_ registry / mcp streamable-http · checked 13h ago

fiscallm

https://fiscallm.com

Registry code: 891f97e4ecbe38a6

api record

FiscaLLM tracks what each user of an AI product costs in model calls, next to the revenue from that user. Price and estimate tools need no key and use list prices checked against the providers' pricing pages. Margin tools read one app's data and need its key (starts with fsk_) in the Authorization header: Bearer <key>. Call fiscallm_setup_guide to learn how to start sending usage.

endpoint
https://fiscallm.com/api/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is fiscallm live?
Yes — it answered the hub's last check (checked 13h ago). It answered 100% of checks over the last 30 days.
Is fiscallm free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does fiscallm have?
10 tools: estimate_llm_cost, subscription_break_even, fiscallm_setup_guide, get_margin_overview, list_llm_prices, get_llm_price, compare_llm_costs, list_users_by_margin, ….
Is fiscallm safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
250ms

last good check

priced tools
0

of 10 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 10 tools
10 auth-required 10 of 10 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • estimate_llm_cost auth-required never probed

    USD cost of a call to a model from its token counts, at list price, and the total for a number of such calls.

    mcp-tool

    {
  "type": "object",
  "required": [
    "model",
    "inputTokens",
    "outputTokens"
  ],
  "properties": {
    "calls": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Number of calls like this one."
    },
    "model": {
      "type": "string",
      "description": "Model id."
    },
    "inputTokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Prompt tokens per call, including any cached ones."
    },
    "cachedTokens": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "How many of the prompt tokens are read from the prompt cache."
    },
    "outputTokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Reply tokens per call."
    },
    "cacheWriteTokens": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "Prompt tokens written to the cache (Anthropic)."
    }
  }
}
    arguments 42 lines
  • subscription_break_even auth-required never probed

    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?

    mcp-tool

    {
  "type": "object",
  "required": [
    "model",
    "monthlyPriceUsd"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id."
    },
    "feePercent": {
      "type": "number",
      "default": 15,
      "maximum": 100,
      "minimum": 0,
      "description": "Store or payment fee. App stores take 15 to 30; Stripe about 3."
    },
    "inputTokens": {
      "type": "integer",
      "default": 1500,
      "minimum": 0,
      "description": "Prompt tokens per message (system prompt and history)."
    },
    "cachedTokens": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "How many of the prompt tokens are read from the prompt cache."
    },
    "outputTokens": {
      "type": "integer",
      "default": 400,
      "minimum": 0,
      "description": "Reply tokens per message."
    },
    "monthlyPriceUsd": {
      "type": "number",
      "description": "The plan's price per month.",
      "exclusiveMinimum": 0
    },
    "messagesPerMonth": {
      "type": "integer",
      "minimum": 0,
      "description": "Optional: a user's expected messages a month, to get that user's margin."
    }
  }
}
    arguments 48 lines
  • fiscallm_setup_guide auth-required never probed

    What FiscaLLM is and the ways to send it AI usage (OpenTelemetry, LiteLLM, SDK, HTTP), connect revenue, and read margins back.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • get_margin_overview auth-required 13h ago

    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.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "default": 30,
      "maximum": 365,
      "minimum": 1,
      "description": "How many days back to look, counting today."
    }
  }
}
    arguments 12 lines
  • list_llm_prices auth-required never probed

    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.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "search": {
      "type": "string",
      "description": "Only models whose id contains this text, e.g. \"haiku\" or \"gpt-5\"."
    },
    "provider": {
      "enum": [
        "openai",
        "anthropic",
        "google"
      ],
      "type": "string",
      "description": "Only this provider's models."
    }
  }
}
    arguments 18 lines
  • get_llm_price auth-required never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id."
    }
  }
}
    arguments 12 lines
  • compare_llm_costs auth-required never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "models",
    "inputTokens",
    "outputTokens"
  ],
  "properties": {
    "calls": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "description": "Number of calls like this one, e.g. per user per month."
    },
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 20,
      "minItems": 2,
      "description": "Model ids to compare."
    },
    "inputTokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Prompt tokens per call, including any cached ones."
    },
    "cachedTokens": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "How many of the prompt tokens are read from the prompt cache."
    },
    "outputTokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Reply tokens per call."
    }
  }
}
    arguments 41 lines
  • list_users_by_margin auth-required never probed

    Each user's AI cost, revenue and margin over a period, the users losing the most money first. Needs the app's key.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "default": 30,
      "maximum": 365,
      "minimum": 1,
      "description": "How many days back to look, counting today."
    },
    "limit": {
      "type": "integer",
      "default": 25,
      "maximum": 500,
      "minimum": 1
    },
    "losingOnly": {
      "type": "boolean",
      "default": false,
      "description": "Only users whose AI cost is above their revenue."
    }
  }
}
    arguments 23 lines
  • get_cost_breakdown auth-required 13h ago

    The app's AI cost over a period split by model and by feature. Needs the app's key.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "default": 30,
      "maximum": 365,
      "minimum": 1,
      "description": "How many days back to look, counting today."
    }
  }
}
    arguments 12 lines
  • get_plan_margins auth-required 13h ago

    AI cost, revenue and margin of each plan or product over a period. Needs the app's key.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "default": 30,
      "maximum": 365,
      "minimum": 1,
      "description": "How many days back to look, counting today."
    }
  }
}
    arguments 12 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 891f97e4ecbe38a6.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/891f97e4ecbe38a6/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/891f97e4ecbe38a6/badge.svg)](https://brick.blue/agent/891f97e4ecbe38a6?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.