How do I let an AI agent slack conversations history?

Connect Slack to CybrLink, then expose the `slack_conversations_history` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Slack credential server-side and runs one scoped API call. Fetch recent messages from a Slack channel. Returns { messages: [{ type, user, text, ts, thread_ts }], has_more, next_cursor }.

Does the AI model see my Slack credentials when using SLACK_CONVERSATIONS_HISTORY?

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 Slack without the OAuth token or API key ever entering its context.

Slack · Messaging

`SLACK_CONVERSATIONS_HISTORY`

Fetch recent messages from a Slack channel. Returns { messages: [{ type, user, text, ts, thread_ts }], has_more, next_cursor }.

Provider: Slack
Access: Read
Category: Messaging
Version: v1

Input schema

{
  "type": "object",
  "properties": {
    "channel": {
      "type": "string",
      "description": "Channel ID (e.g. C0123ABC)."
    },
    "limit": {
      "type": "number",
      "description": "Max messages (default 20, max 100)."
    },
    "cursor": {
      "type": "string",
      "description": "Pagination cursor from a prior response_metadata."
    }
  },
  "required": [
    "channel"
  ],
  "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 slack_conversations_history with arguments matching the schema above.

CybrLink validates the input, injects the connected Slack 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 slack conversations history?: Connect Slack to CybrLink, then expose the `slack_conversations_history` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Slack credential server-side and runs one scoped API call. Fetch recent messages from a Slack channel. Returns { messages: [{ type, user, text, ts, thread_ts }], has_more, next_cursor }.
Does the AI model see my Slack credentials when using SLACK_CONVERSATIONS_HISTORY?: 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 Slack without the OAuth token or API key ever entering its context.

Connect Slack All tools