# TDE (remote · app.tdehq.com)

Before you sign a trade deal: what it does to your cash month by month, and what to ask for instead.

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

> **Recent critical change**: Authorization (2026-10-27). See the changelog below before you install this server.

## Components

- remote · `app.tdehq.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/danha2048-tde/app.md), [page](https://verifymcp.io/servers/danha2048-tde/app)

## Channel facts

- Endpoint: `https://app.tdehq.com/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (update_saved_deal).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 53/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4375 tokens (~230/item across 19 items; 19 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 79/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 26% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the TDE MCP server?

TDE is a hosted endpoint at https://app.tdehq.com/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.

### Claude

```bash
claude mcp add --transport http danha2048-tde 'https://app.tdehq.com/mcp/'
```

### Cursor

```json
{
  "mcpServers": {
    "danha2048-tde": {
      "url": "https://app.tdehq.com/mcp/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "danha2048-tde": {
      "type": "http",
      "url": "https://app.tdehq.com/mcp/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.danha2048-tde]
url = "https://app.tdehq.com/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "danha2048-tde": {
      "type": "remote",
      "url": "https://app.tdehq.com/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add danha2048-tde --url 'https://app.tdehq.com/mcp/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  danha2048-tde:
    url: "https://app.tdehq.com/mcp/"
```

### Netclaw

```json
{
  "McpServers": {
    "danha2048-tde": {
      "Transport": "http",
      "Url": "https://app.tdehq.com/mcp/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add danha2048-tde -t streamable-http -u 'https://app.tdehq.com/mcp/'
```

### Other

```json
{
  "mcpServers": {
    "danha2048-tde": {
      "type": "http",
      "url": "https://app.tdehq.com/mcp/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “capabilities” rewrote its description, which is the text the model reads
- [security] Tool “cash_runway” rewrote its description, which is the text the model reads
- [security] Tool “compare_lanes” rewrote its description, which is the text the model reads
- [security] Tool “compare_quotes” rewrote its description, which is the text the model reads
- [security] Tool “duty_at_stake” rewrote its description, which is the text the model reads
- [security] Tool “landed_cost” rewrote its description, which is the text the model reads
- [security] Tool “plan_ledger” rewrote its description, which is the text the model reads
- [security] Tool “plan_products” rewrote its description, which is the text the model reads
- [security] Tool “quote_check” rewrote its description, which is the text the model reads
- [security] Tool “risk_register” rewrote its description, which is the text the model reads
- [security] Tool “test_order” rewrote its description, which is the text the model reads
- [security] Tool “test_saved_order” rewrote its description, which is the text the model reads
- [security] Tool “update_saved_deal” rewrote its description, which is the text the model reads
- [cosmetic] “compare_lanes” added an optional parameter “second_duty_rate_pct”

### 2026-11-03 (score 68, +1)

- [security] Tool “compare_lanes” rewrote its description, which is the text the model reads
- [security] Tool “compare_quotes” rewrote its description, which is the text the model reads

### 2026-11-01 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 64, −6)

- [critical regression] Authorization: partial → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] New tool “update_saved_deal”, which the server declares destructive
- [functional regression] Schema quality: 3751 → 4188
- [functional] New tool “test_saved_order”

### 2026-10-26 (score 70, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “cost_scenario” rewrote its description, which is the text the model reads
- [security] Tool “forecaster_backtest” rewrote its description, which is the text the model reads
- [security] Tool “lane_state” rewrote its description, which is the text the model reads
- [security] Tool “learned_inputs” rewrote its description, which is the text the model reads
- [security] Tool “margin_cushion” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 245 → 220
- [cosmetic] “cost_scenario” made “profile” optional
- [cosmetic] Tool “cost_scenario” changed its title: Cost scenario → Cost scenario (retired)
- [cosmetic] Tool “forecaster_backtest” changed its title: Forecaster backtest → Forecaster backtest (retired)
- [cosmetic] Tool “lane_state” changed its title: Lane state → Lane state (retired)
- [cosmetic] Tool “learned_inputs” changed its title: Learned inputs → Learned inputs (retired)
- [cosmetic] Tool “margin_cushion” changed its title: Margin cushion → Margin cushion (retired)

### 2026-10-25 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (19)

### `test_order` (~295 tokens)

Test an order

Whether the next order can be placed this month, and how large, checked
month by month against the caller's cash, budget and stock limits.

\`profile` is `{"business": {...}, "navigator": {...}}`. Needs
\`navigator.monthly_demand_units` (a monthly rate, not one order), `business.monthly_spend_gbp` (GBP/month),
\`business.cash_on_hand_gbp` and `business.monthly_revenue_gbp`; optional
\`navigator` keys include `navigator.unit_sell_price_gbp`,
\`supplier_deposit_pct`, `shipping_time_months` and `cash_floor_gbp`.
\`corridor_id` is the lane (default: live); `regime_state` overrides
the lane's state. Returns `first_order`, `status` (`feasible`,
\`best_achievable` with `compromises`, or `below_zero_no_floor`) and
\`minimum_relaxation`. `deal_terms` (where enabled) judges payment terms.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `corridor_id`
- `deal_terms`
- `profile` (object, required)
- `regime_state`

### `landed_cost` (~433 tokens)

Landed cost

CIF value, duty and import VAT, in GBP.

Send the goods value as `goods_gbp`, or as `goods` with `currency`; amounts
in another currency are converted at the Bank of England rate TDE holds,
stated under `fx_rate` with its date. Give `duty_rate_pct`, or a
\`commodity_code` and `origin` for goods entering the UK: the rate is then
read from the UK tariff and stated under `duty_lookup`. When more than one
code fits, `choose_code` lists them and no total is given. A rate that
cannot be found is asked for, never set to 0. For goods entering another
country, `duty_rate_pct` and `vat_rate_pct` are required.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `claim_preference`: True if the goods qualify for the origin's tariff preference.
- `commodity_code`: 10-digit UK commodity code, 6-digit HS code, or a product description.
- `currency`: ISO code of goods, freight and insurance: USD, GBP, CNY, INR, EUR, THB or MYR.
- `destination`: Country the goods enter. Default UK.
- `duty_rate_pct`: Duty rate, percent of CIF. Overrides any looked-up rate.
- `freight`: Freight in `currency`.
- `freight_gbp`: Freight in GBP.
- `goods`: Goods value in `currency`.
- `goods_gbp`: Goods value in GBP.
- `insurance`: Insurance amount in `currency`.
- `insurance_pct`: Insurance, percent of goods value.
- `origin`: Country the goods come from, e.g. China.
- `units`: Units, for per-unit figures.
- `vat_rate_pct`: Import VAT rate, percent. 20 for the UK when unset.

### `lane_state` (~105 tokens)

Lane state (retired)

Retired. This tool was retired on 20 Oct 2026, use test_order. TDE no longer reads a lane's
chokepoint transits or calls a route calm or strained. It answers that line until 19 Nov 2026 and is
then removed. `corridor_id` is accepted and ignored.

Retired: it serves no figure, so there is no provenance stamp to read. Information, not advice.

Input parameters:

- `corridor_id`

### `plan_ledger` (~175 tokens)

Plan ledger, month by month

Every pound the `test_order` plan moves, month by month.

Takes the same `profile`, `regime_state` and `corridor_id` as `test_order`
and builds the same plan without re-solving it, so cash lines and cost lines
agree with that plan. `months` is monthly, the grain the plan is solved at.
\`ledgered: false` with `missing` means no plan exists for this profile.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `corridor_id`
- `profile` (object, required)
- `regime_state`

### `plan_products` (~230 tokens)

Plan several products together

A joint plan for up to 30 products sharing one cash floor, monthly budget,
credit facility and supplier capacity.

\`profile["navigator"]["products"]` is the list of product rows (each with
\`id`, `label`, `monthly_demand_units`, `monthly_spend_gbp` and optional
\`unit_sell_price_gbp`, `starting_inventory_units`). Products are planned
together, not separately and summed. `which_product_lost` names which
product gave up units to hold a shared limit, and why;
\`would_have_been_feasible_separately` names products that pass alone but
not together. `regime_state` and `corridor_id` as in `test_order`.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `corridor_id`
- `profile` (object, required)
- `regime_state`

### `risk_register` (~214 tokens)

Risk register

What could go wrong on the caller's own figures, priced by stage: Source,
Terms, Order, Pay, Ship, Clear, Cash.

Takes the same inputs as `test_order` and prices against the same plan.
Each row has an `exposure` (the cost if it happens), `covers` (what would
cover it) and a `lever` (that cover's cost) where one is priced; otherwise
an `absence` naming the one figure that would unlock it. `not_priced` lists
exposures this register does not price (for example LC fees, demurrage and
quality claims).

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `corridor_id`
- `profile` (object, required)
- `regime_state`

### `cost_scenario` (~110 tokens)

Cost scenario (retired)

Retired. This tool was retired on 20 Oct 2026, use test_order. TDE no longer projects your
costs from past episodes or price indices. It answers that line until 19 Nov 2026 and is then
removed. `profile` and `horizon_months` are accepted and ignored.

Retired: it serves no figure, so there is no provenance stamp to read. Information, not advice.

Input parameters:

- `horizon_months`
- `profile`

### `cash_runway` (~248 tokens)

Cash runway

How long the caller's cash lasts if costs move as the lane's price
scenario says.

Needs cash on hand, revenue, margin and fixed costs in `profile.business`;
each one absent is named in `missing` (`projected: false`). Returns
\`runway_months_low`/`mid`/`high` and `worst_drawdown_gbp` over
\`horizon_months` (default 12); a runway longer than the horizon is `null`.
When the profile also plans an order, the plan's cash answer is added
(`source: "plan"`): `plan_first_break_month` and
\`plan_first_break_amount_gbp` (first month below the cash floor),
\`plan_first_below_zero_month`, `plan_lowest_cash_gbp`,
\`plan_horizon_months`.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `horizon_months`
- `profile` (object, required)

### `duty_at_stake` (~150 tokens)

Duty at stake

Duty on a year of the caller's goods at their stated rate, and what a
preference claim under the UK-India trade agreement could be worth.

COMPUTED from `profile` alone (spend, duty rate, preference status), with no
network call. Whether goods qualify depends on their code and the rules of
origin; the response names where to check.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `profile` (object, required)

### `quote_check` (~237 tokens)

Check a quote

Where a supplier's quote sits in the MEASURED customs-value band (HMRC
unit values, last twelve months) for one six-digit code and origin.

\`hs6` and `origin` (country) are required. `quote` is GBP per unit;
\`unit_mass_kg` converts it to GBP per kilogram, the band's unit. Only GBP
quotes are placed (`currency` unset or `"GBP"`). A customs unit value
averages many shipments, so `placement` says where the quote sits in the
band, not whether it is overpriced. `band.available: false` with
\`band.reason` when no band is measured for that code and origin.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `currency`
- `hs6` (string, required)
- `origin` (string, required)
- `quote`
- `unit_mass_kg`

### `compare_lanes` (~319 tokens)

Compare lanes

One of the caller's saved products bought from its own lane or from a
second lane, side by side: the first lane is the caller's own plan, the
second is that plan with only this product's quote, duty and lead time
changed. The plans are alternatives, never added up.

\`second_origin` names the second lane's origin; `product_id` picks the
product (default: the first in `navigator.products`).
\`second_quote_gbp_per_unit`, `second_lead_time_months` and
\`second_duty_rate_pct` (0 is a stated rate) describe the second lane.
A lane whose duty is neither stated nor in the UK tariff is never
planned at 0%: `available: false`, and `missing` names the duty rate.
Each lane carries its own `status`, `compromises`, `orders_units`,
\`cash_gbp`, `total_cost_gbp` and `duty_source`.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `corridor_id`
- `product_id`
- `profile` (object, required)
- `second_duty_rate_pct`
- `second_lead_time_months`
- `second_origin` (string, required)
- `second_quote_gbp_per_unit`

### `compare_quotes` (~278 tokens)

Compare quotes

One to five supplier quotes, each run as a whole-order plan against the
caller's `profile` (same engine as `test_order`) and ranked: feasible
first, then each plan's total over its months (end stock not credited),
then lead time. Each quote: `label`, `unit_price`; `currency` GBP, USD,
INR, CNY, EUR, THB, MYR (default GBP); optional `moq_units`,
\`lead_time_months`, `payment_terms_months`, `capacity_units_month`,
\`unit_mass_kg` and `lead_time_swing_months` (delivery swing, months)
replace the profile's figure for that quote (`inputs_used` says which).
Rows add `holding_cost_gbp` and `stock_left_at_end_gbp`. A currency with no
Bank of England rate is named in `missing`. `verdict`: up to three sentences.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `corridor_id`
- `profile` (object, required)
- `quotes` (array, required)
- `regime_state`

### `forecaster_backtest` (~101 tokens)

Forecaster backtest (retired)

Retired. This tool was retired on 20 Oct 2026, use test_order. TDE no longer forecasts, so
there is no forecaster backtest to read. This tool answers that line until 19 Nov 2026 and is then removed.
\`event_id` is accepted and ignored.

Retired: it serves no figure, so there is no provenance stamp to read. Information, not advice.

Input parameters:

- `event_id`

### `learned_inputs` (~96 tokens)

Learned inputs (retired)

Retired. This tool was retired on 20 Oct 2026, use test_order. No learned model touches a
figure, so there are no learned inputs to list. This tool answers that line until 19 Nov 2026 and is then removed.
\`profile` is accepted and ignored.

Retired: it serves no figure, so there is no provenance stamp to read. Information, not advice.

Input parameters:

- `profile`

### `margin_cushion` (~101 tokens)

Margin cushion (retired)

Retired. This tool was retired on 20 Oct 2026, use test_order. It answers that line until
19 Nov 2026 and is then removed. `profile`, `margin_pct` and `hs6` are accepted and ignored.

Retired: it serves no figure, so there is no provenance stamp to read. Information, not advice.

Input parameters:

- `hs6`
- `margin_pct`
- `profile`

### `veteran_notes` (~202 tokens)

Veteran notes

What usually goes wrong for these goods on this lane, and what to check
before committing: sourced practitioner notes.

\`hs6_codes` (six-digit codes) and `corridor_id` are optional; without them
only the notes that apply to any goods or any lane are returned.
\`lane_covered` and `chapter_specific` say whether anything more specific
than the general notes matched. `proposed` and `rejected` count the lines
a model proposed and the lines refused for promising a fixed timeframe.

Each line carries its citation: `source_url`, `source_title`, `reviewed` (the date a person checked it against that source), `synthesis` (a reading of several sources rather than one source's words) and `pdf`. A line with no source is not served, so `every_line_sourced` is true. Information, not advice.

Input parameters:

- `corridor_id`
- `hs6_codes`

### `capabilities` (~100 tokens)

What TDE serves

What this server answers: its endpoints, the lanes and whether each is
live, the provenance labels, and the payment presets and splits a profile
can use. Takes no input.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

### `test_saved_order` (~116 tokens)

Your saved order

Whether the order saved in the caller's TDE account can be placed this month, and how
large, checked month by month against their own cash, budget and stock limits. Needs the
caller to connect their TDE account; takes no figures.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

### `update_saved_deal` (~230 tokens)

Change your saved order

Changes figures in the deal saved in the caller's TDE account, then answers whether the
order can be placed. Each change is kept as a new version of the deal, the old values are
returned under `changed` so they can be put back, and nothing is overwritten. Every figure is checked; one the plan needs and the deal
lacks is refused by name, never filled in. Needs the caller to connect their TDE account and
to allow changes.

Figures carry a `provenance` (READ, MEASURED, DERIVED, COMPUTED, PROXY, ESTIMATED or GIVEN; defined in the server instructions) and a `basis`; `missing` names figures only the caller holds. Information, not advice.

Input parameters:

- `changes` (object, required): Figures to change, as {figure path: new value}, for example {"business.cash_on_hand_gbp": 90000, "navigator.shipping_time_months": 3}. Numbers are in the units TDE shows (GBP, percent, units, months)…

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/danha2048-tde/app#diagnostics

## Score history

- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 67
- 2026-11-01: 67
- 2026-10-31: 66
- 2026-10-30: 66
- 2026-10-29: 65
- 2026-10-28: 65
- 2026-10-27: 64
- 2026-10-26: 70
- 2026-10-25: 70
- 2026-10-24: 69
- 2026-10-23: 69
- 2026-10-22: 68
- 2026-10-21: 68
- 2026-10-20: 67

## Common questions

### What is the TDE MCP server?

TDE is an MCP server listed in the public MCP registry as io.github.danha2048/tde. Before you sign a trade deal: what it does to your cash month by month, and what to ask for instead. This page covers its hosted endpoint (https://app.tdehq.com/mcp/).

### Is the TDE MCP server safe to use?

TDE scores 68 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 TDE MCP server expose?

TDE exposes 19 tools: test_order, landed_cost, lane_state, plan_ledger, plan_products, and 14 more. Their descriptions and schemas cost roughly 3,740 tokens of context every time the server is loaded.

### Does the TDE MCP server require authentication?

No. We connected to TDE without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the TDE MCP server still maintained?

TDE is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://app.tdehq.com/mcp/
- Website: https://tdehq.com/
- Changelog RSS feed: https://verifymcp.io/servers/danha2048-tde/app.xml
- Changelog JSON feed: https://verifymcp.io/servers/danha2048-tde/app.json
- HTML version of this page: https://verifymcp.io/servers/danha2048-tde/app