How do I let an AI agent github list repos?

Connect Github to CybrLink, then expose the `github_list_repos` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Github credential server-side and runs one scoped API call. List repositories the connected GitHub token can access. Returns { repos: [{ id, name, full_name, private, html_url, description }] }.

Does the AI model see my Github credentials when using GITHUB_LIST_REPOS?

No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can read this data from Github without the OAuth token or API key ever entering its context.

Github · Developer

`GITHUB_LIST_REPOS`

List repositories the connected GitHub token can access. Returns { repos: [{ id, name, full_name, private, html_url, description }] }.

Provider: Github
Access: Read
Category: Developer
Version: v1

Input schema

{
  "type": "object",
  "properties": {
    "visibility": {
      "type": "string",
      "enum": [
        "all",
        "public",
        "private"
      ],
      "description": "Repo visibility filter (default all)."
    },
    "sort": {
      "type": "string",
      "enum": [
        "created",
        "updated",
        "pushed",
        "full_name"
      ],
      "description": "Sort order (default updated)."
    },
    "perPage": {
      "type": "number",
      "description": "Max repos to return (default 30, max 100)."
    },
    "page": {
      "type": "number",
      "description": "Page number to return (default 1)."
    }
  },
  "additionalProperties": false
}

How to call it

Expose this tool to any MCP-capable agent (Claude, GPT, or your own) through CybrLink's MCP server. The agent calls github_list_repos with arguments matching the schema above.

CybrLink validates the input, injects the connected Github credentials server-side, and runs a single scoped provider API call through the shared proxy — the same guarded path as the generic call_api tool. The raw secret never reaches the model, and the response is trimmed to just the fields the agent needs.

Frequently asked

How do I let an AI agent github list repos?: Connect Github to CybrLink, then expose the `github_list_repos` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Github credential server-side and runs one scoped API call. List repositories the connected GitHub token can access. Returns { repos: [{ id, name, full_name, private, html_url, description }] }.
Does the AI model see my Github credentials when using GITHUB_LIST_REPOS?: No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can read this data from Github without the OAuth token or API key ever entering its context.

Connect Github All tools