# FeeFighter

> Audit junk fees, project annual costs and draft dispute letters. Free.

- name: io.github.everyai-com/fee-fighter
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 90/100 flags: duplicate-repo
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Ffee-fighter
- tools: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Ffee-fighter/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "fee-fighter": {
      "type": "http",
      "url": "https://fee-fighter.magicteams.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-97% +updated-16d-ago -duplicate-repo(15 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list carries no ttlMs, so clients re-fetch it

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,484 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 14 tool changes in 30 days
- fail `stability.rug_pull`: 8 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 1,484 tokens to load them all
- tool set hash: d2994882d5ebb65a04d9d209b56f52f0
- tools last changed: 2026-10-10T20:58:16.708Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.everyai-com/fee-fighter.svg)](https://protogrid.dev/servers/io.github.everyai-com/fee-fighter)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-10 `annual_cost` changed (description, inputSchema, outputSchema)
  - before: Project the cumulative cost of a fee list over 1-30 years by straight multiplication of each fee's annualized amount (no compounding or inflation; one-time fees are counted every year), with a per-fee breakdown. Use for 'what will these cost me over N years'. It does not flag fees: use audit_fees to find problem charges, benchmark_fees for typical ranges.
  - after: Project the cumulative cost of a fee list over 1-30 years by straight multiplication of each recurring fee's annualized amount, with one-time fees counted once (no compounding or inflation), with a per-fee breakdown. Use for 'what will these cost me over N years'. It does not flag fees: use audit_fees to find problem charges, benchmark_fees for typical ranges.
- 2026-10-10 `audit_fees` changed (inputSchema, outputSchema)
- 2026-10-10 `dispute_letter` changed (description, inputSchema, outputSchema) **meaning changed**
  - before: Generate a dispute letter for a specific fee. Use when you have a clear case for a refund or reversal. Do NOT use when you need to analyze multiple fees; use audit_fees instead.
  - after: Draft (text only; nothing is sent) a firm, polite letter asking a company to reverse or refund one specific fee, with grounds, a 14-day written-response request, an escalation path and sending tips. Use once the user has picked a fee to contest. To find which fees are worth disputing first, use audit_fees.
- 2026-10-10 `benchmark_fees` changed (description, inputSchema, outputSchema) **meaning changed**
  - before: Retrieve typical US consumer fee ranges by category. Use when needing a quick reference for fee benchmarks. Avoid when auditing specific fee charges, use audit_fees instead.
  - after: Look up typical US consumer fee ranges (min/max per charge, USD) for one category such as bank_overdraft, or the full 14-category table when category is omitted. Use to answer 'is this fee normal?' questions. To check a user's own list of fees against these ranges, use audit_fees.
- 2026-10-10 `annual_cost` changed (description, inputSchema, outputSchema) **meaning changed**
  - before: Calculate the total cost of a fee list over a specified number of years. Use when projecting simple, non-compounded costs. Do not use when needing to analyze historical fee data; use audit_fees instead.
  - after: Project the cumulative cost of a fee list over 1-30 years by straight multiplication of each fee's annualized amount (no compounding or inflation; one-time fees are counted every year), with a per-fee breakdown. Use for 'what will these cost me over N years'. It does not flag fees: use audit_fees to find problem charges, benchmark_fees for typical ranges.
- 2026-10-10 `audit_fees` changed (description, inputSchema, outputSchema) **meaning changed**
  - before: Annualize and analyze a list of fees for anomalies. Use when needing to identify outliers and duplicates in fee structures. Avoid when needing to calculate annual costs only, use annual_cost instead.
  - after: Audit a list of fees: annualize each one (monthly x12), total the yearly cost and monthly average, and flag charges above the typical US range for their category, duplicate names and one-time fees of $30+ worth disputing. Use when the user lists fees to review. For a multi-year projection use annual_cost; for typical ranges alone use benchmark_fees.
- 2026-10-10 `dispute_letter` changed (outputSchema, annotations)
- 2026-10-10 `benchmark_fees` changed (outputSchema, annotations)
- 2026-10-10 `annual_cost` changed (outputSchema, annotations)
- 2026-10-10 `audit_fees` changed (outputSchema, annotations)

Full history: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Ffee-fighter/changes

## Remotes

- https://fee-fighter.magicteams.ai/mcp (streamable-http, auth none, reachable true, uptime30d 0.9672131)

## Packages

_none_

## Tools (4)

- `annual_cost`: Project the cumulative cost of a fee list over 1-30 years by straight multiplication of each recurring fee's annualized amount, with one-time fees counted once (no compounding or inflation), with a per-fee breakdown. Use for 'what will these cost me over N years'. It does not flag fees: use audit_fees to find problem charges, benchmark_fees for typical ranges.
- `audit_fees`: Audit a list of fees: annualize each one (monthly x12), total the yearly cost and monthly average, and flag charges above the typical US range for their category, duplicate names and one-time fees of $30+ worth disputing. Use when the user lists fees to review. For a multi-year projection use annual_cost; for typical ranges alone use benchmark_fees.
- `benchmark_fees`: Look up typical US consumer fee ranges (min/max per charge, USD) for one category such as bank_overdraft, or the full 14-category table when category is omitted. Use to answer 'is this fee normal?' questions. To check a user's own list of fees against these ranges, use audit_fees.
- `dispute_letter`: Draft (text only; nothing is sent) a firm, polite letter asking a company to reverse or refund one specific fee, with grounds, a 14-day written-response request, an escalation path and sending tips. Use once the user has picked a fee to contest. To find which fees are worth disputing first, use audit_fees.