# `io.github.SUNDRAM07/txwhy` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/io.github.SUNDRAM07/txwhy
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.SUNDRAM07/txwhy
- Version: 0.2.0 (active)
- Publisher: io.github.SUNDRAM07 (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T18:21:08.048Z

Title and description, as the publisher wrote them:

```untrusted-server-text
TxWhy
Failed Solana transaction in, working transaction out. Exact cause, rebuilt tx, verifiable repair.
```

Scanned 2026-11-16T20:18:12.437Z over streamable-http.

**3 tools: 2 change things and 1 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 2 | ask |
| Only reads | read | 1 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Changes things (2)

Creates or changes something that can be changed back. Claude Code: ask.

### `explain_error`

- The name "explain_error" says "explain": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.

Description, as the server wrote it:

```untrusted-server-text
Looks up what a custom program error code means for a given program, using 1,800+ named errors from major Solana programs plus the runtime's own errors. Use it when you only have a code such as 6001 or 0x1771 from a simulation or an RPC response.
```

### `repair_transaction`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Give it a Solana transaction that failed, or one you are about to send. It finds the cause and returns a rebuilt UNSIGNED transaction that has been simulated against live mainnet state to prove it passes. Fixes expired blockhashes, compute-unit limits, priority fees, loaded-data limits, slippage on plain Jupiter swaps (fresh quote, same tolerance), and slippage on direct Pump.fun, PumpSwap, Raydium AMM v4, Meteora DBC and Meteora DAMM v2 swaps (only the limit moves, never more than 25% against the user). Handles legacy, v0 and version 1 (SIMD-0385) transactions and durable nonces. When the failure cannot be fixed by rebuilding (not enough funds, a private program's own error), it says so and explains why instead of returning something that would fail again. Pass exactly one of `transaction` or `signature`. Sign the returned transaction with your own key and send it within about 60 seconds.
```

## Only reads (1)

Looks things up and changes nothing. Claude Code: allow.

### `diagnose_transaction`

- The description's first verb is "explain": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Explains why a transaction that landed on mainnet failed: the exact failing instruction in the call tree, the named error, its cause, and how to fix it. Read-only and fast. Use repair_transaction when you want a working transaction back.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `txwhy`:

```json
{
  "permissions": {
    "allow": [
      "mcp__txwhy__diagnose_transaction"
    ],
    "ask": [
      "mcp__txwhy__repair_transaction",
      "mcp__txwhy__explain_error"
    ],
    "deny": []
  }
}
```

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:00:22.216Z, unchanged since 2026-10-22T14:54:26.987Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `2` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

https://txwhy.vercel.app/api/mcp: tools/list returned 3 tools to an anonymous client, including repair_transaction (write), explain_error (write)
```
