# io.github.varsansri/fxabsolute (npm · fxabsolute-mcp)

Five years of 1-minute forex, index and crypto candles, plus a live bridge to a trader's chart.

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `fxabsolute-mcp`: 79/100 (this document), [markdown](https://verifymcp.io/servers/varsansri-fxabsolute/fxabsolute-mcp.md), [page](https://verifymcp.io/servers/varsansri-fxabsolute/fxabsolute-mcp)

## Channel facts

- Registry: `npm`
- Package: `fxabsolute-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-09-20.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 104 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 22 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 79/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1130 tokens (~113/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 77/100
  - Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 75% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "fxa_reply" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 10 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 io.github.varsansri/fxabsolute MCP server?

io.github.varsansri/fxabsolute runs locally as an npm package, launched with npx -y fxabsolute-mcp. 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 varsansri-fxabsolute -- npx -y fxabsolute-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "varsansri-fxabsolute": {
      "command": "npx",
      "args": [
        "-y",
        "fxabsolute-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "varsansri-fxabsolute": {
      "command": "npx",
      "args": [
        "-y",
        "fxabsolute-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add varsansri-fxabsolute -- npx -y fxabsolute-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "varsansri-fxabsolute": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "fxabsolute-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add varsansri-fxabsolute --command npx --arg -y --arg fxabsolute-mcp
```

### Hermes

```yaml
mcp_servers:
  varsansri-fxabsolute:
    command: "npx"
    args: ["-y", "fxabsolute-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "varsansri-fxabsolute": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "fxabsolute-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add varsansri-fxabsolute -t stdio -c npx -a -y fxabsolute-mcp
```

### Other

```json
{
  "mcpServers": {
    "varsansri-fxabsolute": {
      "command": "npx",
      "args": [
        "-y",
        "fxabsolute-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-09-19 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-04 (score 72, +4)

- [functional improvement] Stability: unverified → 0.23

## MCP tools (10)

### `fxa_instruments` (~53 tokens)

List every instrument FXAbsolute has candle data for, with bar counts and pip size. Call this first if you are unsure what is available. Also states plainly which fields exist — notably, this dataset has no volume.

### `fxa_candles` (~164 tokens)

Fetch OHLC candles for an instrument over a date range, at any timeframe from M1 to W1. Higher timeframes are aggregated from M1 on true clock boundaries. Returns the most recent bars when the range exceeds the limit.

Input parameters:

- `from` (string): ISO date YYYY-MM-DD (inclusive)
- `instrument` (string, required): e.g. EURUSD, XAUUSD, SPX500, BTCUSD
- `limit` (number): Max bars to return, capped at 1000. Default 200.
- `timeframe` (string): M1, M5, M15, M30, H1, H4, D1, W1. Default M5.
- `to` (string): ISO date YYYY-MM-DD (exclusive)

### `fxa_session_scan` (~291 tokens)

Pull specific bars out of a trading session across a whole date range, and summarise them. Example: the first 5-minute candle of the New York session every day for six months (instrument SPX500, session nyse, timeframe M5, bars [1]). Session windows are evaluated in exchange-local time with daylight saving handled, so results do not shift by an hour in summer. Use this instead of pulling raw candles and filtering them yourself.

Input parameters:

- `bars` (array): Which bars of the session to take, 1-based (1 = the opening bar). Use ["all"] for every bar in the session. Default [1].
- `daysOfWeek` (array): Optional filter, e.g. ["Monday","Friday"] or [1,5].
- `from` (string): ISO date YYYY-MM-DD
- `includeRows` (number): How many individual rows to return alongside the summary. Default 50.
- `instrument` (string, required)
- `session` (string): One of: sydney, tokyo, london, newyork, nyse, overlap. "nyse" is the 09:30–16:00 New York cash session; "newyork" is the wider 08:00–17:00 FX session.
- `timeframe` (string): Default M5.
- `to` (string): ISO date YYYY-MM-DD

### `fxa_bucket_stats` (~133 tokens)

Group every bar in a window by hour of day, day of week, month or year, and report how much each bucket moves. Answers "which hour is actually worth trading" and "is Monday different" in one call. Ranked by average bar range, since volume is not available.

Input parameters:

- `from` (string)
- `groupBy` (string): Default hour.
- `instrument` (string, required)
- `timeframe` (string): Default H1.
- `timezone` (string): IANA zone for the buckets, e.g. America/New_York. Default UTC.
- `to` (string)

### `fxa_level_touches` (~146 tokens)

Test whether a price level actually held. Finds every time price reached the level, de-duplicates clustered touches, and measures the reaction that followed. This is the numeric version of asking whether a horizontal line on the chart is respected.

Input parameters:

- `from` (string)
- `includeRows` (number): Default 40.
- `instrument` (string, required)
- `price` (number, required): The level to test.
- `separationBars` (number): Minimum bars between distinct touches. Default 4.
- `timeframe` (string): Default M15.
- `to` (string)
- `tolerancePips` (number): How close counts as a touch. Default 5.

### `fxa_connect_chart` (~118 tokens)

Pair with a trader's open FXAbsolute chart using the code shown in the AI tab of the backtester. Once connected, the trader can type or speak to you and you answer in their chart panel. Call this when the user gives you a pairing code, e.g. "connect to fxabsolute with code AB3K9P".

Input parameters:

- `agentName` (string): How to identify yourself in the trader's panel, e.g. "Claude Code".
- `code` (string, required): The 6-character pairing code from the chart.

### `fxa_wait_for_message` (~102 tokens)

Wait for the trader's next message on the paired chart. Blocks until they send something or the timeout expires. Returns their text plus a structured snapshot of the chart at the moment they asked — read that instead of asking them to describe what they are looking at. Returns waiting:false when nothing arrived, in which case call it again to keep listening.

Input parameters:

- `timeoutSec` (number): How long to wait, 5–600 seconds. Default 240.

### `fxa_reply` (~55 tokens)

Send your answer back to the trader's chart panel. Keep it short and concrete — it renders in a narrow side panel next to the chart, not a terminal.

Input parameters:

- `text` (string, required): The message to show the trader.

### `fxa_set_thinking` (~52 tokens)

Show or hide the thinking indicator in the trader's panel. Call with on:true before a long lookup so they know you are working. fxa_reply clears it automatically.

Input parameters:

- `on` (boolean, required)

### `fxa_disconnect_chart` (~16 tokens)

Leave the paired chart session.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/varsansri-fxabsolute/fxabsolute-mcp#diagnostics

## Score history

- 2026-09-20: 79
- 2026-09-19: 79
- 2026-09-18: 78
- 2026-09-17: 78
- 2026-09-16: 77
- 2026-09-15: 77
- 2026-09-14: 76
- 2026-09-13: 76
- 2026-09-12: 75
- 2026-09-11: 75
- 2026-09-10: 75
- 2026-09-09: 74
- 2026-09-08: 74
- 2026-09-07: 73
- 2026-09-06: 73
- 2026-09-05: 72
- 2026-09-04: 72
- 2026-09-03: 68
- 2026-09-02: 68
- 2026-09-01: 68
- 2026-08-31: 68
- 2026-08-30: 68
- 2026-08-29: 68
- 2026-08-28: 68

## Common questions

### What is the io.github.varsansri/fxabsolute MCP server?

io.github.varsansri/fxabsolute is an MCP server listed in the public MCP registry as io.github.varsansri/fxabsolute. Five years of 1-minute forex, index and crypto candles, plus a live bridge to a trader's chart. This page covers its npm package (fxabsolute-mcp).

### Is the io.github.varsansri/fxabsolute MCP server safe to use?

io.github.varsansri/fxabsolute scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 io.github.varsansri/fxabsolute MCP server expose?

io.github.varsansri/fxabsolute exposes 10 tools: fxa_instruments, fxa_candles, fxa_session_scan, fxa_bucket_stats, fxa_level_touches, and 5 more. Their descriptions and schemas cost roughly 1,130 tokens of context every time the server is loaded.

### Is the io.github.varsansri/fxabsolute MCP server still maintained?

io.github.varsansri/fxabsolute is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.varsansri/fxabsolute MCP server under?

io.github.varsansri/fxabsolute declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/fxabsolute-mcp
- Socket report: https://socket.dev/npm/package/fxabsolute-mcp
- Repository: https://github.com/varsansri/fxabsolute-mcp
- Website: https://www.fxabsolute.com/connect-your-agent
- Changelog RSS feed: https://verifymcp.io/servers/varsansri-fxabsolute/fxabsolute-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/varsansri-fxabsolute/fxabsolute-mcp.json
- HTML version of this page: https://verifymcp.io/servers/varsansri-fxabsolute/fxabsolute-mcp