# create_gist

Create a new gist

Agent View of the PolicyLayer registry record for `create_gist`. HTML page: https://policylayer.com/tools/github/create-gist

## Facts

- Tool: `create_gist`
- Server: GitHub (`oci:ghcr.io/github/github-mcp-server:1.3.0`) — https://policylayer.com/tools/github.md
- Homepage: https://github.com/github/github-mcp-server
- Risk category: Write (Medium risk)
- Registry record: grade D, identity verified
- Server auth posture: gated
- Server rate-limited: no
- Parameters: 4
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `public` | boolean | no | Whether the gist is public |
| `content` | string | no | Content for simple single-file gist creation |
| `filename` | string | no | Filename for simple single-file gist creation |
| `description` | string | no | Description of the gist |

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": "create_gist",
    "arguments": {}
  }
}
```

## Why create_gist is rated Medium

Creating a gist is a reversible write operation that generates new content on GitHub. It has medium severity because gists can be public, potentially exposing the AI's generated content to the internet, and could be used to leak sensitive information or create spam/malicious content. However, it is not destructive (gists can be deleted), not financial, and not an arbitrary code execution.

From the tool's own definition: "Tool name is 'create_gist' and description states 'Create a new gist' — this creates new data in GitHub's gist service."

Risk signals: Accepts raw HTML/template content (content) · Accepts file system path (filename)

## Use case

AI agents use create_gist to create or update resources in GitHub, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub environment.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_gist": {
      "limits": [
        {
          "counter": "create_gist_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on GitHub (85)

- `delete_file` — Destructive — https://policylayer.com/tools/github/delete-file.md
- `projects_write` — Destructive — https://policylayer.com/tools/github/projects-write.md
- `actions_run_trigger` — Execute — https://policylayer.com/tools/github/actions-run-trigger.md
- `assign_copilot_to_issue` — Execute — https://policylayer.com/tools/github/assign-copilot-to-issue.md
- `actions_get` — Read — https://policylayer.com/tools/github/actions-get.md
- `actions_list` — Read — https://policylayer.com/tools/github/actions-list.md
- `get_code_scanning_alert` — Read — https://policylayer.com/tools/github/get-code-scanning-alert.md
- `get_commit` — Read — https://policylayer.com/tools/github/get-commit.md
- `get_copilot_job_status` — Read — https://policylayer.com/tools/github/get-copilot-job-status.md
- `get_copilot_space` — Read — https://policylayer.com/tools/github/get-copilot-space.md
- `get_dependabot_alert` — Read — https://policylayer.com/tools/github/get-dependabot-alert.md
- `get_discussion` — Read — https://policylayer.com/tools/github/get-discussion.md
- `get_discussion_comments` — Read — https://policylayer.com/tools/github/get-discussion-comments.md
- `get_file_contents` — Read — https://policylayer.com/tools/github/get-file-contents.md
- `get_gist` — Read — https://policylayer.com/tools/github/get-gist.md
- `get_global_security_advisory` — Read — https://policylayer.com/tools/github/get-global-security-advisory.md
- `get_job_logs` — Read — https://policylayer.com/tools/github/get-job-logs.md
- `get_label` — Read — https://policylayer.com/tools/github/get-label.md
- `get_latest_release` — Read — https://policylayer.com/tools/github/get-latest-release.md
- `get_me` — Read — https://policylayer.com/tools/github/get-me.md
- `get_notification_details` — Read — https://policylayer.com/tools/github/get-notification-details.md
- `get_release_by_tag` — Read — https://policylayer.com/tools/github/get-release-by-tag.md
- `get_repository_tree` — Read — https://policylayer.com/tools/github/get-repository-tree.md
- `get_secret_scanning_alert` — Read — https://policylayer.com/tools/github/get-secret-scanning-alert.md
- `get_tag` — Read — https://policylayer.com/tools/github/get-tag.md
- `get_team_members` — Read — https://policylayer.com/tools/github/get-team-members.md
- `get_teams` — Read — https://policylayer.com/tools/github/get-teams.md
- `github_support_docs_search` — Read — https://policylayer.com/tools/github/github-support-docs-search.md
- `issue_read` — Read — https://policylayer.com/tools/github/issue-read.md
- `list_branches` — Read — https://policylayer.com/tools/github/list-branches.md
- …and 55 more: https://policylayer.com/tools/github.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=github · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/github