Anto Joel — Portfolio MCP server
com.antojoel/portfolioantojoel.comstreamable-httpv1.0.0Scanned
Ask about Anto Joel: profile, case studies, skill evidence, role-fit checks, and booking a call.
7 tools: 1 do something that can't be undone, 2 change things and 4 only read.
- Reads private data · 2
- Reads text others write · 2
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. 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 Anto Joel — Portfolio MCP server can do
The Anto Joel — Portfolio MCP server is published by antojoel.com, a domain the MCP Registry verified. It has 7 tools. It can do things that cannot be undone, such as sending, paying or publishing (priority_intro) and create or change data (2 tools: evaluate_role_fit and book_call), but cannot delete data. 4 tools only read.
2 tools read private data (get_profile and list_case_studies); 2 tools bring in text other people can write (list_case_studies and priority_intro); 1 tool can send data out of your system (priority_intro). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way 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 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.
7 tools
Can't be undone 1Claude Code: ask
priority_introSend Anto a priority message that lands in his inbox flagged PRIORITY, with a reply within 48 hours.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send Anto a priority message that lands in his inbox flagged PRIORITY, with a reply within 48 hours. Costs $0.01 USDC on Base, paid via x402. You are only charged if the message is delivered. Only call when the user explicitly asks to reach out and has approved the payment; use the user's real email so Anto can reply. For a free option, use book_call.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 2Claude Code: ask
book_callReturns Anto's booking link and a suggested agenda.1 finding
Why it is in this group
- The name "book_call" says "call": 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 "book_call" 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 "book_call" says "call": a word for a change.
Description, as the server wrote it Returns Anto's booking link and a suggested agenda. Use when the user wants to talk to him, schedule an interview, or discuss a project.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
evaluate_role_fitCall when the user shares a job description or asks whether Anto fits a role.1 finding
Why it is in this group
- The name "evaluate_role_fit" says "evaluate": 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 "evaluate_role_fit" 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 "evaluate_role_fit" says "evaluate": a word for a change.
Description, as the server wrote it Call when the user shares a job description or asks whether Anto fits a role. Returns his complete record and a rubric for an honest, evidence-based fit assessment, including gaps.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 4Show 4 read-only tools
get_journeyWork history (resume), newest first: role, company, dates and quantified highlights, plus the career story across India and the UAE.No findings
Why it is in this group
- The name "get_journey" says "get": a word for reading.
Description, as the server wrote it Work history (resume), newest first: role, company, dates and quantified highlights, plus the career story across India and the UAE.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_profileOverview for recruiters, hiring managers and founders: current role, location, what he's open to, how he works, headline stats and contact links.Reads private dataNo findings
Why it is in this group
- The name "get_profile" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "contact": it reads contacts.
Description, as the server wrote it Overview for recruiters, hiring managers and founders: current role, location, what he's open to, how he works, headline stats and contact links. Start here.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_skills_with_evidenceEvery skill mapped to where it shipped and a proof point.No findings
Why it is in this group
- The name "get_skills_with_evidence" says "get": a word for reading.
Description, as the server wrote it Every skill mapped to where it shipped and a proof point. Use to check requirements from a job description. A skill missing from this list has no evidence.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_case_studiesCase studies (production voice AI at Machani Robotics plus six shipped ventures), side projects and build notes, framed as product work: problem, decision, trade-offs, outcome, met…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_case_studies" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "note": it reads notes.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Case studies (production voice AI at Machani Robotics plus six shipped ventures), side projects and build notes, framed as product work: problem, decision, trade-offs, outcome, metrics. Fields that are absent are not documented; do not invent them.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
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.
4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__portfolio__priority_intro"
]
}
}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, 18:34 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
- 3
- 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 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.antojoel.com/mcp: tools/list returned 7 tools to an anonymous client, including priority_intro (irreversible), evaluate_role_fit (write), book_call (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "evaluate_role_fit" 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 "evaluate_role_fit" says "evaluate": a word for a change.
- Warnbook_call
The server marks "book_call" 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 "book_call" says "call": a word for a change.
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 portfolio https://www.antojoel.com/mcpclaude mcp add --transport http portfolio https://www.antojoel.com/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__portfolio__get_profile",
"mcp__portfolio__get_journey",
"mcp__portfolio__list_case_studies",
"mcp__portfolio__get_skills_with_evidence"
],
"ask": [
"mcp__portfolio__evaluate_role_fit",
"mcp__portfolio__book_call",
"mcp__portfolio__priority_intro"
],
"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 portfolio. Review it before you use it.
Capability tags behind 3 rules
- mcp__portfolio__get_profile private-data
- mcp__portfolio__list_case_studies private-data, untrusted-input
- mcp__portfolio__priority_intro 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/com.antojoel/portfolio/verify?hash=a8668712f97eace6969caca7556c671612d5d6ff5a4d7086853e25b29939ea93" | jq -e '.changed == false'Pinned hash a8668712f97e, from Nov 12, 2026, 15:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.antojoel/portfolio/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.antojoel/portfolio)Source: MCP Registry. Synced Oct 21, 2026, 17:49 UTC.
Anto Joel — Portfolio MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Anto Joel — Portfolio MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 3 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 Anto Joel — Portfolio MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Anto Joel — Portfolio MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: priority_intro.
What tools does the Anto Joel — Portfolio MCP server have?
- 7 tools: 1 irreversible, 2 write, 4 read. priority_intro, evaluate_role_fit, book_call, get_profile, get_journey, list_case_studies and get_skills_with_evidence.
Does the Anto Joel — Portfolio MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Anto Joel — Portfolio MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): priority_intro.
Has the Anto Joel — Portfolio MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.