firmfax

endpoint

https://firmfax.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 firmfax live?

Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.

Is firmfax free to use?

Yes — the hub reached it with no key and no payment.

What tools does firmfax have?

6 tools: find_firms, compare_firms, get_evidence, get_firm, list_firms, get_rule_changes.

Is firmfax 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.

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.

• list_firms reads open 6h ago

  Every firm slug and name. Carries no figures, so nothing here needs evidence.

  mcp-tool

  1234

  {
    "type": "object",
    "properties": {}
  }

  arguments 4 lines copy
• get_rule_changes reads open 6h ago

  The dated record of what changed, newest first. Every entry states its KIND, and most of this tape is FirmFax correcting its own data rather than a firm changing its rules. Read counts before describing industry activity: a total taken across kinds overstates it.

  mcp-tool

  1234567891011121314151617181920212223242526

  {
    "type": "object",
    "properties": {
      "kind": {
        "enum": [
          "firm",
          "record",
          "withdrawn"
        ],
        "type": "string",
        "description": "firm = the firm changed a rule. record = FirmFax corrected its own data. withdrawn = we published an entry and then retracted it."
      },
      "slug": {
        "type": "string",
        "description": "Limit to one firm. Omit for every firm."
      },
      "limit": {
        "type": "number",
        "description": "How many entries to return, newest first. Default 50."
      },
      "since": {
        "type": "string",
        "description": "ISO date, e.g. \"2026-08-01\". Entries dated on or after it."
      }
    }
  }

  arguments 26 lines copy
• find_firms reads unknown 6h ago

  Firms matching every criterion given. A firm whose record does not carry a criterion is never counted as a match and never silently dropped: it is returned separately under unknown, with the field that could not be tested. Absence is common here, so read counts before treating the matched list as the answer.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172

  {
    "type": "object",
    "properties": {
      "assetClass": {
        "enum": [
          "forex",
          "futures",
          "crypto"
        ],
        "type": "string",
        "description": "Firms recorded as offering this. 21 of 71 records name no asset class and are returned as unknown."
      },
      "maxResetFee": {
        "type": "number",
        "description": "Reset fee at or below this. 56 of 71 record no fee."
      },
      "maxActivationFee": {
        "type": "number",
        "description": "Activation fee at or below this. 42 of 71 record no fee."
      },
      "maxConsistencyPct": {
        "type": "number",
        "description": "Consistency rule at or below this. 28 of 71 record none."
      },
      "maxDailyLossLimit": {
        "type": "number",
        "description": "Daily loss limit at or below this, in the unit dailyLossLimitUnit names. 31 of 71 record none."
      },
      "maxMinTradingDays": {
        "type": "number",
        "description": "Minimum trading days at or below this, counted as minTradingDaysUnit names. 16 of 71 record none."
      },
      "dailyLossLimitUnit": {
        "enum": [
          "percent",
          "usd"
        ],
        "type": "string",
        "description": "The unit maxDailyLossLimit is in. Daily loss limits are recorded in percent at some firms and in dollars at others, and the two are never compared: a firm recorded in the other unit is returned under unknown with its unit named."
      },
      "maxMinDaysToPayout": {
        "type": "number",
        "description": "Minimum days to first payout at or below this, counted as minDaysToPayoutUnit names. 26 of 71 record none."
      },
      "minTradingDaysUnit": {
        "enum": [
          "calendar_days",
          "trading_days",
          "winning_days"
        ],
        "type": "string",
        "description": "What maxMinTradingDays counts: calendar_days, trading_days or winning_days. A minimum is compared only with minimums counted the same way; a firm counting another way, or stating no unit, is returned under unknown with what it counts named."
      },
      "minDaysToPayoutUnit": {
        "enum": [
          "calendar_days",
          "trading_days",
          "winning_days"
        ],
        "type": "string",
        "description": "What maxMinDaysToPayout counts: calendar_days, trading_days or winning_days. A wait is compared only with waits counted the same way; a firm counting another way, or stating no unit, is returned under unknown with what it counts named."
      },
      "minTradingDaysMinProfit": {
        "type": "number",
        "description": "With winning_days only: the profit a day must reach to count. A firm whose winning days carry a different profit bar is returned under unknown."
      },
      "minDaysToPayoutMinProfit": {
        "type": "number",
        "description": "With winning_days only: the profit a day must reach to count. A firm whose winning days carry a different profit bar is returned under unknown."
      }
    }
  }

  arguments 72 lines copy
• compare_firms reads unknown never probed

  Two firms side by side. Reports each figure with its evidence state and whether the pair is comparable at all: a field neither firm records is not a tie, and a field only one records is not a win. No per-field winner is declared, because the direction of "better" for several of these is a judgement the published scoring model already makes; each firm's grade is returned alongside so the verdict comes from that model rather than from this tool.

  mcp-tool

  1234567891011121314151617

  {
    "type": "object",
    "required": [
      "a",
      "b"
    ],
    "properties": {
      "a": {
        "type": "string",
        "description": "First firm slug."
      },
      "b": {
        "type": "string",
        "description": "Second firm slug."
      }
    }
  }

  arguments 17 lines copy
• get_evidence reads unknown 14h ago

  The stored reading behind a figure: the verbatim quote, the page it came from, and the date we read it. Answers "we hold none" explicitly rather than returning an empty list. `outcome` is load-bearing: a `contradicted`, `contradiction` or `absent` row records what we read, not a figure we publish. Use get_firm for the published figure.

  mcp-tool

  12345678910111213141516

  {
    "type": "object",
    "required": [
      "slug"
    ],
    "properties": {
      "slug": {
        "type": "string",
        "description": "The firm slug, e.g. \"topstep\"."
      },
      "field": {
        "type": "string",
        "description": "One field path, e.g. \"rules.dailyLossLimit\". Omit for every field we hold for this firm."
      }
    }
  }

  arguments 16 lines copy
• get_firm reads unknown 14h ago

  One prop trading firm. Every figure states whether we hold evidence for it, and a firm whose score range spans more than one band carries no letter grade at all.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "slug"
    ],
    "properties": {
      "slug": {
        "type": "string",
        "description": "The firm slug, e.g. \"topstep\"."
      }
    }
  }

  arguments 12 lines copy

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

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.