FeeFighter
REMOTE · FEE-FIGHTER.MAGICTEAMS.AI
Audit junk fees, project annual costs and draft dispute letters. Free.
Available components
Last scanned (17 hours ago)
Scores higher than 74% of remote servers
Reachable. Last reached 23 Oct 2026.
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 771 tokens (~192/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management48
- Stability check failed: schema churn in the 19 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 41 to 44.
- 20 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 34 to 38.
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 28 to 31.
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 18 to 21.
- 13 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 11 to 14.
- 12 Oct 26 +1
- Tool “annual_cost” rewrote its description, which is the text the model reads security
- 10 Oct 26 −1
- Stability: 0.07 → fail ▼ security
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “annual_cost” rewrote its description, which is the text the model reads security
- Tool “audit_fees” rewrote its description, which is the text the model reads security
- Tool “benchmark_fees” rewrote its description, which is the text the model reads security
- Tool “dispute_letter” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- “annual_cost” changed the type of “years”: number → integer ▼ functional
- Tool coverage: 92% → 100% ▲ functional
- First check of Tool coverage: 100 functional
- Schema quality: good → excellent functional
- “annual_cost” reworded the description of “fees” cosmetic
- “annual_cost” reworded the description of “years” cosmetic
- “audit_fees” reworded the description of “fees” cosmetic
- “benchmark_fees” reworded the description of “category” cosmetic
- “dispute_letter” reworded the description of “account_reference” cosmetic
- “dispute_letter” reworded the description of “amount” cosmetic
- “dispute_letter” reworded the description of “company” cosmetic
- “dispute_letter” reworded the description of “date_charged” cosmetic
- “dispute_letter” reworded the description of “fee_name” cosmetic
- “dispute_letter” reworded the description of “reason” cosmetic
- “dispute_letter” reworded the description of “requested_action” cosmetic
- “dispute_letter” reworded the description of “your_name” cosmetic
- 6 Oct 26 +1
- Stability: unverified → 0.07 ▲ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 23 Oct 2026 · Probed https://fee-fighter.magicteams.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=magicteams.ai | CN=WE1,O=Google Trust Services,C=US | 4 Oct 2026 | 2 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 6b121b5470767cdc13e75d84fb32831c |
| SANs: magicteams.ai, fee-fighter.magicteams.ai, *.fee-fighter.magicteams.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of fee-fighter.magicteams.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| magicteams.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://fee-fighter.magicteams.ai/mcp | Verified | 200 | |
| http (plaintext) | http://fee-fighter.magicteams.ai/mcp | HTTPS enforced | 301 | https://fee-fighter.magicteams.ai/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
annual_cost Annual cost ~143
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.
| Name | Type | Req | Description |
|---|---|---|---|
| fees | array | yes | Non-empty list of fees to project, each {name, amount, frequency, category?}; category is accepted but not used here |
| years | integer | – | Number of years to project, integer 1-30; default 1 |
| Name | Type | Req | Description |
|---|---|---|---|
| cumulative_total | number | yes | Sum of all per-fee cumulative amounts, USD |
| note | string | yes | Method note: recurring fees multiplied by years, one-time fees counted once, no compounding |
| per_fee | array | yes | Per-fee projection, in input order |
| years | integer | yes | Number of years projected (1-30) |
No examples provided.
audit_fees Audit fees ~110
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.
| Name | Type | Req | Description |
|---|---|---|---|
| fees | array | yes | Non-empty list of fees to audit, each {name, amount, frequency, category?} |
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | yes | Currency of all amounts; always USD |
| fees | array | yes | One audited row per input fee, in input order |
| flagged_count | integer | yes | Number of fees with at least one flag |
| note | string | yes | Plain-language summary of the audit result; lists any unknown category keys that were ignored |
| total_annual | number | yes | Sum of all annualized fees, USD |
| total_monthly_average | number | yes | total_annual divided by 12, USD |
No examples provided.
benchmark_fees Benchmark fees ~178
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.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Category key (case-insensitive; spaces/hyphens become underscores), one of: bank_overdraft, bank_monthly_maintenance, atm_out_of_network, late_payment, gym_membership_monthly, streaming_monthly, airl… |
| Name | Type | Req | Description |
|---|---|---|---|
| basis | string | – | Basis label for the range (typical US range - verify current pricing) |
| categories | array | – | Every benchmark row (full-table response only) |
| category | string | – | Benchmark category key, e.g. bank_overdraft |
| count | integer | – | Number of categories (full-table response only) |
| currency | string | yes | Currency of all ranges; always USD |
| disclaimer | string | yes | Informational-only disclaimer |
| label | string | – | Human-readable fee label, e.g. 'Out-of-network ATM fee' |
| source_note | string | yes | Where the ranges come from and how to read them |
| typical_max | number | – | High end of the typical US range per charge, USD |
| typical_min | number | – | Low end of the typical US range per charge, USD |
No examples provided.
dispute_letter Dispute letter ~277
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.
| Name | Type | Req | Description |
|---|---|---|---|
| account_reference | string | – | Optional account or reference number; prefer a masked form like '****1234' |
| amount | number | yes | Fee amount in USD, greater than 0, e.g. 38 |
| company | string | yes | Company or bank that charged the fee, e.g. 'First National Bank' |
| date_charged | string | – | Optional date the fee was charged, free text, e.g. 2026-09-14 |
| fee_name | string | yes | Name of the fee being disputed, e.g. 'Overdraft fee' |
| reason | string | – | Optional grounds for the dispute; default cites an undisclosed/unexpected charge and asks for a courtesy reversal |
| requested_action | string | – | What to ask the company to do, e.g. 'waive' or 'refund'; default 'reverse or refund' |
| your_name | string | yes | Account holder's full name, used in From and to sign the letter |
| Name | Type | Req | Description |
|---|---|---|---|
| disclaimer | string | yes | Not legal or financial advice disclaimer |
| letter | string | yes | Full letter text with To/From/Subject header and signature |
| sending_tips | array | yes | Practical tips for sending, following up and escalating |
| subject | string | yes | Subject line, e.g. Request to reverse or refund the $38.00 fee |
No examples provided.
How do I install the FeeFighter MCP server?
FeeFighter is a hosted endpoint at https://fee-fighter.magicteams.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · fee-fighter.magicteams.ai
claude mcp add --transport http everyai-com-fee-fighter 'https://fee-fighter.magicteams.ai/mcp'
What is the FeeFighter MCP server?
FeeFighter is an MCP server listed in the public MCP registry as io.github.everyai-com/fee-fighter. Audit junk fees, project annual costs and draft dispute letters. Free. This page covers its hosted endpoint (https://fee-fighter.magicteams.ai/mcp).
Is the FeeFighter MCP server safe to use?
FeeFighter scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the FeeFighter MCP server expose?
FeeFighter exposes 4 tools: audit_fees, annual_cost, benchmark_fees, dispute_letter. Their descriptions and schemas cost roughly 708 tokens of context every time the server is loaded.
Does the FeeFighter MCP server require authentication?
No. We connected to FeeFighter without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the FeeFighter MCP server still maintained?
FeeFighter is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.