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.

Triremes

REMOTE · TRIREMES.COM

Search real problems people have and business websites with poor SEO/AEO. Read-only, free.

Available components

+2 this week 71 Trust /100

Last scanned (4 hours ago)

Scores higher than 57% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Marketing and SEO

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 Security74
Transport & Reachability100
Schema Quality & AI Usability56
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 813 tokens (~203/item across 4 items; 4 tools + 0 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 Management33
  • Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.

  • 5 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_website_gap_score” rewrote its description, which is the text the model reads security
    • Tool “search_website_gaps” rewrote its description, which is the text the model reads security
    • “search_website_gaps” reworded the description of “gap_score” cosmetic
    • Tool “get_website_gap_score” changed its title: A website's gap score → A website's SEO score cosmetic
  • 4 Nov 26 0
    • Tool “get_website_gap_score” rewrote its description, which is the text the model reads security
    • Tool “search_problems” rewrote its description, which is the text the model reads security
    • Tool “search_website_gaps” rewrote its description, which is the text the model reads security
    • Schema quality: 174 → 203 ▼ functional
    • Server version: 2025-06-18 → 1.0.0 functional
    • “search_website_gaps” reworded the description of “gap_score” cosmetic
  • 3 Nov 26 −1
    • Tool “search_problems” rewrote its description, which is the text the model reads security
    • Tool “get_website_gap_score” rewrote its description, which is the text the model reads security
    • Tool “search_website_gaps” rewrote its description, which is the text the model reads security
    • Tool “show_samples” rewrote its description, which is the text the model reads security
    • Schema quality: 137 → 174 ▼ functional
    • “search_problems” added an optional parameter “max_sold” cosmetic
    • “search_website_gaps” added an optional parameter “max_sold” cosmetic
  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 1 Nov 26 0
    • Tool “get_website_gap_score” rewrote its description, which is the text the model reads security
  • 30 Oct 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.

  • 28 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 27 Oct 26 0
    • Stability: unverified → 0.03 ▲ 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 5 Nov 2026 · Probed https://triremes.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=triremes.com CN=YE1,O=Let's Encrypt,C=US 22 Oct 2026 20 Jan 2027 ECDSA 256 ECDSA-SHA384 6e752e14a78f0ee58a78b00713cb95fcaa2
SANs: *.triremes.com, triremes.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of triremes.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
triremes.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
content-security-policy default-src 'none'; frame-ancestors 'none'
x-content-type-options nosniff

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://triremes.com/mcp Verified 200
http (plaintext) http://triremes.com/mcp HTTPS enforced 308 https://triremes.com/mcp
MCP tools · 4 exposed · ~738 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
get_website_gap_score ~185

One website on sale by its id (3f9a1c07b2e85d64): its SEO score, the share of Triremes' checks of what search engines can read on its homepage that it fails, weighted by how serious each check is (0% means no gaps; higher is worse), with its label (No gaps, Lightly flawed, Flawed, Badly flawed or Catastrophic), the checks it failed by name, when it was measured, its price, how many times it has been sold and the time of each sale, and its page. A website with no SEO score yet is being measured: being_measured is true, it has no price and it can be bought once it has an SEO score.

NameTypeReqDescription
site_idstringyesThe website's id, as search_website_gaps gives it.

No output schema declared.

No examples provided.

search_problems ~187

Search the problems people have that Triremes lists, biggest first: each with its title, tier, how many reports and when the first and the last were, the day Triremes listed it, its summary as its page shows it, whether it is sold as a lead (businesses that have it) or an idea report, its price, how many times a lead has been sold and when it last was, and its page. Leads and idea reports are bought on that page.

NameTypeReqDescription
cursorstring–The next_cursor of the answer before, for the next page.
kindstring–Only leads, or only idea reports.
max_soldinteger–Only leads sold at most this many times; 0 for those never sold.
querystring–Words to find in a problem's title or summary; empty for every problem.

No output schema declared.

No examples provided.

search_website_gaps ~331

Search the business websites Triremes measured with gaps in what search engines and AI answer engines can read, each one sold on its own: what kind of business and where, its SEO score and its label, the checks it failed by name, when it was measured, its price, how many times it has been sold and when it last was, and its page. The business, its website and its contacts are bought on that page. One with no SEO score yet is being measured (being_measured): no price, and it can be bought once it has an SEO score.

NameTypeReqDescription
businessstring–A kind of business, such as Dentists or Roofing Contractors; when several kinds match, the answer lists them.
citystring–A city.
countrystring–A country, as its two-letter ISO code (US, DE).
cursorstring–The next_cursor of the answer before, for the next page.
gap_scorestring–Only websites with an SEO score in this band: catastrophic (Catastrophic: 100%), badly-flawed (Badly flawed: 50% to 99%), flawed (Flawed: 20% to 49%), lightly-flawed (Lightly flawed: 1% to 19%), no-g…
max_soldinteger–Only websites sold at most this many times; 0 for those never sold.

No output schema declared.

No examples provided.

show_samples ~35

The free sample lead, idea report and website with poor SEO / AEO: what a buyer gets, on pages anyone may read.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Triremes MCP server?

Triremes is a hosted endpoint at https://triremes.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 · triremes.com

# add to Claude Code
claude mcp add --transport http com-triremes-triremes 'https://triremes.com/mcp'
Common questions

What is the Triremes MCP server?

Triremes is an MCP server listed in the public MCP registry as com.triremes/triremes. Search real problems people have and business websites with poor SEO/AEO. Read-only, free. This page covers its hosted endpoint (https://triremes.com/mcp).

Is the Triremes MCP server safe to use?

Triremes scores 71 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 Triremes MCP server expose?

Triremes exposes 4 tools: search_problems, search_website_gaps, get_website_gap_score, show_samples. Their descriptions and schemas cost roughly 738 tokens of context every time the server is loaded.

Does the Triremes MCP server require authentication?

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

Is the Triremes MCP server still maintained?

Triremes is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.