An MCP server that measures MCP client behaviour and converts EBCDIC to ASCII, which nobody needs.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Encodes ASCII text to EBCDIC bytes, returned as hex digits. Code pages cp037 (default), cp500, cp273.
ASCII text to encode
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http ebcdic https://mcp.phreakocious.net/mcp
Encodes ASCII text to EBCDIC bytes, returned as hex digits. Code pages cp037 (default), cp500, cp273.
| Argument | Type | Description |
|---|---|---|
| text |
| string |
| ASCII text to encode |
| codepage | string |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "ASCII text to encode"
},
"codepage": {
"enum": [
"cp037",
"cp500",
"cp273"
],
"type": "string",
"default": "cp037"
}
}
}Decodes EBCDIC bytes, given as hex digits, to text. Code pages cp037 (default), cp500, cp273. Nobody needs this; it exists so that a call to it means something.
| Argument | Type | Description |
|---|---|---|
| hex* | string | EBCDIC bytes as hex digits |
| codepage | string |
{
"type": "object",
"required": [
"hex"
],
"properties": {
"hex": {
"type": "string",
"description": "EBCDIC bytes as hex digits"
},
"codepage": {
"enum": [
"cp037",
"cp500",
"cp273"
],
"type": "string",
"default": "cp037"
}
}
}Returns the text you send. Exists to measure MCP client behaviour; this server records who connects.
| Argument | Type | Description |
|---|---|---|
| text* | string | Text to echo back |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Text to echo back"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 1, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.