HirePulse Commerce Research
io.github.edtool79-collab/hirepulse-commerceedtool79-collabstreamable-httpv1.0.0Scanned
11 tools for product data, store discovery and merchant evidence. Free sandbox and x402 payments.
11 tools: 1 do something that can't be undone, 6 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 11
- Can send data out · 2
- 5 findings
Anlyon alternative
7 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →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.
11 tools
Can't be undone 1Claude Code: ask
pre_purchase_merchant_trust_checkReturns structured public evidence and explicit unknowns.Reads text others write1 finding
Why it is in this group
- The name "pre_purchase_merchant_trust_check" says "purchase": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "pre_purchase_merchant_trust_check" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "pre_purchase_merchant_trust_check" says "purchase": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Returns structured public evidence and explicit unknowns. Public trust evidence for an unfamiliar online shop before buying: a cautious evidence score, risk flags, missing signals and limits. Cannot certify safety. $0.005 after the shared free calls. x402 API endpoints: x402_merchant_trust_check. Use for a consumer purchase from an unfamiliar shop; use b2b_vendor_stability_evaluator for B2B supplier procurement. This does not buy goods or authorize payment.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: Pre-Purchase Merchant Check
Changes things 6Claude Code: ask
ask_hirepulse_advisorFree advisor that maps a goal (B2B leads, hiring signals, buying intent, tech stack, Google Ads, due diligence) to the matching HirePulse tool, its price, the free-call balance and…Reads text others writeNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free advisor that maps a goal (B2B leads, hiring signals, buying intent, tech stack, Google Ads, due diligence) to the matching HirePulse tool, its price, the free-call balance and a ready-to-run request. Use when the right tool or expected cost is unclear; go directly to get_company_profile for a known domain and a full company brief. The returned request is a preview and is not executed by this advisor.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: HirePulse Advisor (free)
checkout_active_promo_code_finderReturns structured public evidence and explicit unknowns.Reads text others write1 finding
Why it is in this group
- The name "checkout_active_promo_code_finder" says "checkout": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "checkout_active_promo_code_finder" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "checkout_active_promo_code_finder" says "checkout": a word for a change.
Description, as the server wrote it Returns structured public evidence and explicit unknowns. Coupon code candidates published in the homepage metadata of a shop, with the source text. Codes are not verified at checkout. $0.01 per non-empty result. Use to collect possible discounts before checkout; use universal_product_url_to_json for product prices and availability. Does not apply coupons or place an order.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: Checkout Promo Codes
claim_free_trialGet a one-time trial pass: 25 free successful calls of any single tool, not tied to your IP, valid 30 days.Reads text others write1 finding
Why it is in this group
- The description's first verb is "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "claim_free_trial" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"openWorldHint":true}; The description's first verb is "get": a word for reading.
Description, as the server wrote it Get a one-time trial pass: 25 free successful calls of any single tool, not tied to your IP, valid 30 days. Send exactly one of: a Base wallet that has activity, or a work email (no email is sent). Then pass the token as params._meta["hirepulse/trial_token"] or the X-Trial-Token header.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: true
- title: Claim a free 25-call trial
muse_agentic_store_readiness_auditorReturns structured public evidence and explicit unknowns.Reads text others write1 finding
Why it is in this group
- The name "muse_agentic_store_readiness_auditor" says "store": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "muse_agentic_store_readiness_auditor" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "muse_agentic_store_readiness_auditor" says "store": a word for a change.
Description, as the server wrote it Returns structured public evidence and explicit unknowns. Store audit for shopping agents: machine-readable product data, UCP/ACP discovery, payment hints and robots.txt access, with a heuristic score and prioritized fixes. Not a certification or checkout test. $0.01 per result. Use to diagnose agent-readable store discovery and prioritize fixes; use universal_product_url_to_json for one product or pre_purchase_merchant_trust_check for purchase-risk evidence. Does not modify the store.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: Store Readiness Audit
url_to_clean_markdownPublic web page to clean Markdown with title, meta description and a token estimate; scripts, navigation and ads removed.Reads text others writeCan send data out1 finding
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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.url.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.url.description: "...private addresses, unsafe redirects and credential-bearing URLs are rejected."
Description, as the server wrote it Public web page to clean Markdown with title, meta description and a token estimate; scripts, navigation and ads removed. max_chars 1 to 100000 (default 15000). $0.002; empty results are free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: Web Page to Markdown
x402_merchant_trust_checkPre-payment check of an x402 API endpoint: discovery files, live 402 terms, comparable USDC prices, latency, prompt-injection flags and public Coinbase CDP Bazaar payment statistic…Reads text others writeCan send data outNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.target_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Pre-payment check of an x402 API endpoint: discovery files, live 402 terms, comparable USDC prices, latency, prompt-injection flags and public Coinbase CDP Bazaar payment statistics for the host. Heuristic, not a guarantee. $0.002; unreachable targets are free. Online shops: pre_purchase_merchant_trust_check.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: x402 Merchant Trust Check
Only reads 4Show 4 read-only tools
agentic_shelf_schema_comparatorReturns structured public evidence and explicit unknowns.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Returns structured public evidence and explicit unknowns. Compares a brand with up to 3 competitors as shopping schema: prices, ratings, availability, shipping and returns, from one sampled product per store. $0.02 per comparison. Use for a bounded cross-store comparison; use universal_product_url_to_json for one product or muse_agentic_store_readiness_auditor for a single-store discovery audit. Unavailable evidence stays unknown.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: Shopping Schema Comparison
muse_conversion_leak_lead_finderReturns structured public evidence and explicit unknowns.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Returns structured public evidence and explicit unknowns. Store check for schema gaps, Google ad activity and public business contacts; a lead qualifies only with ad and SEO evidence. Public emails are not verified decision makers. $0.05 per qualified result. Use to qualify a known store for outreach about schema gaps; use muse_agentic_store_readiness_auditor for an audit without lead qualification or extract_company_contacts for contacts only. Does not send outreach or measure conversion loss.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: Conversion Leak Finder
universal_product_url_to_jsonReturns structured public evidence and explicit unknowns.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "universal_product_url_to_json" says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Returns structured public evidence and explicit unknowns. Product page to JSON: price, stock, variants, ratings and shipping evidence from JSON-LD, Microdata and OpenGraph, without a browser. Missing facts are null. $0.002 per result. Use for one product detail URL; use agentic_shelf_schema_comparator for a cross-store comparison or muse_agentic_store_readiness_auditor for a store-wide discovery audit.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: Product Page to JSON
verified_merchant_json_badgeReturns structured public evidence and explicit unknowns.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Returns structured public evidence and explicit unknowns. Signed public-evidence statement for a merchant domain, with expiry and a public verification key. It proves HirePulse issued the assessment, not ownership or purchase safety. $0.005 per result. Use when you need a portable signed assessment; use pre_purchase_merchant_trust_check for risk evidence without a badge or x402_merchant_trust_check for an API endpoint. It does not issue a third-party certification.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- title: Merchant Evidence Badge
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.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write11
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- agentic_shelf_schema_comparator
- ask_hirepulse_advisor
- checkout_active_promo_code_finder
- claim_free_trial
- muse_agentic_store_readiness_auditor
- muse_conversion_leak_lead_finder
- pre_purchase_merchant_trust_check
- universal_product_url_to_json
- url_to_clean_markdown
- verified_merchant_json_badge
- x402_merchant_trust_check
- Can send data out2
- 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.
Findings
Matches of fixed checks, with the text they matched.
The server marks "pre_purchase_merchant_trust_check" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "pre_purchase_merchant_trust_check" says "purchase": a word that usually means money moves, which cannot be taken back.
The server marks "checkout_active_promo_code_finder" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "checkout_active_promo_code_finder" says "checkout": a word for a change.
The server marks "muse_agentic_store_readiness_auditor" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "muse_agentic_store_readiness_auditor" says "store": a word for a change.
- Warnclaim_free_trial
The server marks "claim_free_trial" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"openWorldHint":true}; The description's first verb is "get": a word for reading.
The input schema at properties.url.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.url.description: "...private addresses, unsafe redirects and credential-bearing URLs are rejected."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http hirepulse-commerce https://gethirepulse.xyz/mcp?profile=commerce&ref=registry-commerceclaude mcp add --transport http hirepulse-commerce https://gethirepulse.xyz/mcp?profile=commerce&ref=registry-commerceRun 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__hirepulse-commerce__universal_product_url_to_json",
"mcp__hirepulse-commerce__muse_conversion_leak_lead_finder",
"mcp__hirepulse-commerce__agentic_shelf_schema_comparator",
"mcp__hirepulse-commerce__verified_merchant_json_badge"
],
"ask": [
"mcp__hirepulse-commerce__ask_hirepulse_advisor",
"mcp__hirepulse-commerce__x402_merchant_trust_check",
"mcp__hirepulse-commerce__url_to_clean_markdown",
"mcp__hirepulse-commerce__pre_purchase_merchant_trust_check",
"mcp__hirepulse-commerce__checkout_active_promo_code_finder",
"mcp__hirepulse-commerce__muse_agentic_store_readiness_auditor",
"mcp__hirepulse-commerce__claim_free_trial"
],
"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 hirepulse-commerce. Review it before you use it.
Capability tags behind 11 rules
- mcp__hirepulse-commerce__ask_hirepulse_advisor untrusted-input
- mcp__hirepulse-commerce__x402_merchant_trust_check untrusted-input, outbound
- mcp__hirepulse-commerce__url_to_clean_markdown untrusted-input, outbound
- mcp__hirepulse-commerce__pre_purchase_merchant_trust_check untrusted-input
- mcp__hirepulse-commerce__checkout_active_promo_code_finder untrusted-input
- mcp__hirepulse-commerce__universal_product_url_to_json untrusted-input
- mcp__hirepulse-commerce__muse_agentic_store_readiness_auditor untrusted-input
- mcp__hirepulse-commerce__muse_conversion_leak_lead_finder untrusted-input
- mcp__hirepulse-commerce__agentic_shelf_schema_comparator untrusted-input
- mcp__hirepulse-commerce__verified_merchant_json_badge untrusted-input
- mcp__hirepulse-commerce__claim_free_trial untrusted-input
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://anlyon.dev/api/v1/servers/io.github.edtool79-collab/hirepulse-commerce/verify?hash=3d0c97702bbcad085f637cf43d22e8df78e19ce9905411740807ff31fc644e87" | jq -e '.changed == false'Pinned hash 3d0c97702bbc, from Oct 26, 2026, 22:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://anlyon.dev/servers/io.github.edtool79-collab/hirepulse-commerce/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://anlyon.dev/servers/io.github.edtool79-collab/hirepulse-commerce)Source: MCP Registry · repository. Synced Oct 26, 2026, 22:17 UTC.