Falcon Docs: bank statement extraction for agents (x402)
io.github.ygfalcon/falcon-docsygfalconstreamable-httpv1.1.0Scanned
Bank statement extraction for agents: transactions, ADB, NSF, MCA metrics, plus invoices. x402.
3 tools: 2 change things and 1 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 3
- No findings
Anlyon alternative
2 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 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 →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.
3 tools
Changes things 2Claude Code: ask
extract_documentFull extraction of all pages.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 Full extraction of all pages. Costs $0.03 USDC (x402).
spread_bank_statementBank statement → every transaction + underwriting metrics (ADB, NSF, MCA/loan positions, revenue trend, DSCR inputs, tamper flags).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 Bank statement → every transaction + underwriting metrics (ADB, NSF, MCA/loan positions, revenue trend, DSCR inputs, tamper flags). Costs $0.25 USDC (x402).
Only reads 1Show 1 read-only tool
preview_documentFree: extract page 1 of a PDF (auto-detects invoice/receipt/PO/W-9/bank statement) with per-field confidence.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "preview_document" says "preview": a word for reading.
What it can reach
- private-dataThe name "preview_document" says "preview" and "document": it reads documents.
- private-dataThe input names a file (input.file_base64), and the tool reads: it reads files.
- 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 Free: extract page 1 of a PDF (auto-detects invoice/receipt/PO/W-9/bank statement) with per-field confidence.
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.
3 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 untrusted-input tool breaks every one.
- Reads private data1
- 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 out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__falcon-docs__preview_document"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
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 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http falcon-docs https://falcondocs.vercel.app/mcpclaude mcp add --transport http falcon-docs https://falcondocs.vercel.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__falcon-docs__preview_document",
"mcp__falcon-docs__extract_document",
"mcp__falcon-docs__spread_bank_statement"
],
"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 falcon-docs. Review it before you use it.
Capability tags behind 3 rules
- mcp__falcon-docs__preview_document private-data, untrusted-input, outbound
- mcp__falcon-docs__extract_document outbound
- mcp__falcon-docs__spread_bank_statement 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://anlyon.dev/api/v1/servers/io.github.ygfalcon/falcon-docs/verify?hash=cda8047b1265617079063043f09d3e23d1b8808a193422ba741f6231712a36ca" | jq -e '.changed == false'Pinned hash cda8047b1265, from Oct 23, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://anlyon.dev/servers/io.github.ygfalcon/falcon-docs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://anlyon.dev/servers/io.github.ygfalcon/falcon-docs)Source: MCP Registry. Synced Oct 23, 2026, 20:17 UTC.