ProfitCollector MCP server
ca.bakhour/profitcollectorbakhour.castreamable-httpv1.0.0Scanned
22 pay-per-call developer, security, network and data utilities using x402 on Base.
31 tools: 1 can delete or cancel things, 21 change things and 9 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 24
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- 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 ProfitCollector MCP server can do
The ProfitCollector MCP server is published by bakhour.ca, a domain the MCP Registry verified. It has 31 tools. It can delete or cancel things (1 tool: post_text_dedupe_lines) and create or change data (21 tools: post_json_repair, post_media_image_convert, post_security_repo_risk_report_standard, post_security_repo_risk_report_deep and 17 more). 9 tools only read.
4 tools bring in text other people can write (get_url_parse, get_web_audit, get_security_posture and 1 more); 24 tools can send data out of your system (post_json_repair, post_media_image_convert, post_security_repo_risk_report_standard and 21 more).
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 12, 2026, version 1.0.0.
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.
31 tools
Deletes or cancels 1Claude Code: deny
post_text_dedupe_linesRemove duplicate lines while preserving original order.Can send data outNo findings
Why it is in this group
- The name "post_text_dedupe_lines" says "post": a word for a change.
- The description's first verb is "remove": a word for removing or ending something.
What it can reach
- outboundThe name "post_text_dedupe_lines" says "post": it sends or publishes something to other people.
Description, as the server wrote it Remove duplicate lines while preserving original order.
Changes things 21Claude Code: ask
get_timestamp_convertConvert a Unix timestamp to UTC ISO-8601.No findings
Why it is in this group
- The name "get_timestamp_convert" says "get": a word for reading.
- The description's first verb is "convert": a word for a change.
Description, as the server wrote it Convert a Unix timestamp to UTC ISO-8601.
get_uuid_generateGenerate a random UUID version 4.No findings
Why it is in this group
- The name "get_uuid_generate" says "get": a word for reading.
- The description's first verb is "generate": a word for a change.
Description, as the server wrote it Generate a random UUID version 4.
post_base64_decodeDecode Base64 to UTF-8 text.Can send data outNo findings
Why it is in this group
- The name "post_base64_decode" says "post": a word for a change.
What it can reach
- outboundThe name "post_base64_decode" says "post": it sends or publishes something to other people.
Description, as the server wrote it Decode Base64 to UTF-8 text.
post_base64_encodeEncode UTF-8 text using Base64.Can send data outNo findings
Why it is in this group
- The name "post_base64_encode" says "post": a word for a change.
What it can reach
- outboundThe name "post_base64_encode" says "post": it sends or publishes something to other people.
Description, as the server wrote it Encode UTF-8 text using Base64.
post_data_transformNormalize and transform common structured text automatically.Can send data outNo findings
Why it is in this group
- The name "post_data_transform" says "post": a word for a change.
What it can reach
- outboundThe name "post_data_transform" says "post": it sends or publishes something to other people.
Description, as the server wrote it Normalize and transform common structured text automatically.
post_domain_due_diligenceThe most comprehensive domain assessment: DNS + mail security (SPF/DKIM/DMARC) + TLS + HTTP headers, scored.Can send data outNo findings
Why it is in this group
- The name "post_domain_due_diligence" says "post": a word for a change.
What it can reach
- outboundThe name "post_domain_due_diligence" says "post": it sends or publishes something to other people.
Description, as the server wrote it The most comprehensive domain assessment: DNS + mail security (SPF/DKIM/DMARC) + TLS + HTTP headers, scored. The only endpoint in this group that adds mail-security analysis. Use for a one-shot decision-grade verdict on an unfamiliar domain; use /dns/lookup, /ssl/check, /security/headers, /web/audit or /security/posture instead for a single fact or a cheaper signal.
post_freshdep_scanFlags pinned dependencies in a repository's requirements.txt, package-lock.json, or uv.lock published more recently than a freshness threshold -- a supply-chain-compromise tripwire…Can send data outNo findings
Why it is in this group
- The name "post_freshdep_scan" says "post": a word for a change.
What it can reach
- outboundThe name "post_freshdep_scan" says "post": it sends or publishes something to other people.
Description, as the server wrote it Flags pinned dependencies in a repository's requirements.txt, package-lock.json, or uv.lock published more recently than a freshness threshold -- a supply-chain-compromise tripwire. Free CLI (requirements.txt/package-lock.json only, uv.lock support pending there): github.com/sbakhour/freshdep.
post_hash_sha256Generate SHA-256 digest from text.Can send data outNo findings
Why it is in this group
- The name "post_hash_sha256" says "post": a word for a change.
What it can reach
- outboundThe name "post_hash_sha256" says "post": it sends or publishes something to other people.
Description, as the server wrote it Generate SHA-256 digest from text.
post_hash_sha512Generate SHA-512 digest from text.Can send data outNo findings
Why it is in this group
- The name "post_hash_sha512" says "post": a word for a change.
What it can reach
- outboundThe name "post_hash_sha512" says "post": it sends or publishes something to other people.
Description, as the server wrote it Generate SHA-512 digest from text.
post_json_minifyMinify valid JSON text.Can send data outNo findings
Why it is in this group
- The name "post_json_minify" says "post": a word for a change.
What it can reach
- outboundThe name "post_json_minify" says "post": it sends or publishes something to other people.
Description, as the server wrote it Minify valid JSON text.
post_json_prettyPretty-print valid JSON text.Can send data outNo findings
Why it is in this group
- The name "post_json_pretty" says "post": a word for a change.
What it can reach
- outboundThe name "post_json_pretty" says "post": it sends or publishes something to other people.
Description, as the server wrote it Pretty-print valid JSON text.
post_json_repairRepair common malformed JSON formatting issues.Can send data outNo findings
Why it is in this group
- The name "post_json_repair" says "post": a word for a change.
What it can reach
- outboundThe name "post_json_repair" says "post": it sends or publishes something to other people.
Description, as the server wrote it Repair common malformed JSON formatting issues.
post_json_validateValidate JSON text and return parsing details.Can send data outNo findings
Why it is in this group
- The name "post_json_validate" says "post": a word for a change.
What it can reach
- outboundThe name "post_json_validate" says "post": it sends or publishes something to other people.
Description, as the server wrote it Validate JSON text and return parsing details.
post_media_image_convertConvert an image between common formats (e.g.Can send data outNo findings
Why it is in this group
- The name "post_media_image_convert" says "post": a word for a change.
What it can reach
- outboundThe name "post_media_image_convert" says "post": it sends or publishes something to other people.
Description, as the server wrote it Convert an image between common formats (e.g. PNG/JPEG/WebP) from a URL or base64 payload.
post_quebec_invoice_compliance_checkVerifies GST/QST were calculated correctly per Revenu Quebec's current (non-compounded) formula, and flags whether a French invoice version is present per Charter of the French Lan…Can send data outNo findings
Why it is in this group
- The name "post_quebec_invoice_compliance_check" says "post": a word for a change.
What it can reach
- outboundThe name "post_quebec_invoice_compliance_check" says "post": it sends or publishes something to other people.
Description, as the server wrote it Verifies GST/QST were calculated correctly per Revenu Quebec's current (non-compounded) formula, and flags whether a French invoice version is present per Charter of the French Language s.57/89/91. Pure arithmetic + text check; not legal or tax advice.
post_quebec_invoice_generateAssembles a bilingual (French/English) Quebec invoice document with GST/QST computed exactly per Revenu Quebec's current formula -- you supply both languages' line-item text, this …Can send data outNo findings
Why it is in this group
- The name "post_quebec_invoice_generate" says "post": a word for a change.
What it can reach
- outboundThe name "post_quebec_invoice_generate" says "post": it sends or publishes something to other people.
Description, as the server wrote it Assembles a bilingual (French/English) Quebec invoice document with GST/QST computed exactly per Revenu Quebec's current formula -- you supply both languages' line-item text, this does not translate. Not legal or tax advice.
post_security_repo_risk_report_deepEverything in the standard report, plus a repo-wide secret/credential exposure scan (matched values are never returned).Can send data out1 finding
Why it is in this group
- The name "post_security_repo_risk_report_deep" says "post": a word for a change.
What it can reach
- outboundThe name "post_security_repo_risk_report_deep" says "post": it sends or publishes something to other people.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...tandard report, plus a repo-wide secret/credential exposure scan (matched values are never..."
Description, as the server wrote it Everything in the standard report, plus a repo-wide secret/credential exposure scan (matched values are never returned).
post_security_repo_risk_report_due_diligenceEverything in the deep report, plus real OpenSSF Scorecard maintainer/governance signals and a prioritized recommendation.Can send data outNo findings
Why it is in this group
- The name "post_security_repo_risk_report_due_diligence" says "post": a word for a change.
What it can reach
- outboundThe name "post_security_repo_risk_report_due_diligence" says "post": it sends or publishes something to other people.
Description, as the server wrote it Everything in the deep report, plus real OpenSSF Scorecard maintainer/governance signals and a prioritized recommendation. An automated baseline positioned against $5,000-$95,000 human technical due diligence.
post_security_repo_risk_report_standardSBOM inventory plus real OSV.dev dependency-vulnerability matches and dependency-freshness signals for a public Git repository.Can send data outNo findings
Why it is in this group
- The name "post_security_repo_risk_report_standard" says "post": a word for a change.
What it can reach
- outboundThe name "post_security_repo_risk_report_standard" says "post": it sends or publishes something to other people.
Description, as the server wrote it SBOM inventory plus real OSV.dev dependency-vulnerability matches and dependency-freshness signals for a public Git repository. One-shot alternative to a per-seat secret-scanning subscription.
post_text_statsCalculate character, word, line and byte statistics.Can send data outNo findings
Why it is in this group
- The name "post_text_stats" says "post": a word for a change.
What it can reach
- outboundThe name "post_text_stats" says "post": it sends or publishes something to other people.
Description, as the server wrote it Calculate character, word, line and byte statistics.
post_x402_service_trust_reportLive, on-demand check of ONE x402-protected endpoint before you pay it: payment-requirements structure, TLS certificate, payTo on-chain balance, known-asset recognition, resource/h…Can send data outNo findings
Why it is in this group
- The name "post_x402_service_trust_report" says "post": a word for a change.
What it can reach
- outboundThe name "post_x402_service_trust_report" says "post": it sends or publishes something to other people.
- 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 Live, on-demand check of ONE x402-protected endpoint before you pay it: payment-requirements structure, TLS certificate, payTo on-chain balance, known-asset recognition, resource/host consistency, and discovery-manifest cross-check -- not a cached aggregate reputation score.
Only reads 9Show 9 read-only tools
get_dns_lookupResolve ONE DNS record type for a domain.No findings
Why it is in this group
- The name "get_dns_lookup" says "get": a word for reading.
Description, as the server wrote it Resolve ONE DNS record type for a domain. For all record types at once use /domain/intelligence; for a bundled DNS+TLS+headers audit use /web/audit or /security/posture; for mail-security plus a scored verdict use /domain/due-diligence.
get_domain_intelligenceCollect ALL common DNS record types (A/AAAA/MX/NS/TXT/CAA) for a domain in one call -- the multi-record bundle version of /dns/lookup.No findings
Why it is in this group
- The name "get_domain_intelligence" says "get": a word for reading.
Description, as the server wrote it Collect ALL common DNS record types (A/AAAA/MX/NS/TXT/CAA) for a domain in one call -- the multi-record bundle version of /dns/lookup.
get_jwt_decodeDecode a JWT payload without signature verification.No findings
Why it is in this group
- The name "get_jwt_decode" says "get": a word for reading.
Description, as the server wrote it Decode a JWT payload without signature verification.
get_security_headersInspect HTTP security headers for ONE URL only.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_security_headers" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "inspect" and "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Inspect HTTP security headers for ONE URL only. For headers combined with TLS and DNS, use /web/audit (raw) or /security/posture (scored).
get_security_postureAssess TLS and HTTP security posture for a public HTTPS website -- the SAME inspection as /web/audit, but returns a 0-100 score/grade and findings instead of raw fields.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_security_posture" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Assess TLS and HTTP security posture for a public HTTPS website -- the SAME inspection as /web/audit, but returns a 0-100 score/grade and findings instead of raw fields.
get_ssl_checkInspect the TLS certificate for ONE hostname only.No findings
Why it is in this group
- The name "get_ssl_check" says "get": a word for reading.
Description, as the server wrote it Inspect the TLS certificate for ONE hostname only. For TLS combined with HTTP headers and DNS, use /web/audit (raw) or /security/posture (scored).
get_subnet_calculateCalculate subnet information from CIDR notation.No findings
Why it is in this group
- The name "get_subnet_calculate" says "get": a word for reading.
Description, as the server wrote it Calculate subnet information from CIDR notation.
get_url_parseParse a URL into structured components.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_url_parse" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_url_parse" says "get" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Parse a URL into structured components.
get_web_auditConsolidated DNS, TLS and HTTP security audit for a public HTTPS website, returned as RAW findings (no score) -- the bundled version of /dns/lookup + /ssl/check + /security/headers…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_web_audit" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_web_audit" says "get" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Consolidated DNS, TLS and HTTP security audit for a public HTTPS website, returned as RAW findings (no score) -- the bundled version of /dns/lookup + /ssl/check + /security/headers. Use /security/posture instead for a 0-100 score/grade.
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 write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out24
- 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, 18:31 UTC, unchanged since Oct 22, 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
- 22
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 22 tools that change things (1 destructive, 21 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.bakhour.ca/mcp: tools/list returned 31 tools to an anonymous client, including post_text_dedupe_lines (destructive), post_json_repair (write), post_media_image_convert (write), post_security_repo_risk_report_standard (write), post_security_repo_risk_report_deep (write) and 17 more
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credential".
What this check looks forMatched text
description: "...tandard report, plus a repo-wide secret/credential exposure scan (matched values are never..."
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 profitcollector https://mcp.bakhour.ca/mcpclaude mcp add --transport http profitcollector https://mcp.bakhour.ca/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__profitcollector__get_dns_lookup",
"mcp__profitcollector__get_jwt_decode",
"mcp__profitcollector__get_subnet_calculate",
"mcp__profitcollector__get_domain_intelligence",
"mcp__profitcollector__get_ssl_check"
],
"ask": [
"mcp__profitcollector__post_json_repair",
"mcp__profitcollector__post_media_image_convert",
"mcp__profitcollector__post_security_repo_risk_report_standard",
"mcp__profitcollector__post_security_repo_risk_report_deep",
"mcp__profitcollector__post_security_repo_risk_report_due_diligence",
"mcp__profitcollector__post_x402_service_trust_report",
"mcp__profitcollector__post_freshdep_scan",
"mcp__profitcollector__post_quebec_invoice_compliance_check",
"mcp__profitcollector__post_quebec_invoice_generate",
"mcp__profitcollector__post_json_validate",
"mcp__profitcollector__post_json_pretty",
"mcp__profitcollector__post_json_minify",
"mcp__profitcollector__post_base64_encode",
"mcp__profitcollector__post_base64_decode",
"mcp__profitcollector__post_hash_sha256",
"mcp__profitcollector__post_hash_sha512",
"mcp__profitcollector__get_uuid_generate",
"mcp__profitcollector__get_url_parse",
"mcp__profitcollector__post_text_stats",
"mcp__profitcollector__get_timestamp_convert",
"mcp__profitcollector__post_domain_due_diligence",
"mcp__profitcollector__get_web_audit",
"mcp__profitcollector__get_security_posture",
"mcp__profitcollector__post_data_transform",
"mcp__profitcollector__get_security_headers"
],
"deny": [
"mcp__profitcollector__post_text_dedupe_lines"
]
}
}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 profitcollector. Review it before you use it.
Capability tags behind 24 rules
- mcp__profitcollector__post_json_repair outbound
- mcp__profitcollector__post_media_image_convert outbound
- mcp__profitcollector__post_security_repo_risk_report_standard outbound
- mcp__profitcollector__post_security_repo_risk_report_deep outbound
- mcp__profitcollector__post_security_repo_risk_report_due_diligence outbound
- mcp__profitcollector__post_x402_service_trust_report outbound
- mcp__profitcollector__post_freshdep_scan outbound
- mcp__profitcollector__post_quebec_invoice_compliance_check outbound
- mcp__profitcollector__post_quebec_invoice_generate outbound
- mcp__profitcollector__post_json_validate outbound
- mcp__profitcollector__post_json_pretty outbound
- mcp__profitcollector__post_json_minify outbound
- mcp__profitcollector__post_base64_encode outbound
- mcp__profitcollector__post_base64_decode outbound
- mcp__profitcollector__post_hash_sha256 outbound
- mcp__profitcollector__post_hash_sha512 outbound
- mcp__profitcollector__get_url_parse untrusted-input, outbound
- mcp__profitcollector__post_text_stats outbound
- mcp__profitcollector__post_text_dedupe_lines outbound
- mcp__profitcollector__post_domain_due_diligence outbound
- mcp__profitcollector__get_web_audit untrusted-input, outbound
- mcp__profitcollector__get_security_posture untrusted-input, outbound
- mcp__profitcollector__post_data_transform outbound
- mcp__profitcollector__get_security_headers untrusted-input, outbound
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/ca.bakhour/profitcollector/verify?hash=66ed600303185e4943c917a9d04792d63478abe556ca741226e4520d34738e4e" | jq -e '.changed == false'Pinned hash 66ed60030318, from Nov 12, 2026, 07:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ca.bakhour/profitcollector/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ca.bakhour/profitcollector)Source: MCP Registry. Synced Oct 21, 2026, 17:46 UTC.
ProfitCollector MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ProfitCollector MCP server safe?
- No scan can promise that. What its definitions show: 31 tools, 22 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ProfitCollector MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: post_text_dedupe_lines.
Can the ProfitCollector 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 ProfitCollector MCP server have?
- 31 tools: 1 destructive, 21 write, 9 read. post_text_dedupe_lines, post_json_repair, post_media_image_convert, post_security_repo_risk_report_standard, post_security_repo_risk_report_deep, post_security_repo_risk_report_due_diligence, post_x402_service_trust_report, post_freshdep_scan and 23 more.
Does the ProfitCollector MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ProfitCollector MCP server send data to outside services?
- 24 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): post_json_repair, post_media_image_convert, post_security_repo_risk_report_standard, post_security_repo_risk_report_deep, post_security_repo_risk_report_due_diligence, post_x402_service_trust_report and 18 more.
Has the ProfitCollector MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.