Skip to content

FiscaLLM MCP server

io.github.magna56/fiscallmmagna56streamable-httpv1.0.0Scanned

LLM prices, cost estimates and break-even, plus your app's AI cost and margin per user.

10 tools: 3 change things and 7 only read.

Tools: 0 delete, 0 irreversible, 3 write, 7 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 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.
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 FiscaLLM MCP server can do

The FiscaLLM MCP server is published by the GitHub account magna56. It has 10 tools. It can create or change data (3 tools: estimate_llm_cost, subscription_break_even and fiscallm_setup_guide), but cannot delete data. 7 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

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 11, 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.

10 tools

Changes things 3Claude Code: ask
  • estimate_llm_costUSD cost of a call to a model from its token counts, at list price, and the total for a number of such calls.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    USD cost of a call to a model from its token counts, at list price, and the total for a number of such calls.

    Annotations the server declares

    • title: Estimate the cost of LLM calls
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • fiscallm_setup_guideWhat FiscaLLM is and the ways to send it AI usage (OpenTelemetry, LiteLLM, SDK, HTTP), connect revenue, and read margins back.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    What FiscaLLM is and the ways to send it AI usage (OpenTelemetry, LiteLLM, SDK, HTTP), connect revenue, and read margins back.

    Annotations the server declares

    • title: How to set up FiscaLLM
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • subscription_break_evenHow many AI messages a month a subscriber can send before the model cost uses up what the plan earns, after the store or payment fee.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    How many AI messages a month a subscriber can send before the model cost uses up what the plan earns, after the store or payment fee. Answers: does this plan price cover this model?

    Annotations the server declares

    • title: Break-even usage for a subscription price
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 7Show 7 read-only tools
  • compare_llm_costsUSD cost of the same call (same token counts) on each of several models, cheapest first.No findings

    Why it is in this group

    • The name "compare_llm_costs" says "compare": a word for reading.
    Description, as the server wrote it
    USD cost of the same call (same token counts) on each of several models, cheapest first. Use it to pick a model or to price a switch.

    Annotations the server declares

    • title: Compare the cost of the same workload on several models
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_cost_breakdownThe app's AI cost over a period split by model and by feature.No findings

    Why it is in this group

    • The name "get_cost_breakdown" says "get": a word for reading.
    Description, as the server wrote it
    The app's AI cost over a period split by model and by feature. Needs the app's key.

    Annotations the server declares

    • title: AI cost by model and by feature
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_llm_priceCurrent list price of one model by id, e.g.No findings

    Why it is in this group

    • The name "get_llm_price" says "get": a word for reading.
    Description, as the server wrote it
    Current list price of one model by id, e.g. "gpt-4o-mini" or "claude-sonnet-4-5". Includes the long-context rate and any announced change.

    Annotations the server declares

    • title: Get one model's price
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_margin_overviewThe app's AI cost, revenue, margin, share of revenue spent on AI, request count and daily series over a period.No findings

    Why it is in this group

    • The name "get_margin_overview" says "get": a word for reading.
    Description, as the server wrote it
    The app's AI cost, revenue, margin, share of revenue spent on AI, request count and daily series over a period. Needs the app's key.

    Annotations the server declares

    • title: AI cost, revenue and margin of the app
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_plan_marginsAI cost, revenue and margin of each plan or product over a period.No findings

    Why it is in this group

    • The name "get_plan_margins" says "get": a word for reading.
    Description, as the server wrote it
    AI cost, revenue and margin of each plan or product over a period. Needs the app's key.

    Annotations the server declares

    • title: Margin per subscription plan
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_llm_pricesCurrent list prices (USD per 1M tokens: input, cached input, output) for OpenAI, Anthropic and Google models, with announced price changes.No findings

    Why it is in this group

    • The name "list_llm_prices" says "list": a word for reading.
    Description, as the server wrote it
    Current list prices (USD per 1M tokens: input, cached input, output) for OpenAI, Anthropic and Google models, with announced price changes. Use it to find a model id or to compare prices.

    Annotations the server declares

    • title: List LLM API prices
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_users_by_marginEach user's AI cost, revenue and margin over a period, the users losing the most money first.No findings

    Why it is in this group

    • The name "list_users_by_margin" says "list": a word for reading.
    Description, as the server wrote it
    Each user's AI cost, revenue and margin over a period, the users losing the most money first. Needs the app's key.

    Annotations the server declares

    • title: Users by margin, worst first
    • 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 untrusted-input or outbound.

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 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 18, 2026, 16:21 UTC, unchanged since Nov 11, 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.

    Matched text

    https://fiscallm.com/api/mcp: tools/list returned 10 tools to an anonymous client, including estimate_llm_cost (write), subscription_break_even (write), fiscallm_setup_guide (write)

    What this check looks for

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 fiscallm https://fiscallm.com/api/mcp
claude mcp add --transport http fiscallm https://fiscallm.com/api/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__fiscallm__list_llm_prices",
      "mcp__fiscallm__get_llm_price",
      "mcp__fiscallm__compare_llm_costs",
      "mcp__fiscallm__get_margin_overview",
      "mcp__fiscallm__list_users_by_margin",
      "mcp__fiscallm__get_plan_margins",
      "mcp__fiscallm__get_cost_breakdown"
    ],
    "ask": [
      "mcp__fiscallm__estimate_llm_cost",
      "mcp__fiscallm__subscription_break_even",
      "mcp__fiscallm__fiscallm_setup_guide"
    ],
    "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 fiscallm. Review it before you use it.

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.magna56/fiscallm/verify?hash=cce06c5a026c71ca2cb8e6bb074d89599dcaa45dfd97e7c33dd1ab6fbac6ce10" | jq -e '.changed == false'

Pinned hash cce06c5a026c, from Nov 11, 2026, 01:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.magna56/fiscallm/changes.xml

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

Badge

Anlyon Radar badge for io.github.magna56/fiscallm
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.magna56/fiscallm.svg)](https://radar.anlyon.com/servers/io.github.magna56/fiscallm)

Source: MCP Registry · repository. Synced Nov 11, 2026, 01:18 UTC.

FiscaLLM MCP server: questions and answers

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

Is the FiscaLLM MCP server safe?

No scan can promise that. What its definitions show: 10 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 FiscaLLM MCP server delete data?

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

Can the FiscaLLM 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 FiscaLLM MCP server have?

10 tools: 3 write, 7 read. estimate_llm_cost, subscription_break_even, fiscallm_setup_guide, list_llm_prices, get_llm_price, compare_llm_costs, get_margin_overview, list_users_by_margin and 2 more.

Does the FiscaLLM MCP server need sign-in or OAuth?

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

Does the FiscaLLM MCP server send data to outside services?

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

Has the FiscaLLM MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.