_ registry / mcp streamable-http · checked 22h ago

fee-fighter

https://fee-fighter.magicteams.ai

Registry code: 8a6cdbe94eb1dc6e

api record

FeeFighter audits junk fees from a list you provide: it annualizes and totals them, flags charges above typical US ranges, duplicate names and disputable one-time fees, benchmarks categories against typical US fee ranges, and drafts dispute letters. All maths and text only; nothing stored and nothing sent.

endpoint
https://fee-fighter.magicteams.ai/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
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
263ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts
0

distinct, expensive to fake

calls served
0

successful, last 30 days

_ what it can do 4 tools
1 open 3 never probed 1 of 4 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.

  • benchmark_fees open 22h ago

    Look up typical US consumer fee ranges by category (bank fees, subscriptions, airline charges, tickets and more). Omit category to return the whole reference table.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "category": {
          "type": "string",
          "description": "Category key to look up, e.g. bank_overdraft; omit for the full table"
        }
      }
    }
    arguments 9 lines
  • audit_fees unknown 22h ago

    Audit a list of fees: annualize each one, total the yearly cost and monthly average, and flag charges above typical US ranges, duplicate names and disputable one-time fees.

    mcp-tool

    {
      "type": "object",
      "required": [
        "fees"
      ],
      "properties": {
        "fees": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "name",
              "amount",
              "frequency"
            ],
            "properties": {
              "name": {
                "type": "string",
                "description": "Fee description, e.g. 'Overdraft fee'"
              },
              "amount": {
                "type": "number",
                "description": "Amount charged in USD"
              },
              "category": {
                "type": "string",
                "description": "Optional benchmark category key, e.g. bank_overdraft"
              },
              "frequency": {
                "enum": [
                  "monthly",
                  "annual",
                  "one-time"
                ],
                "type": "string",
                "description": "How often the fee recurs"
              }
            }
          },
          "description": "Fees to audit, each with name, amount, frequency and optional category"
        }
      }
    }
    arguments 43 lines
  • annual_cost unknown 22h ago

    Project the cumulative cost of a fee list over 1-30 years by straight multiplication (no compounding), with a per-fee breakdown. Defaults to 1 year.

    mcp-tool

    {
      "type": "object",
      "required": [
        "fees"
      ],
      "properties": {
        "fees": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "name",
              "amount",
              "frequency"
            ],
            "properties": {
              "name": {
                "type": "string"
              },
              "amount": {
                "type": "number"
              },
              "category": {
                "type": "string"
              },
              "frequency": {
                "enum": [
                  "monthly",
                  "annual",
                  "one-time"
                ],
                "type": "string"
              }
            }
          }
        },
        "years": {
          "type": "number",
          "description": "Years to project (integer 1-30), default 1"
        }
      }
    }
    arguments 42 lines
  • dispute_letter unknown never probed

    Draft a firm, polite letter requesting a reversal or refund of a specific fee, including grounds, a 14-day written response request and escalation paths. Produces text only; nothing is sent.

    mcp-tool

    {
      "type": "object",
      "required": [
        "fee_name",
        "amount",
        "company",
        "your_name"
      ],
      "properties": {
        "amount": {
          "type": "number",
          "description": "Fee amount in USD"
        },
        "reason": {
          "type": "string",
          "description": "Optional grounds for the dispute"
        },
        "company": {
          "type": "string",
          "description": "Company or bank that charged the fee"
        },
        "fee_name": {
          "type": "string",
          "description": "Name of the fee being disputed"
        },
        "your_name": {
          "type": "string",
          "description": "Your name, used to sign the letter"
        },
        "date_charged": {
          "type": "string",
          "description": "Optional date the fee was charged"
        },
        "requested_action": {
          "type": "string",
          "description": "What to ask for, e.g. 'reverse or refund' or 'waive'; default 'reverse or refund'"
        },
        "account_reference": {
          "type": "string",
          "description": "Optional account or reference number"
        }
      }
    }
    arguments 43 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 8a6cdbe94eb1dc6e.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/8a6cdbe94eb1dc6e/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/8a6cdbe94eb1dc6e/badge.svg)](https://brick.blue/agent/8a6cdbe94eb1dc6e?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
80%

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.

_ also on magicteams.ai 14 entries

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

6 more sit on this domain. All of them.