Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

DefaultBench

REMOTE · DEFAULTBENCH.COM · SCANNED SEP 20

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

Available components

+3 this week 73 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability77
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 797 tokens (~56/item across 14 items; 13 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management60
  • Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the DefaultBench MCP server?

DefaultBench is a hosted endpoint at https://defaultbench.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.

remote · defaultbench.com

# add to Claude Code
claude mcp add --transport http nathanyoshua-defaultbench 'https://defaultbench.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "nathanyoshua-defaultbench": {
      "url": "https://defaultbench.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "nathanyoshua-defaultbench": {
      "type": "http",
      "url": "https://defaultbench.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.nathanyoshua-defaultbench]
url = "https://defaultbench.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nathanyoshua-defaultbench": {
      "type": "remote",
      "url": "https://defaultbench.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add nathanyoshua-defaultbench --url 'https://defaultbench.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  nathanyoshua-defaultbench:
    url: "https://defaultbench.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "nathanyoshua-defaultbench": {
      "Transport": "http",
      "Url": "https://defaultbench.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add nathanyoshua-defaultbench -t streamable-http -u 'https://defaultbench.com/mcp'
// mcp.json
{
  "mcpServers": {
    "nathanyoshua-defaultbench": {
      "type": "http",
      "url": "https://defaultbench.com/mcp"
    }
  }
}

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

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Sept 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 276 → 797 functional
    • Server version: 1.0.0 → 1.1.0 functional
    • New tool “compare_resources” functional
    • New tool “complete_seller_analytics_challenge” functional
    • New tool “get_claim_status” functional
    • New tool “get_discovery_sources” functional
    • New tool “get_evidence_history” functional
    • New tool “get_seller_analytics” functional
    • New tool “get_seller_analytics_challenge” functional
    • New tool “inspect_organic_resource” functional
    • New tool “validate_organic_resource” functional
    • “search_agents” added an optional parameter “category” cosmetic
    • “search_agents” added an optional parameter “freshness” cosmetic
    • “search_agents” added an optional parameter “min_success_rate” cosmetic
    • “search_agents” added an optional parameter “protocol” cosmetic
    • “search_agents” added an optional parameter “sort” cosmetic
    • “search_agents” added an optional parameter “source” cosmetic
    • “search_agents” added an optional parameter “tool” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://defaultbench.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=defaultbench.com CN=YR2,O=Let's Encrypt,C=US 2 Sept 2026 1 Dec 2026 RSA 2048 SHA256-RSA 631b7c4a58741758bf8be219b9ed138e1e4
SANs: defaultbench.com
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of defaultbench.com. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
defaultbench.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; base-uri 'none'; object-src 'none'; frame-ancestors 'none'; form-action 'self'; img-src 'self' data:; font-src 'self'; style-src 'self' 'unsafe-inline'; script-src 'self' 'unsafe-inline'; connect-src 'self'; upgrade-insecure-requests
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://defaultbench.com/mcp Verified 200
http (plaintext) http://defaultbench.com/mcp HTTPS enforced 308 https://defaultbench.com/mcp
MCP tools · 13 exposed · ~645 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
compare_resources ~30

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

NameTypeReqDescription
resourcesarrayyes
NameTypeReqDescription
resultyes

No examples provided.

complete_seller_analytics_challenge ~53

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

NameTypeReqDescription
challenge_idstringyes
listing_idstringyes
wallet_signaturestringyes
NameTypeReqDescription
resultyes

No examples provided.

get_claim_status ~39

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

NameTypeReqDescription
resource_idstringyes
NameTypeReqDescription
resultyes

No examples provided.

get_discovery_sources ~28

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultyes

No examples provided.

get_evidence_history ~64

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

NameTypeReqDescription
cursorstring
idstringyes
limitinteger
subject_typestringyes
NameTypeReqDescription
resultyes

No examples provided.

get_listing ~33

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

NameTypeReqDescription
idstringyes
NameTypeReqDescription
resultyes

No examples provided.

get_seller_analytics ~73

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

NameTypeReqDescription
access_tokenstringyes
fromstring
granularitystring
listing_idstringyes
tostring
NameTypeReqDescription
resultyes

No examples provided.

get_seller_analytics_challenge ~56

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

NameTypeReqDescription
listing_idstringyes
wallet_addressstringyes
NameTypeReqDescription
resultyes

No examples provided.

inspect_keyword ~42

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

NameTypeReqDescription
cursorstring
keywordstringyes
limitinteger
NameTypeReqDescription
resultyes

No examples provided.

inspect_organic_resource ~36

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

NameTypeReqDescription
idstringyes
NameTypeReqDescription
resultyes

No examples provided.

quote_rank ~37

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

NameTypeReqDescription
keywordstringyes
walletstring
NameTypeReqDescription
resultyes

No examples provided.

search_agents ~113

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

NameTypeReqDescription
categorystring
cursorstring
freshnessstring
limitinteger
min_success_ratenumber
organic_cursorstring
protocolstring
querystringyes
sortstring
sourcestring
toolstring
NameTypeReqDescription
resultyes

No examples provided.

validate_organic_resource ~41

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

NameTypeReqDescription
resource_idstringyes
NameTypeReqDescription
resultyes

No examples provided.

Common questions

What is the DefaultBench MCP server?

DefaultBench is an MCP server listed in the public MCP registry as io.github.NathanYoshua/defaultbench. Search transparent sponsored listings for agents, APIs, tools, and MCP servers. This page covers its hosted endpoint (https://defaultbench.com/mcp).

Is the DefaultBench MCP server safe to use?

DefaultBench scores 73 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 DefaultBench MCP server expose?

DefaultBench exposes 13 tools: search_agents, get_evidence_history, compare_resources, get_discovery_sources, inspect_organic_resource, and 8 more. Their descriptions and schemas cost roughly 645 tokens of context every time the server is loaded.

Does the DefaultBench MCP server require authentication?

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

Is the DefaultBench MCP server still maintained?

DefaultBench is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.