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.

Second Opinion

REMOTE · SECONDOPINIONX402.COM · SCANNED SEP 22

Adversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402.

0 this week 83 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 Usability87
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 813 tokens (~116/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Second Opinion MCP server?

Second Opinion is a hosted endpoint at https://secondopinionx402.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 · secondopinionx402.com

# add to Claude Code
claude mcp add --transport http com-secondopinionx402-second-opinion 'https://secondopinionx402.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-secondopinionx402-second-opinion": {
      "url": "https://secondopinionx402.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-secondopinionx402-second-opinion": {
      "type": "http",
      "url": "https://secondopinionx402.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-secondopinionx402-second-opinion]
url = "https://secondopinionx402.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-secondopinionx402-second-opinion": {
      "type": "remote",
      "url": "https://secondopinionx402.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-secondopinionx402-second-opinion --url 'https://secondopinionx402.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-secondopinionx402-second-opinion:
    url: "https://secondopinionx402.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-secondopinionx402-second-opinion": {
      "Transport": "http",
      "Url": "https://secondopinionx402.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-secondopinionx402-second-opinion -t streamable-http -u 'https://secondopinionx402.com/mcp'
// mcp.json
{
  "mcpServers": {
    "com-secondopinionx402-second-opinion": {
      "type": "http",
      "url": "https://secondopinionx402.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.

  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +1
    • Stability: 0.97 → pass security
  • 13 Aug 26 0
    • The server now declares the “prompts” capability functional
    • The server now declares the “resources” capability functional
    • First check of Schema quality: 100 functional
    • New prompt “adopt_verification_policy” functional
    • New prompt “verify_before_acting” functional
    • New resource “verification-policy” functional
    • Server version: 0.2.1 → 0.2.2 functional
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 8 Aug 26 0
    • Tool “second_opinion_quick” rewrote its description, which is the text the model reads security
    • Server version: 0.2.0 → 0.2.1 functional
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 22 Sept 2026 · Probed https://secondopinionx402.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=secondopinionx402.com CN=WE1,O=Google Trust Services,C=US 19 Sept 2026 18 Dec 2026 ECDSA 256 ECDSA-SHA256 9859e9c0e62cb9690e2606f81429d756
SANs: secondopinionx402.com, *.secondopinionx402.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of secondopinionx402.com. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
secondopinionx402.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
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data:; font-src 'self'; connect-src 'self'; object-src 'none'; base-uri 'self'; form-action 'self'; frame-ancestors 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://secondopinionx402.com/mcp Verified 200
http (plaintext) http://secondopinionx402.com/mcp HTTPS enforced 301 https://secondopinionx402.com/mcp
MCP tools · 6 exposed · ~759 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
second_opinion_panel ~152

Three independent adversarial verifiers attack the claim through different lenses (evidence, logic, currency) and vote ($0.75, ~90s). Use for high-stakes or contested claims where a single check is not enough. Without a payment argument it returns an exact pay-per-call quote (no account, no API key).

NameTypeReqDescription
claimstringyesThe single claim to verify, stated plainly.
contextstringWhy this claim matters / where it came from.
paymentstringBase64 x402 payment payload built by YOUR wallet for one of the quoted accepts entries (the same string the X-PAYMENT header carries). Omit to receive a machine-readable quote.

No output schema declared.

No examples provided.

second_opinion_pricing ~62

FREE: current tiers, prices, and exact on-chain payment requirements (accepts) for every rail — Algorand, Base, Polygon, Solana. Use this to pre-build a payment, or to discover what a verification will cost before committing.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

second_opinion_quick ~174

Independent reasoning-only check of a claim ($0.02, ~20s, no web research). Use for logic, internal consistency, and stable established knowledge (definitions, architectures, history, maths). Returns refuted/supported/inconclusive with calibrated confidence; honestly escalates to second_opinion_verify when the claim needs current-world research. Without a payment argument it returns an exact pay-per-call quote (no account, no API key).

NameTypeReqDescription
claimstringyesThe single claim to verify, stated plainly.
contextstringWhy this claim matters / where it came from.
paymentstringBase64 x402 payment payload built by YOUR wallet for one of the quoted accepts entries (the same string the X-PAYMENT header carries). Omit to receive a machine-readable quote.

No output schema declared.

No examples provided.

second_opinion_result ~63

Fetch the verdict for a paid async job — polling is FREE and the verdict is already paid for. Returns status running|done|failed, with the full verdict when done.

NameTypeReqDescription
job_idstringyesThe job id returned by a paid verification tool call.

No output schema declared.

No examples provided.

second_opinion_try ~135

FREE TRIAL — no wallet, no payment, no account: the same quick reasoning-only check as second_opinion_quick, 3/day per caller (claims up to 500 chars; global daily cap applies). The trial verdict is unsigned — paid verdicts add an offline-verifiable Ed25519 receipt and live web research on the verify/panel tiers. Try the product here; use the paid tools for real work.

NameTypeReqDescription
claimstringyesThe single claim to verify, stated plainly (free trial: max 500 chars).
contextstringWhy this claim matters / where it came from.

No output schema declared.

No examples provided.

second_opinion_verify ~173

Independent adversarial verification with live web research ($0.20, ~60s). A separate AI attempts to refute the claim using current sources and returns a verdict with citations. Use before irreversible commitments that depend on current-world facts. Without a payment argument it returns an exact pay-per-call quote (no account, no API key).

NameTypeReqDescription
claimstringyesThe single claim to verify, stated plainly.
claimed_sourcesarrayURLs you relied on — they will be scrutinised, not trusted.
contextstringWhy this claim matters / where it came from.
paymentstringBase64 x402 payment payload built by YOUR wallet for one of the quoted accepts entries (the same string the X-PAYMENT header carries). Omit to receive a machine-readable quote.

No output schema declared.

No examples provided.

Common questions

What is the Second Opinion MCP server?

Second Opinion is an MCP server listed in the public MCP registry as com.secondopinionx402/second-opinion. Adversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402. This page covers its hosted endpoint (https://secondopinionx402.com/mcp).

Is the Second Opinion MCP server safe to use?

Second Opinion scores 83 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 Second Opinion MCP server expose?

Second Opinion exposes 6 tools: second_opinion_quick, second_opinion_verify, second_opinion_panel, second_opinion_try, second_opinion_result, second_opinion_pricing. Their descriptions and schemas cost roughly 759 tokens of context every time the server is loaded.

Does the Second Opinion MCP server require authentication?

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

Is the Second Opinion MCP server still maintained?

Second Opinion is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.