conversations_replies
Retrieve threaded message conversations from Slack channels using channel ID and thread timestamp, with pagination support for handling long discussions.
Instructions
Fetches all messages in a specific thread by channel and thread timestamp. Supports pagination.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| accessToken | Yes | Slack OAuth token (xoxp-... or xoxb-...) | |
| channel_id | Yes | Channel ID (e.g., C1234567890), channel name (#general), or DM (@username) | |
| thread_ts | Yes | Message timestamp in format 1234567890.123456 | |
| limit | No | Time range (1d, 7d, 1m, 90d) or message count (e.g., 100) | |
| cursor | No | Pagination cursor from previous response | |
| include_activity_messages | No | Include join/leave system messages (default: false) |
Implementation Reference
- src/tools.ts:185-228 (handler)The handler function that executes the conversations_replies tool. Validates input, resolves channel ID, calls Slack conversations.replies API, filters messages, and returns formatted response.export async function conversationsReplies(args: any): Promise<ToolResponse> { try { const validated = ConversationsRepliesSchema.parse(args); const client = new WebClient(validated.accessToken); console.log('Fetching thread replies for channel:', validated.channel_id, 'thread:', validated.thread_ts); // Resolve channel name/username to ID if needed const channelId = await resolveChannelId(client, validated.channel_id); // Parse limit parameter const limitParams = parseLimit(validated.limit); // Fetch thread replies const result = await client.conversations.replies({ channel: channelId, ts: validated.thread_ts, cursor: validated.cursor, ...limitParams }); // Filter out activity messages if not requested let messages = result.messages || []; if (!validated.include_activity_messages) { messages = messages.filter((msg: any) => !msg.subtype || !['channel_join', 'channel_leave'].includes(msg.subtype)); } return { success: true, data: { messages, has_more: result.has_more, cursor: result.response_metadata?.next_cursor, channel_id: channelId, thread_ts: validated.thread_ts } }; } catch (error: any) { if (error.name === 'ZodError') { return { success: false, error: `Validation error: ${error.errors.map((e: any) => e.message).join(', ')}` }; } return handleSlackError(error); } }
- src/schemas.ts:19-26 (schema)Zod schema defining the input parameters and validation for the conversations_replies tool.export const ConversationsRepliesSchema = z.object({ accessToken: z.string().describe("Slack OAuth token (xoxp-... or xoxb-...)"), channel_id: z.string().describe("Channel ID (e.g., C1234567890), channel name (#general), or DM (@username)"), thread_ts: z.string().describe("Message timestamp in format 1234567890.123456"), limit: z.union([z.string(), z.number()]).optional().describe("Time range (1d, 7d, 1m, 90d) or message count (e.g., 100)"), cursor: z.string().optional().describe("Pagination cursor from previous response"), include_activity_messages: z.boolean().optional().describe("Include join/leave system messages (default: false)") });
- src/index.ts:100-104 (registration)Registers the conversations_replies tool in the MCP server's tool list, providing name, description, and input schema.{ name: 'conversations_replies', description: 'Fetches all messages in a specific thread by channel and thread timestamp. Supports pagination.', inputSchema: zodToMCPSchema(ConversationsRepliesSchema) },
- src/index.ts:133-135 (registration)Dispatches execution of the conversations_replies tool in the server's callTool handler switch statement.case 'conversations_replies': result = await conversationsReplies(args); break;