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.

Fudge for Shopify

REMOTE · MCP.FUDGE.AI

Run your Shopify store with AI: drafts you approve, what to fix, and how your store is doing.

Available components

+3 this week 70 Trust /100

Last scanned (13 hours ago)

Scores higher than 54% of remote servers

Reachable. Last reached 21 Nov 2026.

Category E-commerce

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 Usability72
  • 89% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 11543 tokens (~167/item across 69 items; 68 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 Management37
  • Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 77% of tool parameters carry a description.Partial
Tool Safety92
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 2 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "request_publish_review" implies "publish" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 70 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
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

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

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.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “check_page” rewrote its description, which is the text the model reads security
    • Tool “check_page_speed” rewrote its description, which is the text the model reads security
    • Tool “find_context” rewrote its description, which is the text the model reads security
    • Tool “read_store_document” rewrote its description, which is the text the model reads security
    • Tool “read_work” rewrote its description, which is the text the model reads security
    • Schema quality: 145 → 167 ▼ functional
    • New prompt “seo_queue” functional
    • New tool “read_store_activity” functional
    • New tool “run_seo_tool” functional
  • 18 Nov 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.

  • 17 Nov 26 0
    • Tool “get_store_audit_result” rewrote its description, which is the text the model reads security
    • Tool “list_store_audits” rewrote its description, which is the text the model reads security
    • Tool “run_ai_readiness_check” rewrote its description, which is the text the model reads security
    • Tool “run_catalog_data_audit” rewrote its description, which is the text the model reads security
    • New tool “list_audit_runs” functional
    • New tool “read_audit_evidence” functional
  • 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.

  • 14 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “list_store_audits” rewrote its description, which is the text the model reads security
    • Schema quality: 7784 → 9344 ▼ functional
    • New prompt “bfcm_readiness” functional
    • New tool “check_ai_visibility” functional
    • New tool “check_product_schema” functional
    • New tool “find_missing_pages” functional
    • New tool “find_page_two_pages” functional
    • New tool “record_discovery_source” functional
    • New tool “run_bfcm_audit” functional
    • New tool “run_seo_report” functional
  • 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.

  • 12 Nov 26 0
    • Tool “edit_draft_file” rewrote its description, which is the text the model reads security
    • Tool “list_offers” rewrote its description, which is the text the model reads security
    • Tool “read_draft_file” rewrote its description, which is the text the model reads security
    • “write_draft_file” reworded the description of “content” 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 21 Nov 2026 · Probed https://mcp.fudge.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.fudge.ai CN=YR1,O=Let's Encrypt,C=US 6 Nov 2026 4 Feb 2027 RSA 2048 SHA256-RSA 640c8fb90e6889caeae1f68a57b45d2d534
SANs: mcp.fudge.ai
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
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 mcp.fudge.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
fudge.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
Header Value
strict-transport-security max-age=63072000

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.fudge.ai/mcp Verified 200
http (plaintext) http://mcp.fudge.ai/mcp HTTPS enforced 308 https://mcp.fudge.ai/mcp
MCP tools · 68 exposed · ~11,127 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
run_knowledge_base_check ~149

Run Fudge’s free Shopify Knowledge Base report: 15 shopper questions with the exact answers, gaps and conflicts with published information. Takes 2–5 minutes and waits up to 45 seconds. Returns a run in progress or a result from the last 24 hours unless `fresh` is true.

NameTypeReqDescription
domainstring–The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
freshboolean–Start a new run even when a result from the last 24 hours exists.
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

run_seo_report ~252

Run Fudge’s free SEO report on a Shopify store: a score out of 100 averaged from its page-two, missing-pages, AI-visibility and product-schema audits, which it runs together, and a short list of what to do first. It adds the store’s Google ranking counts, whether Google can read the store (robots.txt, home page title, theme files), buttons on the home page and one product page that lead nowhere, how its articles rank, real-visitor phone speed from the Chrome UX Report and one improved title previewed as a Google result. Free, no sign-in; waits up to 45 seconds, and the full report takes about 3–7 minutes. Shared per store for a day; anything not measured is reported as unknown.

NameTypeReqDescription
countrystring–The market to check, as a two-letter ISO country code such as GB. Omit it for the store’s main market.
domainstring–The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

run_seo_tool ~1,224

Run one of Fudge’s SEO lookups for the store by id, with the same result the merchant gets from Fudge, such as a keyword lookup. A paid lookup spends the store’s daily SEO tool budget, shared with the merchant and Fudge’s agents, and is refused once it is used up. A long result comes a page at a time: pass its `nextCursor` back as `cursor` with the same id to read the next page for free, without running the lookup again.

NameTypeReqDescription
cursorstring–A nextCursor this tool returned: reads the next page of that run, free; input is ignored
idstringyeskeyword-lookup: Keyword lookup: monthly searches, difficulty and who ranks on Google for one search in one country; check-page: Check a page: one store page’s server HTML against the page checks (pag…
inputobject–Fields by tool: keyword-lookup: keyword, country; check-page: page; is-indexed: page; check-product: product; speed-test: page; rich-result-test: page; set-product-kind: kind, products, vendors, type…
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

search_catalog ~112

Find the store’s products, collections, pages and articles by name or handle, or list them by type. Matches singular, plural and partial words, and returns close matches when nothing matches every word.

NameTypeReqDescription
limitinteger––
offsetinteger––
querystring–Words from the title or handle. Leave empty to list by type in title order.
storestring–The connected store to use. Omit when only one is connected.
typesarray––

No output schema declared.

No examples provided.

search_design_references ~86

Search Fudge’s Lookbook of analysed ecommerce stores, pages and patterns. Describe the shopper problem or page element, not a brand. Use when the merchant wants to see how other stores solve something.

NameTypeReqDescription
industrystring––
limitnumber––
pageKindstring––
querystringyes–
scopestringyes–

No output schema declared.

No examples provided.

search_draft_files ~134

Find theme files in a Fudge draft. With `pattern`, search contents by regular expression; without it, list files matching `paths` globs.

NameTypeReqDescription
draftstringyesThe draft’s fudge://project/… ref.
pathsarrayyesFiles, folders or glob patterns, e.g. ["sections", "snippets/*price*.liquid"].
patternstring–Regular expression (RE2 syntax: no lookarounds or backreferences) to search for in those files.
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

search_guides ~58

Search Fudge’s reference articles on SEO, AI discovery, conversion, merchandising, content, store design and analytics. Returns matching paths and excerpts.

NameTypeReqDescription
querystringyesWhat the merchant wants to do or know, in a few words.

No output schema declared.

No examples provided.

send_feedback ~206

Send the Fudge team a problem with its tools, a capability you needed, or feedback the merchant asked you to pass on.

NameTypeReqDescription
messagestringyesUp to 250 words, starting with a one-line summary. For a problem: what you did, what the tools returned and what would have made it easy. For missing: the task, what you did instead and what the tool…
storestring–The connected store to use. Defaults to the first one.
typestringyesbroken: a Fudge tool failed or did the wrong thing. stuck: you couldn’t finish the task with Fudge’s tools. hard: the tools made the task much harder than it should be. missing: the task needed somet…

No output schema declared.

No examples provided.

set_preview_consent ~106

Record the merchant’s answer from the preview consent card, with the answer code only that card receives.

NameTypeReqDescription
answerstringyesThe answer code from Fudge’s consent card.
draftstringyesThe draft’s fudge://project/… ref.
scopestringyesproject: this draft only; site: every draft.
statestringyes–
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

show_design_references ~48

Show 3–8 Lookbook references as a gallery of screenshots, best first, each with a one-sentence note on why it suits this store.

NameTypeReqDescription
referencesarrayyes–

No output schema declared.

No examples provided.

show_draft ~70

Show a Fudge draft in the side panel with its screenshot, saved time, change count and links. Without a ref, lists recent drafts.

NameTypeReqDescription
refstring–A fudge://project/… ref.
storestring–The connected store to use. Defaults to the first one.

No output schema declared.

No examples provided.

show_preview_consent ~85

Ask the merchant, with a card, whether new products and collections in a draft may be previewed by direct link on their live store. Use when a result says previewing needs their consent.

NameTypeReqDescription
draftstringyesThe draft’s fudge://project/… ref.
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

show_resources ~64

Show Fudge items to the merchant as rows that open in Fudge: work, Plans, findings, recommendations, reports, products and pages.

NameTypeReqDescription
refsarrayyes–
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

start_draft ~216

Open a private Fudge draft to build in directly. Fudge copies the live theme into a draft with its own preview. Give a short title and the storefront `page`, or `work` to continue existing work. `requestId` makes retries create one draft. Use for precise changes you make yourself; needs a Fudge plan that includes building.

NameTypeReqDescription
pagestring–Storefront path the work is about, e.g. /products/blue-runner, /collections/sale or /pages/about. Anchors the preview. Defaults to the home page.
requestIdstringyesA unique ID you choose for this request, e.g. a UUID. Retries reuse it.
storestring–The connected store to use. Omit when only one is connected.
titlestringyesShort merchant-facing name for the work, e.g. “Size guide on product pages”.
workstring–A fudge://project/… ref to continue instead of starting new work.

No output schema declared.

No examples provided.

start_store_builder ~80

Start Fudge’s free AI store builder for someone with a store idea but no store yet. It works out a name, logo and brand, then shows store concepts on Fudge’s website. Returns a link for them.

NameTypeReqDescription
descriptionstringyesThe store idea: what they sell, who for, and anything they’ve said about the brand.

No output schema declared.

No examples provided.

start_website_redesign ~87

Start Fudge’s free website redesign for a Shopify store, which generates three homepage concepts on Fudge’s website. Use when the merchant wants new design directions for their whole site. Returns a link for them.

NameTypeReqDescription
domainstringyesThe Shopify storefront, e.g. example.com.
instructionsstring–What the merchant wants from the redesign, in their words.

No output schema declared.

No examples provided.

stop_work ~87

Stop Fudge’s reply running on one work item. With `runId`, stops only that run. The draft and anything already saved stay.

NameTypeReqDescription
refstringyesThe work’s fudge://thread/… or fudge://project/… ref.
runIdstring––
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

write_draft_file ~197

Create a new theme file in a Fudge draft, or with `replace` rewrite a whole file. New theme filenames include the draft’s file prefix, except templates, config and locales. Every sections/*.liquid file needs a {% schema %} with a non-empty "name".

NameTypeReqDescription
contentstringyesThe complete file content, without line gutters.
draftstringyesThe draft’s fudge://project/… ref.
pathstringyesA theme file such as sections/main-product.liquid or templates/product.json, or a content document such as .entities/product/123.jsonc or .entities/page/45.body.html.
replaceboolean–True to replace an existing file you have read in full.
revisionstring–The revision returned when this file was read, when replacing.
storestring–The connected store to use. Omit when only one is connected.

No output schema declared.

No examples provided.

Install

How do I install the Fudge for Shopify MCP server?

Fudge for Shopify is a hosted endpoint at https://mcp.fudge.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.fudge.ai

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

What is the Fudge for Shopify MCP server?

Fudge for Shopify is an MCP server listed in the public MCP registry as ai.fudge/fudge. Run your Shopify store with AI: drafts you approve, what to fix, and how your store is doing. This page covers its hosted endpoint (https://mcp.fudge.ai/mcp).

Is the Fudge for Shopify MCP server safe to use?

Fudge for Shopify scores 70 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 Fudge for Shopify MCP server expose?

Fudge for Shopify exposes 68 tools: list_stores, record_discovery_source, connect_store, get_store_overview, search_design_references, and 63 more. Their descriptions and schemas cost roughly 11,127 tokens of context every time the server is loaded.

Does the Fudge for Shopify MCP server require authentication?

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

Is the Fudge for Shopify MCP server still maintained?

Fudge for Shopify is still listed as active in the MCP registry. We last reached this channel on 21 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 Fudge for Shopify MCP server?

VerifyMCP ran 14 checks on Fudge for Shopify, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 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.