Read files by glob
read_filesUse this when the exact file list is not already known and the user wants the contents of every file matching one glob under a directory. Use start_search instead to find filenames or text matches without reading every matched file. If exact paths are already known, use read_multiple_files; for one known path use read_file.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"device": "<device>"
},
"name": "read_files"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Absolute directory (or single file) to start from. | |
| device | Yes | ReMCP device id returned by list_devices. Required for every device operation. | |
| pattern | No | Glob matched against the relative path and the file name, such as "src/**/*.ts" or "*.md". Default **/* . | |
| max_files | No | Stop after this many files. Default 100, maximum 500. | |
| include_ignored | No | Also descend into .git and node_modules. Default false. | |
| max_lines_per_file | No | Lines kept per file. Default 2000. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | Optional structured result data for follow-up reasoning and tool calls. | |
| text | Yes | Concise human-readable result of the tool call. |