sources

Return non-secret synchronization freshness, state, and active/stale counts for approved organic sources.

evidence

get_evidence_history

Return declared provenance plus timestamped bounded conformance and reliability observations. Evidence is not trust, safety, quality, or endorsement.

listing

get_listing

Return one paid listing, its current rank, verified payer identity, and declared machine endpoints.

quote

quote_rank

Calculate informational minimum additions for higher positions. Final rank is determined at settlement.

validate

validate_organic_resource

Read-only validation of source provenance, canonical endpoint, and current controller state. It never creates a listing or payment.

Endpoints

URL	Transport	State	Latency	Checked
https://defaultbench.com/mcp	streamable-http	answering	364 ms	5 min ago

Alternatives to DefaultBench

same job, measured the same way

Clarvia

by digitamaz

AI agent tool discovery and scoring. Search 15,400+ MCP servers, APIs, and CLIs.

77 installs/wk local only

Agenticorg

by mishrasanjeev

AgenticOrg MCP server for AI agents, A2A discovery, SOP deploy, and MCP tool listing.

42 installs/wk local only

YouTube Transcript & Search MCP Server

by transcriptout

YouTube transcripts, search, channels, playlists and bulk transcript jobs for AI agents. 14 tools.

14 tools answering

A2asearch MCP

by tadas-github

Search 10,000+ AI agents, MCP servers, and CLI tools via A2ASearch from any MCP client.

1 080 installs/wk local only

travelMCP Directory

by omnitravel

Search MCP servers, agent skills and APIs for travel: hotel ID mapping, rates, rooms.

3 tools answering

AgentRank

by superlowburn

Search and compare MCP servers, agent tools, and skills using current maintenance signals.

42 installs/wk 5 tools answering

Vaultguard MCP

by kota1026

VaultGuard MCP Server - Yearn V3 / DeFi vault security and analysis tools for AI coding agents....

25 installs/wk local only

mcp-audit

by firatmio

Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.

33 installs/wk local only

DefaultBench — questions

Answers built from our own checks of this server.

What can DefaultBench do?

It exposes 13 tools, read directly from the server on our last check. Among them: compare_resources, complete_seller_analytics_challenge, get_claim_status, get_discovery_sources, get_evidence_history, get_listing and 7 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is DefaultBench mostly used for?

Its tools cluster around inspect and seller. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is DefaultBench working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 51 of 92 checks got a reply (55.4%), average response time 446 ms. The bar chart above shows every period we have measured.

How do I connect DefaultBench?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does DefaultBench need an API key?

No. DefaultBench completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 13 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is DefaultBench?

It answers our handshake in 446 ms on average, which is faster than 33% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is DefaultBench open source?

Yes — it is published under the MIT licence and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.