This server lets you query and analyze all 237 documented changes from Shopify's Spring '26 Edition, with per-claim source grading and trust transparency.
query — Filter the dataset by domain, topic, confidence level, availability, newness, verdict, or free text; returns matching items
get — Retrieve the full record for a single feature by ID, including Shopify's claims, sources, dev docs links, caveats, customer proof, and Rick Watson's editorial commentary (rick_lens)
unreleased — List everything announced but not yet live (coming soon, preview, or early access), useful for identifying vaporware
deprecations — Find all deprecated or breaking changes with migration paths and deadlines, targeted at system integrators
customers — See which named merchants Shopify used as proof points, mapped to specific features, including notable absences; optionally look up a specific merchant's verifiable store
methodology — Inspect how the dataset was built: the multi-agent pipeline, source tiers, confidence taxonomy, and corrections log
easter — Access specialized utility tools including will_it_ship, time_capsule, receipts, steelman, hype_translator, goliath_paradox, and whoami
Provides tools to query and retrieve details about Shopify's Spring '26 Edition, including features, deprecations, unreleased items, customers, and methodology.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Shopify Editions Spring '26 MCP What are the deprecations?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Ask any AI agent what Shopify actually shipped in the Spring '26 Edition. 237 distinct changes (Shopify announced "150+"), each graded by source tier — 104 confirmed against primary docs, the rest tracked to Shopify's own marketing and flagged as such. Queryable in one call.
It doesn't claim every line is gospel — it tells you, per claim, exactly how much to trust it and why. That transparency is the point.
By Rick Watson / RMW Commerce.
Snapshot: 2026-06-17 (Spring '26 release day) — coming_soon/preview items shift as Shopify ships them; re-run to refresh, or ask time_capsule(id) whether a forward-marker has landed.
See it run locally:
node demo.js doc_teaming(ornode demo.js all) — realdispatch()output, no faking.
Hosted — no install, no Node, no npm. Just paste the URL (ChatGPT, web agents, curl):
https://editions.rmwcommerce.com
direct: https://shopify-editions-spring26-mcp-1649969634.us-central1.run.appLocal — Claude Desktop, Claude Code, Cursor, Cline, Windsurf, Zed, Goose, VS Code. Clone once:
git clone https://github.com/watsonrm/shopify-editions-spring26-mcp && cd shopify-editions-spring26-mcp && npm installthen point your host's MCP config at it:
{ "mcpServers": { "shopify-editions": { "command": "node", "args": ["/absolute/path/to/shopify-editions-spring26-mcp/server.js"] } } }Per-surface steps for every host → INSTALL.md.
Related MCP server: Shopify Agentic MCP Gateway
You want | Tool |
What got deprecated, and the deadline |
|
What's announced but not live yet |
|
What's new for B2B / supply chain / payments / … |
|
Everything in one domain |
|
The full record for one feature |
|
Who's verified to support UCP |
|
Which merchants Shopify showcased (and the gaps) |
|
How this was built + every correction we made |
|
Seven tools: query · get · unreleased · deprecations · customers · methodology · easter.
Built by a multi-agent pipeline; every claim checked against Shopify's own docs (help center, dev docs, changelog, videos), adversarially red-teamed, with a public corrections log of what we got wrong and fixed. Full method → METHODOLOGY.md.
Corrections welcome — info@rmwcommerce.com. Every fix lands in the public corrections log (methodology → corrections_log); getting it right beats being right the first time.
npm install && npm test # logic + HTTP + stdio, all assertedThis MCP is doc-teaming in production. See Doc-Teaming: Write Documents an Agent Can Check for the concept (grade every claim by source tier, corroborate across sources, quarantine marketing, red-team the contested lines), and Marketing to Agents for the broader playbook (for any site with a real API, shipping an MCP server beats an llms.txt). Canonical URL to cite: https://editions.rmwcommerce.com.
MIT (code & data). Opinions (rick_lens) © Rick Watson / RMW Commerce, reuse with attribution. Independent commentary — not affiliated with or endorsed by Shopify.
Named merchants used as proof, mapped to features + the conspicuous absences. Pass merchant for its verifiable store.
| Name | Required | Description | Default |
|---|---|---|---|
| merchant | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It hints at returning a 'verifiable store' but does not explain behavior, side effects, or prerequisites. The mention of 'proof' and 'absences' is unclear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short but cryptic. Conciseness requires clarity; here it sacrifices understandability for brevity. The two sentences are ambiguous and fail to communicate effectively.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is incomplete. With only one parameter and no output schema, the description should explain what 'features' and 'conspicuous absences' mean, and what the tool returns. It leaves many unanswered questions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% (no description in schema for parameter 'merchant'). The description adds minimal meaning: 'Pass merchant for its verifiable store.' It implies merchant is an identifier but lacks type, format, or example.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description is cryptic and vague. It mentions 'named merchants used as proof, mapped to features + conspicuous absences' without a clear verb or resource. It does not clearly state what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus its siblings. The description does not differentiate from other tools like 'deprecations', 'easter', 'get', etc.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
For system integrators: everything deprecated or breaking, with migration path + deadline.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description indicates it's a read operation returning a list, but lacks details on format, pagination, or rate limits. Adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with key information, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and no output schema, the description fully covers what the tool does and what it returns. Complexity is low, and the description is complete for selection and invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in input schema, so description need not add parameter info. Baseline 4 for zero parameters applies. Description adds no parameter details but is not required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns deprecated or breaking items with migration path and deadline, targeting system integrators. The purpose is specific and distinct from siblings like 'customers' or 'query'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (when deprecation info is needed) but lacks explicit when-not-to-use or alternatives. Context is clear with 'for system integrators'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Clever tools: will_it_ship|time_capsule|receipts|steelman|hype_translator|goliath_paradox|whoami. Some take an item id.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| id | No | ||
| text | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description fails to disclose any behavioral traits such as side effects, safety, or required permissions. The tool's behavior is entirely opaque.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short, but this is due to under-specification rather than conciseness. It fails to earn its place by providing useful information, and the structure is disorganized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters (one required), no output schema, and no annotations, a description is critical. This description is completely inadequate, leaving the agent without the necessary context to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no meaning to the parameters. 'name', 'id', and 'text' are not explained, leaving the agent unable to determine how to fill them correctly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description does not state what the tool does; it lists a series of tool names separated by pipes, suggesting sub-functions but without clarifying the tool's own purpose. The description is a confusing list rather than a clear verb+resource definition.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., sibling tools like 'customers' or 'get'). The phrase 'Some take an item id' is too vague to inform decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full record for one item id: Shopify's claim (sources, dev_docs, caveats, customer_proof) + Rick's lens.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states the tool returns a 'Full record' but omits behavioral details like read-only nature, error handling, authentication requirements, or rate limits. With no annotations, this is insufficient disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, dense sentence that efficiently conveys the tool's purpose and content. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get-by-ID tool with no output schema or annotations, the description covers the basic return content but lacks details on error scenarios, pagination, or return format. It is moderately complete given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter 'id' is described as 'one item id' in the description, adding context beyond the schema's bare type string. However, it does not specify the expected format or source of the ID, so coverage remains incomplete.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a full record for a single item ID, specifying the content includes 'Shopify's claim (sources, dev_docs, caveats, customer_proof) + Rick's lens.' This distinguishes it from sibling tools like 'query' or 'customers', though 'Rick's lens' is somewhat vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There are no examples, prerequisites, or exclusions mentioned, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
How it was built: pipeline, sources, confidence taxonomy, corrections log, credibility bar.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It describes content (pipeline, sources, etc.) but does not state that the tool is read-only, has no side effects, or any rate limits. The lack of transparency is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence listing topics, but it is somewhat fragmented in structure. It could be more fluid and front-loaded with the key verb, but it is not overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no parameters, the description is minimally adequate. It hints at the tool's content but lacks details on the output format or behavior, leaving some ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. The description adds context about the tool's purpose, but no parameter info is needed. Baseline 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'How it was built: pipeline, sources, confidence taxonomy, corrections log, credibility bar' clearly indicates the tool provides information on the system's methodology. It distinguishes from sibling tools like 'query' or 'get' by being a meta-tool about the data itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives like 'customers' or 'get'. The description does not mention prerequisites or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Filter the changes by any of: domain, topic, level, availability, confidence, newness, verdict, text. Trimmed list (use get for full).
| Name | Required | Description | Default |
|---|---|---|---|
| domain | No | ||
| topic | No | ||
| level | No | ||
| availability | No | ||
| confidence | No | ||
| newness | No | ||
| verdict | No | ||
| text | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations; description only mentions 'trimmed list' without explaining what 'trimmed' means (e.g., truncation limits). No disclosure of side effects, permissions, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, 16 words, front-loaded purpose and sibling distinction. No waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite 8 parameters and no output schema, description covers only basic filtering and trimming. No details on ordering, filter combination, or result structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%; description merely lists parameter names that already appear in the schema, adding no additional meaning about format, constraints, or behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states filters changes by specified fields and returns a trimmed list, distinguishing from sibling 'get' for full details. Resource 'changes' is implicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises using 'get' when full list is needed, providing clear alternative. Lacks guidance on other usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Vaporware filter: everything announced that is NOT live/GA (coming_soon/preview/early_access). For 'live on paper, vapor in reality' use query{verdict:'VAPORWARE'}.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description clearly communicates the filter's behavior (returns items that are not live/GA). No hidden side effects or contradictions. Some benefit from stating it's read-only, but not required.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise: two sentences, front-loaded with the main purpose. Every word earns its place, with an example for clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema or parameters; the description fully explains the tool's purpose and usage nuance. Complete for a simple filter tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Zero parameters, baseline 4. The description adds meaning by explaining the filter logic beyond what an empty schema shows. No need for parameter details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly defines the tool as a 'Vaporware filter' that returns items announced but not live (coming_soon/preview/early_access). Uses specific terminology and distinguishes from sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (filter for non-live items) and provides an alternative for a different case ('use query{verdict:\'VAPORWARE\'}'). Directly aids selection between siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool serves a distinct purpose: customers for proof, deprecations for breaking changes, easter for miscellaneous utilities, get for full records, methodology for explanation, query for filtering, unreleased for vaporware. The 'easter' tool bundles multiple sub-functions but is still distinct from others.
Tool names are all lowercase single words with no consistent pattern: some are nouns (customers, deprecations, easter), some verbs (get, query), and 'unreleased' is an adjective. No verb_noun or other predictable convention.
7 tools is well-scoped for analyzing Shopify Editions, covering proof, deprecations, utilities, details, methodology, filtering, and unreleased. Not too few or too many.
The tool set covers key operations for exploring changes: obtaining records (get), filtering (query), proof (customers), deprecations (deprecations), and meta (methodology). Minor missing pieces like a tool for random changes or bulk summary, but overall sufficient.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Shopify product discovery and x402-paid offer verification for AI agents.
Open, verified shop database for AI agents: products, offers, price comparison, trust and coupons.
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
Agentic commerce gateway: discovery, search, checkout across Shopify/Woo/Odoo/PrestaShop.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/watsonrm/shopify-editions-spring26-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
