Skip to content

Oxaide — Singapore company research for AI agents MCP server

io.github.leewenjie/oxaideleewenjiestreamable-httpv2.0.1Scanned

Agent-buys cited Singapore company research: ACRA/URA/GeBIZ packs, S$49/390/1500 per job.

8 tools: 1 do something that can't be undone, 3 change things and 4 only read.

Tools: 0 delete, 1 irreversible, 3 write, 4 read.
  • Reads private data · 2
  • Reads text others write · 5
  • Can send data out · 0
  • No findings

Sign-in required, no OAuth metadata. Remote posture

Anlyon alternative

4 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 Radar 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 →

What the Oxaide — Singapore company research for AI agents MCP server can do

The Oxaide — Singapore company research for AI agents MCP server is published by the GitHub account leewenjie. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (pay_audit) and create or change data (3 tools: create_audit, ping_check and subscribe_watch), but cannot delete data. 4 tools only read.

2 tools read private data (ping_check and get_audit_result); 5 tools bring in text other people can write (create_audit, ping_check, pay_audit and 2 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 6, 2026, version 2.0.1.

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

Can't be undone 1Claude Code: ask
  • pay_auditPay a quoted job.Reads text others writeNo findings

    Why it is in this group

    • The name "pay_audit" says "pay": a word that usually means money moves, which cannot be taken back.

    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
    Pay a quoted job. method=stripe returns a Stripe Checkout URL (cards + PayNow). method=x402 (default) returns x402 v2 payment requirements (USDC on Base); pay, then call again with the PAYMENT-SIGNATURE header or _meta["x402/payment"] to settle. Work starts only after payment is verified AND settled.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Changes things 3Claude Code: ask
  • create_auditCreate a private research job (Oxaide).Reads text others writeNo findings

    Why it is in this group

    • The name "create_audit" says "create": a word for a change.

    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
    Create a private research job (Oxaide). Returns a job id immediately; the AI quote (S$49 Quick check / S$390 Pack / S$1500 Board pack) is emailed within ~15m. Pay with pay_audit before any work starts.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • ping_checkRun one prepaid registry ping (Quick check, ~5 min, result by email + status page).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "ping_check" says "ping": a word for reading.
    • The description's first verb is "run": a word for a change.

    What it can reach

    • private-dataThe description's first sentence says "email": it reads mail.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "run" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Run one prepaid registry ping (Quick check, ~5 min, result by email + status page). Needs a pack_id from a ping-pack purchase (100 pings S$150, 90d). The delivery email must match the purchase email (+tags ok). No pack? POST /api/brief/ping-pack first (see https://oxaide.com/agents).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • subscribe_watchStart a prepaid 12-month Watchdesk watch: UEN S$490, business-name S$290, IPOS-filing S$790, supplier S$990, portfolio S$2,490, grant-call S$490, award-intel S$990.Reads text others writeNo findings

    Why it is in this group

    • The name "subscribe_watch" says "subscribe": a word for a change.

    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
    Start a prepaid 12-month Watchdesk watch: UEN S$490, business-name S$290, IPOS-filing S$790, supplier S$990, portfolio S$2,490, grant-call S$490, award-intel S$990. Returns a Stripe checkout URL (cards + PayNow); the watch activates on payment. Needs the target + delivery email.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 4Show 4 read-only tools
  • get_auditGet one job: status, quoted tier/price, payment state, delivery state.No findings

    Why it is in this group

    • The name "get_audit" says "get": a word for reading.
    Description, as the server wrote it
    Get one job: status, quoted tier/price, payment state, delivery state. Poll after create_audit.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_audit_resultGet the delivered answer/pack for a job (markdown summary; files arrive by email + status page).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_audit_result" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "file": it reads files.
    • untrusted-inputThe description's first sentence says "get" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Get the delivered answer/pack for a job (markdown summary; files arrive by email + status page).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_auditsAdmin only: list recent jobs.No findings

    Why it is in this group

    • The name "list_audits" says "list": a word for reading.
    Description, as the server wrote it
    Admin only: list recent jobs. Requires admin_token matching the server MCP_ADMIN_TOKEN (disabled when unset). Never open to the public.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • lookup_ownershipFree instant lookup: registered name, status, entity type, and registration date for a UEN from the monthly register snapshot.No findings

    Why it is in this group

    • The name "lookup_ownership" says "lookup": a word for reading.
    Description, as the server wrote it
    Free instant lookup: registered name, status, entity type, and registration date for a UEN from the monthly register snapshot. Officers and shareholders are NOT in the free snapshot — for the ownership chain, open a cited screen with create_audit ("Ownership of <name> (<uen>)").

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • 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 outbound.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write5
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.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 19:07 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
410
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: initialize answered HTTP 410.

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 200 to 410
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 4 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 410; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 4 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 410
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 4 to 0
    • Protocol version: 2025-06-18 to none
  2. Tools1 changed.~1 changedView diff

Install

Pinned to version 2.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http oxaide https://oxaide.com/mcp
claude mcp add --transport http oxaide https://oxaide.com/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__oxaide__get_audit",
      "mcp__oxaide__get_audit_result",
      "mcp__oxaide__lookup_ownership",
      "mcp__oxaide__list_audits"
    ],
    "ask": [
      "mcp__oxaide__create_audit",
      "mcp__oxaide__ping_check",
      "mcp__oxaide__pay_audit",
      "mcp__oxaide__subscribe_watch"
    ],
    "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 oxaide. Review it before you use it.

Capability tags behind 5 rules
  • mcp__oxaide__create_audit untrusted-input
  • mcp__oxaide__ping_check private-data, untrusted-input
  • mcp__oxaide__pay_audit untrusted-input
  • mcp__oxaide__get_audit_result private-data, untrusted-input
  • mcp__oxaide__subscribe_watch 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://radar.anlyon.com/api/v1/servers/io.github.leewenjie/oxaide/verify?hash=4ad1b5e1f1e651218a6d00bec64fe72a2a1d5e1f3a21c9c4a5a5cd6f0fb85427" | jq -e '.changed == false'

Pinned hash 4ad1b5e1f1e6, from Nov 6, 2026, 02:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.leewenjie/oxaide/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.leewenjie/oxaide
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.leewenjie/oxaide.svg)](https://radar.anlyon.com/servers/io.github.leewenjie/oxaide)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:38 UTC.

Oxaide — Singapore company research for AI agents MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Oxaide — Singapore company research for AI agents MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 4 of which can change, send or delete something, and 0 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 Oxaide — Singapore company research for AI agents MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Oxaide — Singapore company research for AI agents MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: pay_audit.

What tools does the Oxaide — Singapore company research for AI agents MCP server have?

8 tools: 1 irreversible, 3 write, 4 read. pay_audit, create_audit, ping_check, subscribe_watch, get_audit, get_audit_result, lookup_ownership and list_audits.

Does the Oxaide — Singapore company research for AI agents MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Oxaide — Singapore company research for AI agents MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Oxaide — Singapore company research for AI agents MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 6, 2026. Every change is on this page and in its Atom feed.