# get_file_contents

Read a file (decoded) or list a directory in a repo, at an optional ref.

Agent View of the PolicyLayer registry record for `get_file_contents`. HTML page: https://policylayer.com/tools/io-github-abhishekkumar2021-github/get-file-contents

## Facts

- Tool: `get_file_contents`
- Server: GitHub (`@abhishekmcp/github`) — https://policylayer.com/tools/io-github-abhishekkumar2021-github.md
- Install: `npx -y @abhishekmcp/github`
- Homepage: https://github.com/Abhishekkumar2021/mcp-suite
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 4 (3 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `ref` | string | no | Branch, tag, or commit SHA |
| `path` | string | yes |  |
| `repo` | string | yes | Repository name |
| `owner` | string | yes | Repository owner (user or org) |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_file_contents",
    "arguments": {
      "path": "<path>",
      "repo": "<repo>",
      "owner": "<owner>"
    }
  }
}
```

## Why get_file_contents is rated Low

This tool only retrieves and displays file contents or directory listings from a GitHub repository. It performs no creation, modification, deletion, code execution, or financial operations.

From the tool's own definition: "Tool name is 'get_file_contents' and description states 'Read a file (decoded) or list a directory in a repo'. The verb 'Read' and the action of retrieving file contents without modification clearly indicate a data retrieval operation with no side effects."

Risk signals: Accepts file system path (path)

## Use case

AI agents call get_file_contents to retrieve information from GitHub without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches GitHub:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_file_contents": {}
  }
}
```

## Other tools on GitHub (15)

- `github_logout` — Destructive — https://policylayer.com/tools/io-github-abhishekkumar2021-github/github-logout.md
- `github_login` — Other — https://policylayer.com/tools/io-github-abhishekkumar2021-github/github-login.md
- `get_issue` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/get-issue.md
- `get_pull_request` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/get-pull-request.md
- `get_repo` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/get-repo.md
- `list_issues` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/list-issues.md
- `list_notifications` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/list-notifications.md
- `list_pull_requests` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/list-pull-requests.md
- `rate_limit` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/rate-limit.md
- `search_code` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/search-code.md
- `search_issues` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/search-issues.md
- `search_repos` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/search-repos.md
- `whoami` — Read — https://policylayer.com/tools/io-github-abhishekkumar2021-github/whoami.md
- `add_issue_comment` — Write — https://policylayer.com/tools/io-github-abhishekkumar2021-github/add-issue-comment.md
- `create_issue` — Write — https://policylayer.com/tools/io-github-abhishekkumar2021-github/create-issue.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-abhishekkumar2021-github · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-abhishekkumar2021-github