Commerce Intelligence MCP server
io.phoslabs/commerce-intelligencephoslabs.iostreamable-httpv4.0.1Scanned
Behavioral-science tools for commerce: checkout, drop-off, pricing, churn. 5 free calls, then paid.
8 tools: 5 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Commerce Intelligence MCP server can do
The Commerce Intelligence MCP server is published by phoslabs.io, a domain the MCP Registry verified. It has 8 tools. It can create or change data (5 tools: write_product_copy, fix_checkout, optimize_onboarding, predict_churn and 1 more), but cannot delete data. 3 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 9, 2026, version 4.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Changes things 5Claude Code: ask
fix_checkoutRedesign a checkout, signup, or purchase flow to reduce abandonment.1 finding
Why it is in this group
- The name "fix_checkout" says "checkout": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "fix_checkout" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "fix_checkout" says "checkout": a word for a change.
Description, as the server wrote it Redesign a checkout, signup, or purchase flow to reduce abandonment. Returns step-by-step redesigned flow with friction removed and behavioral principles applied. CONVERT. 20 credits (€0.20 per call).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
optimize_onboardingReduce time-to-value for new signups.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Reduce time-to-value for new signups. Identifies onboarding friction and designs a flow that gets users to their 'aha moment' faster. RETAIN. 20 credits (€0.20 per call).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
optimize_pricingDesign price framing, anchoring, and tier structure to maximize willingness to pay.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Design price framing, anchoring, and tier structure to maximize willingness to pay. Includes decoy pricing analysis and value articulation strategy. CONVERT. 20 credits (€0.20 per call).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
predict_churnIdentify which customers are about to leave and why.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Identify which customers are about to leave and why. Returns churn risk scores with behavioral drivers and retention interventions. RETAIN. 20 credits (€0.20 per call).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
write_product_copyWrite product descriptions, landing page copy, or marketing messages that convert.1 finding
Why it is in this group
- The name "write_product_copy" says "write": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "write_product_copy" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "write_product_copy" says "write": a word for a change.
Description, as the server wrote it Write product descriptions, landing page copy, or marketing messages that convert. Uses social proof, loss framing, anchoring, and scarcity — without being manipulative. CONVERT. 20 credits (€0.20 per call).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 3Show 3 read-only tools
detect_biasesFind cognitive biases in your messaging, UX copy, or product framing.No findings
Why it is in this group
- The description's first verb is "find": a word for reading.
Description, as the server wrote it Find cognitive biases in your messaging, UX copy, or product framing. Returns biases found with severity and debiasing recommendations. UNDERSTAND. 20 credits (€0.20 per call).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
diagnose_dropoffFind where and why customers abandon your funnel.No findings
Why it is in this group
- The description's first verb is "find": a word for reading.
Description, as the server wrote it Find where and why customers abandon your funnel. Analyzes each step for statistically significant drop-offs and identifies the behavioral barrier at each point. Input: describe the funnel steps, optionally with data as JSON {steps: [{name, users}, ...]}. CONVERT. 20 credits (€0.20 per call).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:14 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.phoslabs.io/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://mcp.phoslabs.io/
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.phoslabs.io/mcp: tools/list returned 8 tools to an anonymous client, including write_product_copy (write), fix_checkout (write), optimize_onboarding (write), predict_churn (write), optimize_pricing (write)
Posture changes
- Oct 29, 2026
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 5
- Protocol version: none to 2025-06-18
- WWW-Authenticate on 401: no to not observed
- RFC 9728 protected resource metadata: https://mcp.phoslabs.io/.well-known/oauth-protected-resource to https://mcp.phoslabs.io/.well-known/oauth-protected-resource/mcp
Findings
Matches of fixed checks, with the text they matched.
The server marks "write_product_copy" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "write_product_copy" says "write": a word for a change.
- Warnfix_checkout
The server marks "fix_checkout" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "fix_checkout" says "checkout": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 5; Protocol version: none -> 2025-06-18 (and 2 more).View diff
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 5
- Protocol version: none to 2025-06-18
- WWW-Authenticate on 401: no to not observed
- RFC 9728 protected resource metadata: https://mcp.phoslabs.io/.well-known/oauth-protected-resource to https://mcp.phoslabs.io/.well-known/oauth-protected-resource/mcp
Install
Pinned to version 4.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http commerce-intelligence https://mcp.phoslabs.io/mcpclaude mcp add --transport http commerce-intelligence https://mcp.phoslabs.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__commerce-intelligence__diagnose_dropoff",
"mcp__commerce-intelligence__find_hidden_barriers",
"mcp__commerce-intelligence__detect_biases"
],
"ask": [
"mcp__commerce-intelligence__write_product_copy",
"mcp__commerce-intelligence__fix_checkout",
"mcp__commerce-intelligence__optimize_onboarding",
"mcp__commerce-intelligence__predict_churn",
"mcp__commerce-intelligence__optimize_pricing"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as commerce-intelligence. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.phoslabs/commerce-intelligence/verify?hash=c4f915789ed214a745cab3339426378b86e029525b56bc7ea57a10539bb45895" | jq -e '.changed == false'Pinned hash c4f915789ed2, from Nov 9, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.phoslabs/commerce-intelligence/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.phoslabs/commerce-intelligence)Source: MCP Registry. Synced Oct 28, 2026, 05:18 UTC.
Commerce Intelligence MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Commerce Intelligence MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 5 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Commerce Intelligence MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Commerce Intelligence MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Commerce Intelligence MCP server have?
- 8 tools: 5 write, 3 read. write_product_copy, fix_checkout, optimize_onboarding, predict_churn, optimize_pricing, diagnose_dropoff, find_hidden_barriers and detect_biases.
Does the Commerce Intelligence MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Commerce Intelligence MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Commerce Intelligence MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.