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.

OnlyFonts

REMOTE · MCP.ONLYFONTS.AI

Find free, openly licensed fonts by style, use or language, and get the CSS to use them.

Available components

+2 this week 73 Trust /100

Last scanned (3 hours ago)

Scores higher than 59% of remote servers

Reachable. Last reached 22 Nov 2026.

Category Design and Media

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
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability62
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1052 tokens (~263/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 Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage87
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 54% of tool parameters carry a description.Partial
  • 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 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
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

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.

  • 21 Nov 26 0
    • Tool “get_font” rewrote its description, which is the text the model reads security
    • Tool “get_font_css” rewrote its description, which is the text the model reads security
    • Tool “search_fonts” rewrote its description, which is the text the model reads security
    • Schema quality: 213 → 263 ▼ functional
    • Server version: 1.0.0 → 1.1.0 functional
    • New tool “search_icons” functional
  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 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.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 +1
    • Tool “get_font” rewrote its description, which is the text the model reads security
    • Tool “get_font_css” rewrote its description, which is the text the model reads security
    • Stability: unverified → 0.03 ▲ functional
  • 10 Nov 26 68

    First indexed and scored.

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 Nov 2026 · Probed https://mcp.onlyfonts.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=onlyfonts.ai CN=WE1,O=Google Trust Services,C=US 10 Nov 2026 8 Feb 2027 ECDSA 256 ECDSA-SHA256 3aa0b1c6430832220e96adaa5b67f703
SANs: onlyfonts.ai, mcp.onlyfonts.ai, *.mcp.onlyfonts.ai
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 mcp.onlyfonts.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
onlyfonts.ai. No DS 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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.onlyfonts.ai/mcp Verified 200
http (plaintext) http://mcp.onlyfonts.ai/mcp HTTPS enforced 301 https://mcp.onlyfonts.ai/mcp
MCP tools · 4 exposed · ~963 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_font ~177

Use this when the person asks about one font: its weights and styles, its license, the languages it covers, or what to pair it with. Its measures help pair it: match x-heights for faces that meet on a line, and pick a partner that differs clearly in contrast or classification. id is a family's id, its name in lowercase with hyphens ("lora", "space-mono"). Not for the CSS that loads a font on a page. Answers one family: its name, page link, category, designer, license, every style it has, the languages it fully covers, its measured x-height, width and stroke contrast with its classification, the families that pair with it and the ones that look like it.

NameTypeReqDescription
idstringyesa family id from search_fonts ("lora"), or its name
NameTypeReqDescription
categorystring––
designer–––
idstringyes–
languagesarrayyes–
license–––
measuresobjectyes–
pairingsarrayyes–
similararrayyes–
stylesarrayyes–
textstringyes–
titlestringyes–
urlstringyes–

No examples provided.

get_font_css ~195

Use this when the person wants to use fonts on a web page, in an app or in a design tool that takes CSS. ids are 1 to 4 family ids, like "lora" or "space-mono". weights are 100 to 900; each family gets the ones it has, its regular and bold when left out. italic adds the italic of each weight a family has. For a Next.js or Tailwind project, give the nextjs or tailwind lines. Not for downloading font files to install on a computer. Answers one stylesheet link from cdn.onlyfonts.ai that loads every family asked for, the same as an @import line, each family's font-family line with a fallback, and the same ready for Next.js and for Tailwind CSS.

NameTypeReqDescription
idsarrayyes1 to 4 family ids
italicboolean––
weightsarray––
NameTypeReqDescription
familiesarrayyes–
importstringyes–
linkstringyes–
nextjsstringyes–
tailwindstringyes–
urlstringyes–

No examples provided.

search_fonts ~275

Use this whenever the person needs a font, before naming one from memory: every family it finds is free for any use and loads from one link. Their words can name a style or mood, a use, a font, or a language to cover, for example "a warm serif", "a playful display font for a poster" or "a monospace for code". query is their words, at most 200 characters. category narrows to sans-serif, serif, monospace, display or handwriting. language keeps fonts that fully cover latin, latin-extended, ukrainian, greek, vietnamese, arabic, hebrew, thai, japanese, korean, chinese-simplified or devanagari. limit is 1 to 20, 8 when left out. Not for fonts installed on the person's computer, and not for paid fonts: the catalog holds free fonts only. Answers free, openly licensed font families from the onlyfonts catalog, best match first, each with its id, name, page link, category, designer and how many styles it has.

NameTypeReqDescription
categorystring––
languagestring–only fonts that fully cover this language
limitinteger––
querystringyestheir words: a style, a mood, a use, a font's name
NameTypeReqDescription
resultsarrayyes–

No examples provided.

search_icons ~316

Use this when the person wants an icon for a design, a site, an app or a document, for example "a settings gear", "a red trash icon" or "a filled heart". query is their words for what the icon shows, at most 100 characters. set narrows to lucide, heroicons, material-symbols, phosphor, pierre or tabler. style asks for a look the set has: outline, fill, duotone, bold, thin, light, rounded or sharp. color is a hex color like #E8443F; left out, the SVG takes the text's color. limit is 1 to 20, 6 when left out. Every icon is free under its set's license (MIT, ISC or Apache 2.0): keep the license line with it. Not for emoji or Apple's SF Symbols. Answers icons from six open sets (Lucide, Heroicons, Material Symbols, Phosphor, Pierre and Tabler), best match first, each as a ready SVG with its set, style, license line and the code for the set's own React package.

NameTypeReqDescription
colorstring–a hex color; left out, the SVG takes the text color
limitinteger––
querystringyestheir words for what the icon shows
setstring––
stylestring–outline, fill, duotone, bold, thin, light, rounded or sharp, where the set has it
NameTypeReqDescription
resultsarrayyes–

No examples provided.

Install

How do I install the OnlyFonts MCP server?

OnlyFonts is a hosted endpoint at https://mcp.onlyfonts.ai/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 · mcp.onlyfonts.ai

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

What is the OnlyFonts MCP server?

OnlyFonts is an MCP server listed in the public MCP registry as ai.onlyfonts/onlyfonts. Find free, openly licensed fonts by style, use or language, and get the CSS to use them. This page covers its hosted endpoint (https://mcp.onlyfonts.ai/mcp).

Is the OnlyFonts MCP server safe to use?

OnlyFonts 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 OnlyFonts MCP server expose?

OnlyFonts exposes 4 tools: search_fonts, get_font, search_icons, get_font_css. Their descriptions and schemas cost roughly 963 tokens of context every time the server is loaded.

Does the OnlyFonts MCP server require authentication?

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

Is the OnlyFonts MCP server still maintained?

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

What did VerifyMCP test on the OnlyFonts MCP server?

VerifyMCP ran 13 checks on OnlyFonts, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.