Skip to content

FINLY Balance Report Analysis MCP server

il.co.finly/report-analysisfinly.co.ilstreamable-httpv0.1.0Scanned

Israeli mortgage reports with Hebrew results, 15-minute recovery and authorized external OCR.

4 tools: 1 can delete or cancel things, 2 change things and 1 only read.

Tools: 1 delete, 0 irreversible, 2 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 FINLY Balance Report Analysis MCP server can do

The FINLY Balance Report Analysis MCP server is published by finly.co.il, a domain the MCP Registry verified. It has 4 tools. It can delete or cancel things (1 tool: delete_report_analysis_result) and create or change data (2 tools: analyze_balance_report and get_report_analysis_requirements). 1 tool only reads.

1 tool brings in text other people can write (analyze_balance_report).

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 15, 2026, version 0.1.0.

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

Deletes or cancels 1Claude Code: deny
  • delete_report_analysis_resultCancel this operation and delete its encrypted result using its exact capability.No findings

    Why it is in this group

    • The name "delete_report_analysis_result" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Cancel this operation and delete its encrypted result using its exact capability. A deleted operation cannot be restarted. No raw report, identity or result is placed in the URL.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Changes things 2Claude Code: ask
  • analyze_balance_reportAnalyze a PDF, JPEG or PNG balance report.Reads text others write1 finding

    Why it is in this group

    • The name "analyze_balance_report" says "analyze": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "analyze_balance_report" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "analyze_balance_report" says "analyze": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Analyze a PDF, JPEG or PNG balance report. Include the pre-issued operation for encrypted result recovery and safe same-payload replay for up to 15 minutes from issuance; restarting the service ends recovery. Omit operation only for legacy immediate-only delivery. Raw reports are not persisted. Returns structured facts and readable Hebrew text/HTML. External OCR sends personal/financial mortgage data to Google Document AI outside Israel only with an agent attestation that the existing task permits this transfer, or legacy separate approval. The supplier notice hash is not evidence a human saw it. Local-only is the default. A terminal failure never restarts the same operation.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • get_report_analysis_requirementsGet the processing notice, external OCR supplier notices for existing-task authority or legacy approval, and a single-use proof-of-work challenge.1 finding

    Why it is in this group

    • The name "get_report_analysis_requirements" says "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "get_report_analysis_requirements" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_report_analysis_requirements" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Get the processing notice, external OCR supplier notices for existing-task authority or legacy approval, and a single-use proof-of-work challenge. Normal report analysis requires no additional FINLY approval. Solve SHA-256(challenge_token + ":" + proof) so its first two bytes are zero.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 1Show 1 read-only tool
  • get_report_analysis_resultRetrieve the result or pending status using the exact operation capability received before upload.No findings

    Why it is in this group

    • The name "get_report_analysis_result" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve the result or pending status using the exact operation capability received before upload. Does not upload, analyze, call OCR, renew expiry or prove Customer identity. An expired or restarted service cannot recover the result.

    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 private-data or outbound.

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 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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:55 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 destructive, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://finly.co.il/mcp/reports: tools/list returned 4 tools to an anonymous client, including delete_report_analysis_result (destructive), analyze_balance_report (write), get_report_analysis_requirements (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "analyze_balance_report" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "analyze_balance_report" says "analyze": a word for reading.

    What this check looks for
  • The server marks "get_report_analysis_requirements" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_report_analysis_requirements" says "get": a word for reading.

    What this check looks for

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 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http report-analysis https://finly.co.il/mcp/reports
claude mcp add --transport http report-analysis https://finly.co.il/mcp/reports

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__report-analysis__get_report_analysis_result"
    ],
    "ask": [
      "mcp__report-analysis__analyze_balance_report",
      "mcp__report-analysis__get_report_analysis_requirements"
    ],
    "deny": [
      "mcp__report-analysis__delete_report_analysis_result"
    ]
  }
}

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 report-analysis. Review it before you use it.

Capability tags behind 1 rule
  • mcp__report-analysis__analyze_balance_report 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/il.co.finly/report-analysis/verify?hash=d6d9436ee3bdbd6c9b7715b21e35e429bca95bfc801df499e447df5382ab17ac" | jq -e '.changed == false'

Pinned hash d6d9436ee3bd, from Nov 15, 2026, 12:17 UTC.

Watch

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

https://radar.anlyon.com/servers/il.co.finly/report-analysis/changes.xml

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

Badge

Anlyon Radar badge for il.co.finly/report-analysis
[![Anlyon Radar](https://radar.anlyon.com/badge/il.co.finly/report-analysis.svg)](https://radar.anlyon.com/servers/il.co.finly/report-analysis)

Source: MCP Registry. Synced Oct 21, 2026, 18:13 UTC.

FINLY Balance Report Analysis MCP server: questions and answers

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

Is the FINLY Balance Report Analysis MCP server safe?

No scan can promise that. What its definitions show: 4 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 FINLY Balance Report Analysis MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: delete_report_analysis_result.

Can the FINLY Balance Report Analysis 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 FINLY Balance Report Analysis MCP server have?

4 tools: 1 destructive, 2 write, 1 read. delete_report_analysis_result, analyze_balance_report, get_report_analysis_requirements and get_report_analysis_result.

Does the FINLY Balance Report Analysis MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the FINLY Balance Report Analysis MCP server send data to outside services?

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

Has the FINLY Balance Report Analysis MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.