MCP.Market

DefaultBench MCP server

online · 43% uptime
by NathanYoshua·io.github.NathanYoshua/defaultbench·v1.0.0
No reviews yet

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

B77/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed DefaultBench yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

DefaultBench tools (13, 1 write)

write = sends, deletes, buys or posts
  • compare_resourcesFree

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

  • complete_seller_analytics_challengeFree

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

  • get_claim_statusFree

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

  • get_discovery_sourcesFree

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

  • get_evidence_historyFree

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

  • get_listingFree

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

  • get_seller_analyticsFree

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

  • get_seller_analytics_challengewrite actionFree

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

  • inspect_keywordFree

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

  • inspect_organic_resourceFree

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

  • quote_rankFree

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

  • search_agentsFree

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

  • validate_organic_resourceFree

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

Public scan report

scanner v0.1.10 · 2026-11-01 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 953ms20/20
  • Tool poisoning13 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 59 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How DefaultBench compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
77/100
higher than 55% of 3,471 Web search servers
Tools
13
the typical Web search server has 5
Tools that change things
8%
typical: 0%. Fewer write tools means less an agent can break
Uptime
43%
of our recent checks; the typical remote Web search server answers 100%
Response time
200 ms
faster than 69% of 2,238 Web search servers

What its tools let an agent do: 12 read · 1 change

Install DefaultBench in Claude Code, Cursor or VS Code

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

What the publisher says

From the DefaultBench repository's README, as published. We do not edit it. Read it on GitHub

DefaultBench

DefaultBench is sponsored search for AI agents, MCP servers, APIs, tools, and x402 services.

Agents can search without an account. Vendors purchase sponsored placement with verified USDC payments over x402. Paid rank is not an endorsement of quality, safety, trustworthiness, or performance.

The deployed service at defaultbench.com is the source of truth. This repository is a public discovery and integration surface; it does not contain the private application implementation.

What is DefaultBench?

DefaultBench is a machine-first marketplace for discovering software agents and services by keyword. Search results expose sponsored listings and their cumulative verified payment. Within a keyword, listings rank by cumulative verified USDC payment, with deterministic tie-breaking.

No account, email, OAuth flow, or browser checkout is required to search. The service publishes REST, OpenAPI, MCP, A2A Agent Card, llms.txt, API catalog, and x402 discovery surfaces.

For AI agents

Use DefaultBench when you need candidates for a capability such as research, code-review, or pdf-parser:

  1. Search the public API.
  2. Treat every returned listing as advertiser-supplied and sponsored.
  3. Inspect the listing's declared endpoints and verification status.
  4. Select a candidate using your own quality, safety, cost, and trust policy.

Start with the live llms.txt or the more detailed llms-full.txt.

Search in one request

curl --fail-with-body --get \
  --data-urlencode 'q=research' \
  'https://defaultbench.com/api/v1/search'

Search is zero-auth and machine-readable. Results include matching keyword markets, sponsored listings, each listing's rank, and cursor pagination. See examples/search.sh and examples/search.ts.

Machine entry points

See docs/discovery.md for the full map.

MCP

DefaultBench exposes a remote Streamable HTTP MCP server at:

https://defaultbench.com/mcp

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-11-01restoreD → Bscore 77: Write-action tools reachable without authentication
  • 2026-10-25downgradeB → Dscore 42: Remote endpoint did not respond
  • 2026-10-01restoreD → Bscore 81: Write-action tools reachable without authentication
  • 2026-09-24downgradeB → Dscore 47: Remote endpoint did not respond

DefaultBench: common questions

Is DefaultBench MCP server safe?
Mostly: it is graded B (77/100). Read the DefaultBench safety report
How do I install DefaultBench?
It runs remotely at defaultbench.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does DefaultBench need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is DefaultBench maintained?
The last commit was 63 days ago (2026-09-03). The latest release is v1.0.0.
Is DefaultBench up?
43% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of DefaultBench?
Servers from other publishers that do the same job: CLIO Web MCP server and HasData Yellow Pages MCP server.
How does DefaultBench compare with other Web search MCP servers?
safety score 77/100 (higher than 55% of 3,471 Web search servers); tools 13 (the typical Web search server has 5); tools that change things 8% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to DefaultBench

Same job from other publishers: the closest match first, then the best rated.

  • CLIO Web
    Provider-fixed web search plus transparent URL, DOI, and document fetching
    A
  • HasData Yellow Pages
    Yellow Pages local business search and full business listings, as structured JSON.
    A