# 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.

- Trust score: 70/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.fudge.ai`: 70/100 (this document), [markdown](https://verifymcp.io/servers/ai-fudge-fudge/mcp.md), [page](https://verifymcp.io/servers/ai-fudge-fudge/mcp)

## Channel facts

- Endpoint: `https://mcp.fudge.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (edit_store_document).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - 89% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - 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.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 77% of tool parameters carry a description.
- **Tool Safety**: 92/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 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.
  - An AI judge read all 70 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## 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.

### Claude

```bash
claude mcp add --transport http ai-fudge-fudge 'https://mcp.fudge.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-fudge-fudge": {
      "url": "https://mcp.fudge.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-fudge-fudge": {
      "type": "http",
      "url": "https://mcp.fudge.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-fudge-fudge]
url = "https://mcp.fudge.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-fudge-fudge": {
      "type": "remote",
      "url": "https://mcp.fudge.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-fudge-fudge --url 'https://mcp.fudge.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-fudge-fudge:
    url: "https://mcp.fudge.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-fudge-fudge": {
      "Transport": "http",
      "Url": "https://mcp.fudge.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-fudge-fudge -t streamable-http -u 'https://mcp.fudge.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-fudge-fudge": {
      "type": "http",
      "url": "https://mcp.fudge.ai/mcp"
    }
  }
}
```

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 70, +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.

### 2026-11-19 (score 69, 0)

- [security] 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
- [functional regression] Schema quality: 145 → 167
- [functional] New prompt “seo_queue”
- [functional] New tool “read_store_activity”
- [functional] New tool “run_seo_tool”

### 2026-11-18 (score 69, +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.

### 2026-11-17 (score 68, 0)

- [security] 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
- [functional] New tool “list_audit_runs”
- [functional] New tool “read_audit_evidence”

### 2026-11-15 (score 68, +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.

### 2026-11-14 (score 67, 0)

- [security] 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
- [functional regression] 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”

### 2026-11-13 (score 67, +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.

### 2026-11-12 (score 66, 0)

- [security] 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
- [cosmetic] “write_draft_file” reworded the description of “content”

## MCP tools (68)

### `list_stores` (~18 tokens)

List connected stores

List the Shopify stores this connection can use.

### `record_discovery_source` (~90 tokens)

Save how you found Fudge

Save how the merchant heard about Fudge during setup. Record only their stated answer, or null if they explicitly skip. Never infer the source. Existing answers and skips are preserved; this changes no storefront content.

Input parameters:

- `answer` (required): The merchant’s own answer, or null only if they explicitly skip.
- `store` (string): The connected store to use. Omit when only one is connected.

### `connect_store` (~38 tokens)

Connect another store

Create a link the merchant opens to connect another Shopify store. Use when they ask to add a store. The link works once within 10 minutes.

### `get_store_overview` (~112 tokens)

Get store overview

Read a store’s overview: business context, standing memory, Google connection, work waiting on the merchant, Plans, top recommendations and recent results. With `area`, that area’s findings, Plans, work, outputs and headline numbers. Use for a brief or before planning work.

Input parameters:

- `area` (string): seo, ai-discovery, conversion or merchandising, or a library such as landing-pages or blog.
- `store` (string): The connected store to use. Omit when only one is connected.

### `search_design_references` (~86 tokens)

Search design references

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.

Input parameters:

- `industry` (string)
- `limit` (number)
- `pageKind` (string)
- `query` (string, required)
- `scope` (string, required)

### `show_design_references` (~48 tokens)

Show design references

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

Input parameters:

- `references` (array, required)

### `get_store_performance` (~312 tokens)

Get store performance

Measure the store, or a product, collection, page, article or URL given as `subject`. `metrics` returns headline values with their previous period, definition and source. `breakdown` returns ranked rows such as queries, landing pages, channels, AI assistants, devices, countries, products or discount codes. With neither, returns what exists for the subject. Periods default to the 28 days ending three days ago against the 28 days before. Google Analytics, Search Console and Shopify are separate measurements.

Input parameters:

- `ascending` (boolean)
- `breakdown` (string)
- `compare` (boolean)
- `comparisonEnd` (string)
- `comparisonStart` (string)
- `country` (string): Search Console three-letter country code, e.g. usa.
- `days`
- `device` (string)
- `endDate` (string)
- `limit` (integer)
- `metrics` (array)
- `offset` (integer)
- `sort` (string): Breakdown metric to rank by, e.g. clicks, impressions, sessions, revenue, orders.
- `startDate` (string)
- `store` (string): The connected store to use. Omit when only one is connected.
- `subject` (string): What to measure: a product, collection, page or article ID (product-42 or a Shopify GID), its name or handle, a storefront URL or path (/products/x), or omit for the whole store.

### `run_seo_tool` (~1224 tokens)

Run an SEO tool

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.

Input parameters:

- `cursor` (string): A nextCursor this tool returned: reads the next page of that run, free; input is ignored
- `id` (string, required): keyword-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…
- `input` (object): 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…
- `store` (string): The connected store to use. Omit when only one is connected.

### `get_store_insights` (~212 tokens)

Get saved findings

Read the findings and recommendations Fudge has saved for this store, most important first; narrow by area, subject, kind, date or text. With `ref`, one record in full with its sources and measurements. An empty list means nothing is saved yet. This never starts an investigation.

Input parameters:

- `area` (string): seo, ai-discovery, conversion or merchandising, or a library such as landing-pages or quizzes.
- `kind` (string)
- `limit` (integer)
- `query` (string): Words to find in the title, summary or body.
- `ref` (string): Read one record in full; the other filters are ignored.
- `since` (string): Only records created or updated on or after this date.
- `store` (string): The connected store to use. Omit when only one is connected.
- `subject` (string): A product, collection, page or article ID (product-42 or a Shopify GID), or a Fudge Plan ref.

### `get_design_guide` (~71 tokens)

Get design guide

Read the store’s design guide: colours, typography, spacing, components and brand voice. Use when designing or reviewing pages. With no guide yet and a distinctive theme, this starts a one-time extraction.

Input parameters:

- `store` (string): The connected store to use. Omit when only one is connected.

### `search_guides` (~58 tokens)

Search Fudge guides

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

Input parameters:

- `query` (string, required): What the merchant wants to do or know, in a few words.

### `read_guide` (~46 tokens)

Read Fudge guide

Read one of Fudge’s reference articles by path, such as seo/audit.md. Without a path, lists them all.

Input parameters:

- `path` (string): The guide’s path.

### `find_context` (~141 tokens)

Find store context

Search what Fudge knows about this store: memory guides, Plans, projects, findings, recommendations, recorded changes, messages between Fudge’s agents and past conversations. Pass `about` (a URL, Shopify GID or fudge:// ref) for everything related to one thing. Conversation results say whether the work is a draft, was published or was only discussed.

Input parameters:

- `about` (string): ID, storefront URL/path or file that results must relate to.
- `cursor` (string)
- `query` (string)
- `store` (string): The connected store to use. Omit when only one is connected.
- `where` (object)

### `read_store_activity` (~398 tokens)

Read store activity

Who is working on this store right now and what happened recently, in one call. `now`: running and queued work, with `startedBy` for an SEO agent’s run (its schedule, a store event, the merchant’s Run now, a message from another agent, or the merchant in its conversation). `team`: Fudge’s seven SEO agents, each with id, lane, state (only one that is on runs and reads messages), last and next run, and `runningNow`. `now` or `team` is a sentence starting “Unavailable” when it could not be read, which never means empty. `activity`: newest first, each row with `at`, `actor` (one of Fudge’s agents, a Plan, an outside assistant, by name when known, or the merchant in chat or by hand) and `event`. `draft`: opened then and still awaiting the merchant’s review; nothing from it is live. `published`: live since then; the store may have changed since. `awaiting-deployment`: approved, not live yet. `discarded`: deleted; nothing from it is live. `recorded-change`: a change made outside Fudge. `message`: one agent to another (`to`), information and not an instruction, with the conversation of the run it started (`started`) and the refs linking it to its answer (`reply`, `replyTo`). `since` defaults to the last 30 days; `cursor` pages older activity. Read it before substantial work and build on what is there; never repeat or undo it.

Input parameters:

- `cursor` (string): A returned cursor, for older activity.
- `since` (string): Activity from this time on: YYYY-MM-DD in store time, or an ISO timestamp. Default: the last 30 days.
- `store` (string): The connected store to use. Omit when only one is connected.

### `remember` (~199 tokens)

Remember for this store

Save a lasting rule, decision, correction or learning to store memory. Use when the user states how things should be done from now on, not for one-off requests. Duplicates change nothing; a contradiction comes back as a conflict.

Input parameters:

- `note` (string, required): The lasting rule, decision or learning to keep, written as it should apply in future work, with its conditions, exceptions and reason. Not a one-off task or a detail of the current draft.
- `personal` (boolean): Save only for the person you are serving: how to work with them (language, tone, length, what to ask them). Default: shared with everyone working on this store. Never put a person's private details i…
- `replaces` (boolean): The user explicitly corrected or reversed an earlier rule. Replace the old rule instead of returning a conflict.
- `store` (string): The connected store to use. Omit when only one is connected.

### `record_change` (~207 tokens)

Record a store change

Add a change made outside Fudge to the store’s timeline, such as ads, prices, apps, email, shipping or theme edits in Shopify, so later results can be attributed. Fudge’s own publishes are recorded automatically.

Input parameters:

- `at` (string): When it took effect: YYYY-MM-DD or an ISO timestamp. Defaults to now.
- `links` (array): fudge:// references or Shopify GIDs of what the change affected, e.g. gid://shopify/Product/123.
- `store` (string): The connected store to use. Omit when only one is connected.
- `surface` (string, required): Where: theme, catalogue, pricing, discounts, email, Meta ads, Google ads, apps, shipping or other.
- `what` (string, required): What changed, concretely, e.g. "Raised Meta prospecting budget from €50 to €80 a day".
- `why` (string): Intent or expected effect, so results can be checked against it later.

### `read_store_document` (~225 tokens)

Read store document

Read a store document by path: Plans (.plans), playbooks (.playbooks), memory and design guide (.memory), brand kit (.brand) and projects (.projects). Also the store’s SEO and AI search reports, the same numbers the merchant sees in Fudge, read-only and never collecting new data: `.seo/reports/index.md` holds every report’s headline with its source, period and scope; `.seo/reports/<id>.md` one report’s rows, with filters and the next page as `?name=value` (each file lists its own); `.seo/results/changes.md` what each published change did to Google clicks and visits; `.seo/results/opportunities.md` the pages worth on-page work. Omit `path` to list top-level folders; a folder path lists its documents.

Input parameters:

- `offset` (integer): Character offset from a previous `next`.
- `path` (string): Document or folder path, optionally with its ?query.
- `store` (string): The connected store to use. Omit when only one is connected.

### `edit_store_document` (~123 tokens)

Edit store document

Change part of a store document, such as a Plan’s brief or the design guide, by replacing exact text. Fails if the text is gone or the document has changed since it was read.

Input parameters:

- `new_string` (string, required): Replacement text; empty deletes old_string.
- `old_string` (string, required): Exact text to replace.
- `path` (string, required): Path of the existing document.
- `replace_all` (boolean): Replace every occurrence. Defaults to false.
- `store` (string): The connected store to use. Omit when only one is connected.

### `create_store_document` (~108 tokens)

Create store document

Create a document inside an existing Plan, such as .plans/<slug>/brief.md, or with `replace` rewrite a whole document that was just read.

Input parameters:

- `content` (string, required): Complete document content.
- `path` (string, required): Destination path, for example .plans/<slug>/brief.md.
- `replace` (boolean): True to replace an existing document you have read in full.
- `store` (string): The connected store to use. Omit when only one is connected.

### `create_plan` (~138 tokens)

Create Plan

Start a new Plan for a goal the merchant has agreed and no existing Plan covers, with a title, areas, milestones and an optional brief. Schedules and recurring work are approved in Fudge.

Input parameters:

- `areas` (array, required): Areas the Plan serves; empty for store-wide work.
- `brief` (string): Markdown brief: goal, audience, decisions and constraints. Saved as brief.md in the Plan.
- `milestones` (array, required)
- `store` (string): The connected store to use. Omit when only one is connected.
- `title` (string, required): Short outcome-focused title, e.g. “Rank for trail running shoes”.

### `list_store_audits` (~89 tokens)

List store audits

List the audits Fudge can run for this store: the Knowledge Base diagnostic, free SEO and BFCM audits and eight agent reviews, with each one’s latest result: a free audit’s status, check date, headline, score and result page. Listing starts nothing and spends nothing.

Input parameters:

- `store` (string): The connected store to use. Omit when only one is connected.

### `run_ai_readiness_check` (~162 tokens)

Run AI Readiness check

Run Fudge’s free AI visibility audit: whether ChatGPT, Google AI Mode and Gemini name, cite or show the store for shopping questions in its main market, with a score and prioritized fixes. Takes about 5 minutes and waits up to 45 seconds. Reuses a running or fresh result unless `fresh` is true; an active run is always shared.

Input parameters:

- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `fresh` (boolean): Start a new run even when a result from the last 24 hours exists.
- `store` (string): The connected store to use. Omit when only one is connected.

### `run_catalog_data_audit` (~152 tokens)

Run catalog data audit

Run Fudge’s free product schema and catalogue audit: product markup, categories, product details and whether AI buyer searches find the right products, with a score and prioritized fixes. Waits up to 45 seconds. Reuses a running or fresh result unless `fresh` is true; an active run is always shared.

Input parameters:

- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `fresh` (boolean): Start a new run even when a result from the last 24 hours exists.
- `store` (string): The connected store to use. Omit when only one is connected.

### `run_knowledge_base_check` (~149 tokens)

Run Knowledge Base check

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.

Input parameters:

- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `fresh` (boolean): Start a new run even when a result from the last 24 hours exists.
- `store` (string): The connected store to use. Omit when only one is connected.

### `run_seo_report` (~252 tokens)

SEO report

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.

Input parameters:

- `country` (string): The market to check, as a two-letter ISO country code such as GB. Omit it for the store’s main market.
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `store` (string): The connected store to use. Omit when only one is connected.

### `check_ai_visibility` (~259 tokens)

AI visibility check

Asks the public ChatGPT, Google AI Mode and Gemini apps 18 shopping questions written from a Shopify store’s catalogue in its market’s language, plus what the store is known for and, on ChatGPT, its returns and free shipping. Reports an AI visibility score; how often each assistant names the store, cites its pages or shows its products, by product line; who the answers name most often and which sources they cite; how AI describes the store; and whether ChatGPT states its return window and free-shipping threshold correctly. Real app answers, signed out, not model APIs. Free, no sign-in; waits up to 45 seconds, the first answers arrive within a minute and the rest within about 5. Shared per store for a day; unmeasured items are reported as unknown.

Input parameters:

- `country` (string): The market to check, as a two-letter ISO country code such as GB. Omit it for the store’s main market.
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `store` (string): The connected store to use. Omit when only one is connected.

### `find_page_two_pages` (~230 tokens)

Page-two finder

Finds a Shopify store’s collections, pages and articles that rank #4–20 on Google in the store’s market (DataForSEO rankings), checks the most valuable on Google today, and gives each one’s searches, monthly volumes, a range of extra clicks from reaching #3 and the change it needs, plus pages that were near page one and have left the top 20, with the cause found. One rewritten title is previewed as a Google result. Free, no sign-in; waits up to 45 seconds of a run’s usual 1–4 minutes. Shared per store for 7 days; anything not measured is reported as not checked.

Input parameters:

- `country` (string): The market to check, as a two-letter ISO country code such as GB. Omit it for the store’s main market.
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `store` (string): The connected store to use. Omit when only one is connected.

### `find_missing_pages` (~227 tokens)

Missing pages finder

Builds the Google searches for what a Shopify store sells from its catalogue (each kind of product with its attributes and audiences), keeps those a model judges are for its products, and checks the largest it has no collection for on Google today. Returns the missing pages worth building, with monthly searches and who ranks, and collections Google doesn’t show for searches they cover. Uses DataForSEO Google data and the store’s public catalogue. Free, no sign-in; waits up to 45 seconds of a run’s usual 1–4 minutes. Shared per store for 7 days. Anything it could not judge is reported as unknown, never as a finding.

Input parameters:

- `country` (string): The market to check, as a two-letter ISO country code such as GB. Omit it for the store’s main market.
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `store` (string): The connected store to use. Omit when only one is connected.

### `check_product_schema` (~230 tokens)

Product schema check

Checks up to 12 of a Shopify store’s product pages, spread over product types, sale and stock, against Google’s merchant listing and product rich result rules, using Google’s Required, Recommended and Agreement levels and wording. It compares each page’s markup with Shopify’s own product data and Shopify Catalog, checks the product list for missing descriptions, images, brands, categories and buyer details and whether Shopify Catalog searches find the right products, and, when the markup lacks the store’s policies, returns a paste-ready return and shipping policy JSON-LD block built only from its own policy pages, saying where in the theme it goes. Free, no sign-in; waits up to 45 seconds of a run’s usual 2–4 minutes. Shared per store for an hour. Anything it could not check is reported as unknown.

Input parameters:

- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `store` (string): The connected store to use. Omit when only one is connected.

### `run_bfcm_audit` (~239 tokens)

BFCM audit

Checks a Shopify store’s Black Friday readiness in four scored parts: gift searches its products fit (real monthly Google searches and the store’s position today, in its main market or the one `country` names), who is #1 for the store’s own "<brand> black friday" search and whether its sale states dates, how to get the discount and what’s included, its return, shipping and delivery details, and whether its public Shopify AI answers those questions correctly. Every problem comes with evidence and a fix brief. Free, no sign-in; waits up to 45 seconds, then returns progress and report links. Anything it could not check is reported as unchecked with its reason, never scored.

Input parameters:

- `country` (string): The market to check, as a two-letter ISO country code such as GB. Omit it for the store’s main market.
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `store` (string): The connected store to use. Omit when only one is connected.

### `get_store_audit_result` (~145 tokens)

Get audit result

Read the latest full audit: status, result card and report links. Quick checks are previews, not completed audits. A previous successful report is linked separately when the latest run has not completed. Reading starts nothing. `waitSeconds` waits up to 50 seconds for a running report.

Input parameters:

- `audit` (string, required): The diagnostic’s id.
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `store` (string): The connected store to use. Omit when only one is connected.
- `waitSeconds` (integer): Default 0.

### `read_audit_evidence` (~205 tokens)

Read audit evidence

Read complete retained evidence from a free audit run, including full AI answers, sources, product records and findings. Discovers named collections, then returns selected records with explicit pagination and availability. Reads only; never starts collection or spends audit allowance.

Input parameters:

- `audit` (string, required)
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `limit` (number): Integer from 1 to 100 child records. Strings use 10,000-character pages.
- `offset` (number): Non-negative integer; use the previous page’s nextOffset.
- `recordId` (string): A returned JSON-pointer record id; maximum 2,000 characters.
- `runId` (string, required): A returned run id, from 1 to 100 characters.
- `store` (string): The connected store to use. Omit when only one is connected.

### `list_audit_runs` (~160 tokens)

List audit runs

List retained free audit runs for the store, newest first, with stable run ids, dates and a continuation cursor. Reads only; never starts collection or spends audit allowance.

Input parameters:

- `audit` (string, required)
- `country` (string): Two-letter ISO country code, such as GB.
- `cursor` (string): The nextCursor from the previous page; maximum 1,000 characters.
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `limit` (number): Integer from 1 to 100 runs per page.
- `store` (string): The connected store to use. Omit when only one is connected.

### `check_page_speed` (~184 tokens)

Check page speed

Measure a store page with Google PageSpeed Insights: Lighthouse score and lab metrics, real-visitor Core Web Vitals, the largest improvement opportunities and a diagnosis of the cause (LCP element and phases, request chain, render-blocking requests, third parties, layout-shift culprits). Each device takes 10–30 seconds; results are cached for an hour. On a password-protected store, only real-visitor data is available.

Input parameters:

- `device` (string)
- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `page` (string): A store URL or path, e.g. / or /products/blue-runner.
- `store` (string): The connected store to use. Omit when only one is connected.

### `check_store_technical` (~98 tokens)

Check store crawlability

Check the live store’s crawlability for search and AI: robots.txt rules, /llms.txt, sitemap.xml, password protection and whether products are publicly reachable.

Input parameters:

- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `store` (string): The connected store to use. Omit when only one is connected.

### `check_page` (~145 tokens)

Check page SEO

Check one live store page’s server HTML for SEO and structured data, as browsers and Google read it: page head, title, canonical, noindex, structured data in JSON-LD, microdata or RDFa, lang, viewport, image alt text, mixed content and word count.

Input parameters:

- `domain` (string): The Shopify storefront to check, e.g. example.com. Required until a store is connected; afterwards, omit it to use a connected store.
- `page` (string): A store URL or path, e.g. / or /products/blue-runner.
- `store` (string): The connected store to use. Omit when only one is connected.

### `start_website_redesign` (~87 tokens)

Start website redesign

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.

Input parameters:

- `domain` (string, required): The Shopify storefront, e.g. example.com.
- `instructions` (string): What the merchant wants from the redesign, in their words.

### `start_store_builder` (~80 tokens)

Start AI store builder

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.

Input parameters:

- `description` (string, required): The store idea: what they sell, who for, and anything they’ve said about the brand.

### `check_catalog_data` (~223 tokens)

Check catalogue data

Check catalogue data coverage across published products, collections, pages and articles: taxonomy, SEO fields, product type, vendor, description, images, alt text and optionally GTIN and MPN. Without `type`, totals and per-field coverage; with `type`, the items missing fields, a page at a time. The first call scans the live catalogue and can return status "scanning". Results are kept for an hour.

Input parameters:

- `includeProductIdentifiers` (boolean): Also check GTIN/barcode and MPN on products. A separate, slower scan.
- `limit` (integer)
- `missing` (string): With type: only items missing this field, named as in the summary, e.g. "Meta description".
- `offset` (integer)
- `refresh` (boolean): Rescan instead of reusing this hour’s result. Only after the merchant changed catalogue data.
- `store` (string): The connected store to use. Omit when only one is connected.
- `type` (string): List this type’s offenders instead of the summary.

### `search_catalog` (~112 tokens)

Search catalogue

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.

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `query` (string): Words from the title or handle. Leave empty to list by type in title order.
- `store` (string): The connected store to use. Omit when only one is connected.
- `types` (array)

### `list_offers` (~71 tokens)

List offers

List the store’s current offers: Fudge offers, active Shopify discounts, native bundles, and shipping rates by zone or market with their free-shipping conditions. Use for an offers or average-order-value review.

Input parameters:

- `store` (string): The connected store to use. Omit when only one is connected.

### `capture_page` (~185 tokens)

Capture page screenshots

Screenshot one store page in a real browser on desktop and/or mobile and return the images. Pass `draft` to see a Fudge draft. `fullPage` captures top to bottom. Takes 15–60 seconds; up to 50 captures per store per day.

Input parameters:

- `device` (string)
- `draft` (string): A draft’s fudge://project/… ref: capture the page as that draft shows it. Staged product and page content changes appear only on Fudge’s review page, not here.
- `fullPage` (boolean)
- `page` (string): A store URL or path, e.g. / or /products/blue-runner. Defaults to the home page, or with `draft` to the page the draft is about.
- `store` (string): The connected store to use. Omit when only one is connected.

### `get_keyword_metrics` (~129 tokens)

Get keyword metrics

Get Google search volume, difficulty, intent, CPC and 12-month history for specific keywords in one country. Missing values are unknown, not zero. Changes nothing and uses no credits; each store has a daily limit.

Input parameters:

- `keywords` (array, required)
- `language` (string): Language code, e.g. "en". Defaults to the store’s language.
- `location` (string, required): Target country, e.g. "United States". Ask the merchant which countries they sell to if unknown.
- `store` (string): The connected store to use. Omit when only one is connected.

### `find_keyword_ideas` (~139 tokens)

Find keyword ideas

Find longer search phrases containing a seed keyword, with volume, difficulty and intent. Changes nothing and uses no credits; each store has a daily limit.

Input parameters:

- `language` (string): Language code, e.g. "en". Defaults to the store’s language.
- `limit` (integer)
- `location` (string, required): Target country, e.g. "United States". Ask the merchant which countries they sell to if unknown.
- `maxDifficulty` (number)
- `minVolume` (integer)
- `seed` (string, required)
- `store` (string): The connected store to use. Omit when only one is connected.

### `get_search_results` (~136 tokens)

Get search results

Read Google’s live first results page for one search in one country: ranked results, features, AI Overview citations, People Also Ask and related searches. Changes nothing and uses no credits; each store has a daily limit.

Input parameters:

- `device` (string)
- `keyword` (string, required)
- `language` (string): Language code, e.g. "en". Defaults to the store’s language.
- `location` (string, required): Target country, e.g. "United States". Ask the merchant which countries they sell to if unknown.
- `store` (string): The connected store to use. Omit when only one is connected.

### `get_ranked_keywords` (~169 tokens)

Get ranked keywords

List the Google searches a domain ranks for in one country, with position, URL, volume, difficulty and estimated traffic. Defaults to this store; pass a competitor’s domain to compare. Changes nothing and uses no credits; each store has a daily limit.

Input parameters:

- `domain` (string): Defaults to this store’s domain.
- `language` (string): Language code, e.g. "en". Defaults to the store’s language.
- `limit` (integer)
- `location` (string, required): Target country, e.g. "United States". Ask the merchant which countries they sell to if unknown.
- `pathPrefix` (string): Only URLs under this path, e.g. /blogs/.
- `store` (string): The connected store to use. Omit when only one is connected.

### `list_work` (~119 tokens)

List work

List Fudge work for this store, including work started in Fudge or another assistant. `view: "needs_you"` returns what is waiting on the merchant. `query` searches past work.

Input parameters:

- `before` (string)
- `kind` (string)
- `limit` (number): 1–50, default 20.
- `query` (string): Ranked search; cannot be combined with before.
- `store` (string): The connected store to use. Omit when only one is connected.
- `view` (string)

### `read_work` (~263 tokens)

Read work

With `ref`: one work item’s live state, progress, latest result, what it is waiting for, and draft or publication state with links; `waitSeconds` waits up to 50 seconds. With `about` (a URL, path, Shopify GID, theme file or fudge:// ref): what has changed there, by `view` current, history or summary. `about: "fudge://store"` with `view: "history"` is the whole store’s change timeline.

Input parameters:

- `about` (string): Storefront URL/path, Shopify GID, theme file, fudge://discount/<key>, .projects/.plans path, or fudge://store for the whole store.
- `cursor` (string)
- `from` (string): With view history: YYYY-MM-DD in store time, or an ISO timestamp.
- `ref` (string): A work item to read: fudge://project/… or fudge://thread/….
- `store` (string): The connected store to use. Omit when only one is connected.
- `to` (string)
- `view` (string)
- `waitSeconds` (integer): With ref: wait up to this long for running work to finish or need the merchant. Default 0.

### `message_fudge` (~205 tokens)

Message Fudge

Ask Fudge to do work for this store: build or revise a page, article or other draft, investigate, or answer a question. Without `ref`, starts a new conversation; with `ref`, continues that work. Uses the store’s Fudge credits. `requestId` makes retries deliver once. Publishing always needs the merchant’s own approval in Fudge.

Input parameters:

- `delivery` (string)
- `message` (string, required): The merchant’s request in full: what to do, for which page or products, and any decisions already made.
- `ref` (string): fudge://thread/… or fudge://project/… to continue; omit to start new work.
- `requestId` (string, required): A unique ID you choose for this request, e.g. a UUID. Retries reuse it.
- `store` (string): The connected store to use. Omit when only one is connected.
- `title` (string): Short title for a new conversation.

### `stop_work` (~87 tokens)

Stop work

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

Input parameters:

- `ref` (string, required): The work’s fudge://thread/… or fudge://project/… ref.
- `runId` (string)
- `store` (string): The connected store to use. Omit when only one is connected.

### `request_publish_review` (~90 tokens)

Request publish review

Prepare a finished draft for the merchant’s publish decision. Returns the link to Fudge’s review page, what will change and whether publishing needs a plan. This does not publish; only the merchant can, in Fudge.

Input parameters:

- `ref` (string, required): The work’s fudge://project/… ref.
- `store` (string): The connected store to use. Omit when only one is connected.

### `open_fudge_home` (~69 tokens)

Fudge Home

Open Fudge Home for a store: work waiting on the merchant, the next recommended step and the four growth areas. Use when the merchant asks to open Fudge or see their store at a glance.

Input parameters:

- `store` (string): The connected store to use. Defaults to the first one.

### `show_draft` (~70 tokens)

Draft preview

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

Input parameters:

- `ref` (string): A fudge://project/… ref.
- `store` (string): The connected store to use. Defaults to the first one.

### `start_draft` (~216 tokens)

Start draft

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.

Input parameters:

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

### `read_draft_file` (~239 tokens)

Read draft file

Read a file in a Fudge draft: a theme file, a theme folder listing, or a content document under .entities (list with .entities/product?query=…). Each line starts with a gutter ending at its first tab, numbered on the first, last and every tenth line; long files return `line_offset`. Theme files return a `revision`. Append #info to see where a theme file is used.

Input parameters:

- `char_offset` (integer): Character offset within a very long first line, only when the result says to continue with one.
- `draft` (string, required): The draft’s fudge://project/… ref.
- `line_limit` (integer): Lines to return. Omit to read up to the limit.
- `line_offset` (integer): 0-based line to start from, from a previous read.
- `path` (string, required): A 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.
- `store` (string): The connected store to use. Omit when only one is connected.

### `search_draft_files` (~134 tokens)

Search draft files

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

Input parameters:

- `draft` (string, required): The draft’s fudge://project/… ref.
- `paths` (array, required): Files, folders or glob patterns, e.g. ["sections", "snippets/*price*.liquid"].
- `pattern` (string): Regular expression (RE2 syntax: no lookarounds or backreferences) to search for in those files.
- `store` (string): The connected store to use. Omit when only one is connected.

### `edit_draft_file` (~146 tokens)

Edit draft file

Change part of a theme file or .entities document in a Fudge draft by replacing exact text, without line gutters. Fudge validates the result and refreshes the preview.

Input parameters:

- `draft` (string, required): The draft’s fudge://project/… ref.
- `edits` (array, required)
- `path` (string, required): A 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.
- `revision` (string): The revision returned when this file was read.
- `store` (string): The connected store to use. Omit when only one is connected.

### `write_draft_file` (~197 tokens)

Write draft file

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".

Input parameters:

- `content` (string, required): The complete file content, without line gutters.
- `draft` (string, required): The draft’s fudge://project/… ref.
- `path` (string, required): A 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.
- `replace` (boolean): True to replace an existing file you have read in full.
- `revision` (string): The revision returned when this file was read, when replacing.
- `store` (string): The connected store to use. Omit when only one is connected.

### `delete_draft_file` (~133 tokens)

Delete draft file

Delete a theme file from a Fudge draft, or stage removal of an item by its .entities path. Fudge refuses deletions that would break references. Publishing applies the removal; until then it can be undone.

Input parameters:

- `draft` (string, required): The draft’s fudge://project/… ref.
- `path` (string, required): A 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.
- `store` (string): The connected store to use. Omit when only one is connected.

### `edit_draft_content` (~238 tokens)

Edit draft content

Change products, collections, pages, articles, blogs and their metafields in a Fudge draft with sparse patches, many items in one call.
\- Name only the fields you change; nested objects such as seo merge per key.
\- Rows with an "id" (variants, options, media) merge by id; omit "id" to add a row; {"id": …, "_delete": true} removes one. Variants and media live at .entities/product/{id}/variants.jsonc and media.jsonc.
\- Lists such as tags take a full array or {"add": […], "remove": […]}.
\- Metafields: .entities/product/{id}.metafields with {"namespace.key": {"type": …, "value": …}}; "value": null removes one.
Changes to existing items are staged for the merchant’s review. Items the draft created change in Shopify at once.

Input parameters:

- `draft` (string, required): The draft’s fudge://project/… ref.
- `edits` (array, required)
- `store` (string): The connected store to use. Omit when only one is connected.

### `create_draft_product` (~96 tokens)

Create product in draft

Create a new hidden product in a Fudge draft, with options, variants, prices and media. It is deleted if the draft is discarded and becomes active when the merchant publishes. Use only when the merchant asks.

Input parameters:

- `draft` (string, required): The draft’s fudge://project/… ref.
- `product` (object, required)
- `store` (string): The connected store to use. Omit when only one is connected.

### `create_draft_collection` (~87 tokens)

Create collection in draft

Create a new hidden collection in a Fudge draft. It is deleted if the draft is discarded and goes live when the merchant publishes. Use only when the merchant asks.

Input parameters:

- `collection` (object, required)
- `draft` (string, required): The draft’s fudge://project/… ref.
- `store` (string): The connected store to use. Omit when only one is connected.

### `create_draft_page` (~86 tokens)

Create page in draft

Create a new Shopify page in a Fudge draft, optionally with its own template. It can be previewed in the draft and goes live when the merchant publishes.

Input parameters:

- `draft` (string, required): The draft’s fudge://project/… ref.
- `page` (object, required)
- `store` (string): The connected store to use. Omit when only one is connected.

### `create_draft_article` (~80 tokens)

Create article in draft

Create a new blog article in a Fudge draft. It can be previewed in the draft and goes live when the merchant publishes.

Input parameters:

- `article` (object, required)
- `draft` (string, required): The draft’s fudge://project/… ref.
- `store` (string): The connected store to use. Omit when only one is connected.

### `show_preview_consent` (~85 tokens)

Ask to allow previews

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.

Input parameters:

- `draft` (string, required): The draft’s fudge://project/… ref.
- `store` (string): The connected store to use. Omit when only one is connected.

### `set_preview_consent` (~106 tokens)

Record preview choice

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

Input parameters:

- `answer` (string, required): The answer code from Fudge’s consent card.
- `draft` (string, required): The draft’s fudge://project/… ref.
- `scope` (string, required): project: this draft only; site: every draft.
- `state` (string, required)
- `store` (string): The connected store to use. Omit when only one is connected.

### `send_feedback` (~206 tokens)

Send feedback to Fudge

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

Input parameters:

- `message` (string, required): Up 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…
- `store` (string): The connected store to use. Defaults to the first one.
- `type` (string, required): broken: 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…

### `show_resources` (~64 tokens)

Show in Fudge

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

Input parameters:

- `refs` (array, required)
- `store` (string): The connected store to use. Omit when only one is connected.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-fudge-fudge/mcp#diagnostics

## Score history

- 2026-11-21: 70
- 2026-11-20: 70
- 2026-11-19: 69
- 2026-11-18: 69
- 2026-11-17: 68
- 2026-11-16: 68
- 2026-11-15: 68
- 2026-11-14: 67
- 2026-11-13: 67
- 2026-11-12: 66
- 2026-11-11: 66
- 2026-11-10: 65

## 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.

## Links

- Remote endpoint: https://mcp.fudge.ai/mcp
- Repository: https://github.com/fudge-ai/fudge-plugin
- Website: https://www.fudge.ai/shopify-mcp-server/
- Changelog RSS feed: https://verifymcp.io/servers/ai-fudge-fudge/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-fudge-fudge/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-fudge-fudge/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-fudge-fudge/mcp
