Agent Vending Factory MCP server
io.github.RubenTay/agent-vending-factoryRubenTaystreamable-httpv0.1.3Scanned
Pay-per-call MCP tools via x402 USDC: ZAR prices, data extraction, Python sandbox, SA flights.
4 tools: 4 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 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 Agent Vending Factory MCP server can do
The Agent Vending Factory MCP server is published by the GitHub account RubenTay. It has 4 tools. It can create or change data (4 tools: tool_zar_prices, tool_data_transformer, tool_compute_sandbox and tool_sa_airport_oracle), but cannot delete data. None of its tools only reads.
4 tools can send data out of your system (tool_zar_prices, tool_data_transformer, tool_compute_sandbox and 1 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 0.1.3.
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.
4 tools
Changes things 4Claude Code: ask
tool_compute_sandboxPOST /tools/tool_compute_sandbox/run — Executes Python 3.12 code in an isolated subprocess with a 5-second hard timeout.Can send data outNo findings
Why it is in this group
- The description's first verb is "post": a word for a change.
What it can reach
- outboundThe description's first verb is "post": it sends or publishes something to other people.
Description, as the server wrote it POST /tools/tool_compute_sandbox/run — Executes Python 3.12 code in an isolated subprocess with a 5-second hard timeout. Input: {python_code: string, input_data: any (optional, bound as variable 'input_data')}. Output: {success, result, stdout (capped 50KB), execution_time_ms, error_type}. Return value: assign to 'result' variable. Pre-loaded: math, json, re, statistics, itertools, functools, collections, decimal, datetime, random, hashlib, base64. Blocked: import, open(), eval(), exec(), os, sys, network, class definitions, dunder attributes. error_type values: syntax_error | security_error | runtime_error | timeout_error. Cost: $0.1500 USDC per call.
tool_data_transformerPOST /tools/tool_data_transformer/run — Extracts structured JSON from raw text using a caller-supplied JSON Schema.Can send data outNo findings
Why it is in this group
- The description's first verb is "post": a word for a change.
What it can reach
- outboundThe description's first verb is "post": it sends or publishes something to other people.
Description, as the server wrote it POST /tools/tool_data_transformer/run — Extracts structured JSON from raw text using a caller-supplied JSON Schema. Input: {raw_text: string, target_json_schema: object (JSON Schema draft-07)}. Output: {success, extracted_data, extraction_method, validation_passed, error}. extraction_method is one of: 'direct_parse', 'embedded_json', 'regex_extraction'. No LLM involved — pure parsing pipeline. Type coercion applied for integer/number/boolean fields. Works best with flat schemas; deeply nested structures extract less reliably via key-value pass. Cost: $0.0500 USDC per call.
tool_sa_airport_oraclePOST /tools/sa-airport-oracle/run — Returns live flight status from ACSA (airports.co.za).Can send data outNo findings
Why it is in this group
- The description's first verb is "post": a word for a change.
What it can reach
- outboundThe description's first verb is "post": it sends or publishes something to other people.
Description, as the server wrote it POST /tools/sa-airport-oracle/run — Returns live flight status from ACSA (airports.co.za). Input: {airport_code: 'JNB'|'CPT'|'DUR', flight_number: string, request_type: 'arrival'|'departure'}. Output: {success, live_status, scheduled_time, estimated_time, actual_time, gate, carousel, terminal, flight_number, airport_code, request_type, error}. Coverage: JNB (O.R. Tambo), CPT (Cape Town Int'l), DUR (King Shaka). Data window: flights within 48 hours. Call GET /tools/sa-airport-oracle/health (free) first — if structure_valid=false, do not proceed. error_type values: 'stale_data' (do not retry), 'not found' (retry after 10-15 min), network error (retry once). flight_number is case-insensitive and normalised to uppercase internally. Read-only — no booking/ticketing. Cost: $0.1200 USDC per call.
tool_zar_pricesPOST /tools/zar-prices/run — Returns live bid/ask/last prices for crypto/ZAR pairs.Can send data outNo findings
Why it is in this group
- The description's first verb is "post": a word for a change.
What it can reach
- outboundThe description's first verb is "post": it sends or publishes something to other people.
Description, as the server wrote it POST /tools/zar-prices/run — Returns live bid/ask/last prices for crypto/ZAR pairs. Input: {pair: 'BTC/ZAR'|'ETH/ZAR'|'SOL/ZAR'|'USDC/ZAR'|'all'}. Output: array of {exchange, pair, price, bid, ask, timestamp} objects. Sources: VALR (all 4 pairs), Luno (BTC/ZAR + ETH/ZAR only). SOL/ZAR and USDC/ZAR are VALR-only. Fetches all exchanges concurrently. Timestamps are ISO-8601 UTC. Cost: $0.0050 USDC per call.
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.
- 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 out4
- 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, 19:00 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
- 4
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent-vending-factory-3srpjtr7na-ew.a.run.app/mcp: tools/list returned 4 tools to an anonymous client, including tool_zar_prices (write), tool_data_transformer (write), tool_compute_sandbox (write), tool_sa_airport_oracle (write)
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-vending-factory https://agent-vending-factory-3srpjtr7na-ew.a.run.app/mcpclaude mcp add --transport http agent-vending-factory https://agent-vending-factory-3srpjtr7na-ew.a.run.app/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": [],
"ask": [
"mcp__agent-vending-factory__tool_zar_prices",
"mcp__agent-vending-factory__tool_data_transformer",
"mcp__agent-vending-factory__tool_compute_sandbox",
"mcp__agent-vending-factory__tool_sa_airport_oracle"
],
"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 agent-vending-factory. Review it before you use it.
Capability tags behind 4 rules
- mcp__agent-vending-factory__tool_zar_prices outbound
- mcp__agent-vending-factory__tool_data_transformer outbound
- mcp__agent-vending-factory__tool_compute_sandbox outbound
- mcp__agent-vending-factory__tool_sa_airport_oracle 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/io.github.RubenTay/agent-vending-factory/verify?hash=e7c0a2c38ce9c114d7aba1381383a112c5b0bf72e62312a0cad346c2ec3d4617" | jq -e '.changed == false'Pinned hash e7c0a2c38ce9, from Nov 16, 2026, 04:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.RubenTay/agent-vending-factory/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.RubenTay/agent-vending-factory)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:21 UTC.
Agent Vending Factory MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Vending Factory MCP server safe?
- No scan can promise that. What its definitions show: 4 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 Agent Vending Factory MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Vending Factory 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 Agent Vending Factory MCP server have?
- 4 tools: 4 write. tool_zar_prices, tool_data_transformer, tool_compute_sandbox and tool_sa_airport_oracle.
Does the Agent Vending Factory MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Vending Factory MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): tool_zar_prices, tool_data_transformer, tool_compute_sandbox and tool_sa_airport_oracle.
Has the Agent Vending Factory MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.