GitHub file batch
github_filesReads up to 10 GitHub repository files per call, returning content plus per-path success or error details so one missing file doesn't fail the batch.
Instructions
Batch file read: fetches up to 10 paths per call from one repository concurrently, one core call per uncached path, zero for cache hits, and reports per-item success and failure so one missing or malformed path never rejects the call. Returns {results[{path, ok, data{path, sha, size, encoding, content, binary, truncated}} or {path, ok, error{code, message}}], elapsed_ms, meta}.
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": {
"repo": "<repo>",
"paths": "<paths>"
},
"name": "github_files"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | Branch, tag, or commit; defaults to the repository default branch | |
| repo | Yes | Repository in owner/name form | |
| fresh | No | Bypass the local cache | |
| paths | Yes | File paths inside the repository; up to 10 per call |