FabTally Guard MCP server
io.github.zvmzaretsky/fabtally-guardzvmzaretskystreamable-httpv1.0.0Scanned
Verify before you act: deps-check, x402-preflight, json-repair & url-read for agents.
4 tools: 3 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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 FabTally Guard MCP server can do
The FabTally Guard MCP server is published by the GitHub account zvmzaretsky. It has 4 tools. It can create or change data (3 tools: deps_check, x402_preflight and json_repair), but cannot delete data. 1 tool only reads.
1 tool brings in text other people can write (url_read); 2 tools can send data out of your system (x402_preflight and url_read).
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 21, 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.
4 tools
Changes things 3Claude Code: ask
deps_checkPAID $0.003 (x402, USDC on Base).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it PAID $0.003 (x402, USDC on Base). Vet a software package BEFORE installing it. Returns existence, latest-vs-requested, deprecation/yank markers, known CVEs from OSV.dev, typosquat similarity to popular names, SPDX license, and age/download signals with a plain-English risk verdict. Args: ecosystem (npm|pypi|crates), name, version (optional). Without payment returns the x402 challenge; pass x_payment to settle.
json_repairPAID $0.002 (x402, USDC on Base).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it PAID $0.002 (x402, USDC on Base). Coerce near-miss LLM JSON to a JSON-Schema-conformant object: strip code fences/prose, fix trailing commas/quotes/unquoted keys, normalise Python literals, balance brackets, then coerce types, apply defaults, and drop extraneous keys. Returns the repaired object OR precise per-field errors. Args: json (the raw string), schema (a JSON Schema object). Without payment returns the x402 challenge.
x402_preflightPAID $0.002 (x402, USDC on Base).Can 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.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it PAID $0.002 (x402, USDC on Base). Verify another x402 endpoint BEFORE paying it: does an unpaid call return a valid x402 v2 402 challenge? do the quoted amount/asset/network/payTo match the site's /.well-known/x402? is TLS valid, host reachable, openapi present? Returns pass/fail + per-check reasons + the parsed price you would pay. Args: url. Without payment returns the x402 challenge; pass x_payment to settle.
Only reads 1Show 1 read-only tool
url_readPAID $0.004 (x402, USDC on Base).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "url_read" says "read": a word for reading.
What it can reach
- untrusted-inputThe name "url_read" says "read" and "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 PAID $0.004 (x402, USDC on Base). Fetch a PUBLIC url and return clean Markdown + a token estimate for RAG ingestion — readability extraction, boilerplate stripped. Respects robots.txt, public pages only, no login/paywall bypass, nothing stored. Args: url. Without payment returns the x402 challenge; pass x_payment to settle.
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 write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- 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.
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, 19:23 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://guard.fabtally.com/mcp: tools/list returned 4 tools to an anonymous client, including deps_check (write), x402_preflight (write), json_repair (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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http fabtally-guard https://guard.fabtally.com/mcpclaude mcp add --transport http fabtally-guard https://guard.fabtally.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": [],
"ask": [
"mcp__fabtally-guard__deps_check",
"mcp__fabtally-guard__x402_preflight",
"mcp__fabtally-guard__json_repair",
"mcp__fabtally-guard__url_read"
],
"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 fabtally-guard. Review it before you use it.
Capability tags behind 2 rules
- mcp__fabtally-guard__x402_preflight outbound
- mcp__fabtally-guard__url_read 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/io.github.zvmzaretsky/fabtally-guard/verify?hash=692f5c2837bae4c113ca2ca387d03a00c50a28aa6c5526610f17ce3b7c95a9a7" | jq -e '.changed == false'Pinned hash 692f5c2837ba, from Nov 21, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.zvmzaretsky/fabtally-guard/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.zvmzaretsky/fabtally-guard)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:52 UTC.
FabTally Guard MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the FabTally Guard MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 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 FabTally Guard MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the FabTally Guard 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 FabTally Guard MCP server have?
- 4 tools: 3 write, 1 read. deps_check, x402_preflight, json_repair and url_read.
Does the FabTally Guard MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the FabTally Guard MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): x402_preflight and url_read.
Has the FabTally Guard MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.