Skip to main content
Glama

discourse_get_draft

Retrieve saved draft content from Discourse forums using specific keys like 'new_topic' for new topics or 'topic_' for replies. Access partially composed posts to continue editing where you left off.

Instructions

Retrieve a specific draft by its key. Common keys: "new_topic" for new topic drafts, "topic_" for reply drafts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
draft_keyYesDraft key (e.g., "new_topic", "topic_123", "new_private_message")
sequenceNoExpected sequence number (optional)

Implementation Reference

  • The handler function for the discourse_get_draft tool. It fetches the draft from the Discourse API using the provided draft_key and optional sequence, parses the JSON data, formats a markdown response with preview and full JSON, and handles errors.
    async (input: unknown, _extra: unknown) => { const { draft_key, sequence } = schema.parse(input); try { const { client } = ctx.siteState.ensureSelectedSite(); const params = new URLSearchParams(); if (typeof sequence === "number") params.set("sequence", String(sequence)); const url = `/drafts/${encodeURIComponent(draft_key)}.json${params.toString() ? `?${params}` : ""}`; const data = (await client.get(url)) as { draft?: string; draft_sequence?: number; }; if (!data?.draft) { return { content: [{ type: "text", text: `No draft found for key "${draft_key}".` }] }; } let parsedDraft: Record<string, unknown> = {}; try { parsedDraft = JSON.parse(data.draft); } catch { parsedDraft = { raw: data.draft }; } const lines = [`# Draft: \`${draft_key}\`\n`]; lines.push(`**Sequence:** ${data.draft_sequence ?? "unknown"}`); if (parsedDraft.title) lines.push(`**Title:** ${parsedDraft.title}`); if (parsedDraft.categoryId) lines.push(`**Category ID:** ${parsedDraft.categoryId}`); if (parsedDraft.tags && Array.isArray(parsedDraft.tags)) { lines.push(`**Tags:** ${(parsedDraft.tags as string[]).join(", ")}`); } if (parsedDraft.action) lines.push(`**Action:** ${parsedDraft.action}`); if (parsedDraft.reply) { lines.push(`\n**Content:**\n${parsedDraft.reply}`); } lines.push("\n```json"); lines.push( JSON.stringify( { draft_key, draft_sequence: data.draft_sequence, data: parsedDraft, }, null, 2 ) ); lines.push("```"); return { content: [{ type: "text", text: lines.join("\n") }] }; } catch (e: unknown) { const msg = e instanceof Error ? e.message : String(e); return { content: [{ type: "text", text: `Failed to get draft: ${msg}` }], isError: true }; } }
  • Zod input schema defining draft_key (required string) and optional sequence (number). Used for validation in the tool handler.
    const schema = z.object({ draft_key: z .string() .min(1) .max(40) .describe('Draft key (e.g., "new_topic", "topic_123", "new_private_message")'), sequence: z.number().int().min(0).optional().describe("Expected sequence number (optional)"), });
  • Registration of the discourse_get_draft tool using server.registerTool, including name, metadata (title, description, inputSchema), and handler function.
    server.registerTool( "discourse_get_draft", { title: "Get Draft", description: 'Retrieve a specific draft by its key. Common keys: "new_topic" for new topic drafts, "topic_<id>" for reply drafts.', inputSchema: schema.shape, }, async (input: unknown, _extra: unknown) => { const { draft_key, sequence } = schema.parse(input); try { const { client } = ctx.siteState.ensureSelectedSite(); const params = new URLSearchParams(); if (typeof sequence === "number") params.set("sequence", String(sequence)); const url = `/drafts/${encodeURIComponent(draft_key)}.json${params.toString() ? `?${params}` : ""}`; const data = (await client.get(url)) as { draft?: string; draft_sequence?: number; }; if (!data?.draft) { return { content: [{ type: "text", text: `No draft found for key "${draft_key}".` }] }; } let parsedDraft: Record<string, unknown> = {}; try { parsedDraft = JSON.parse(data.draft); } catch { parsedDraft = { raw: data.draft }; } const lines = [`# Draft: \`${draft_key}\`\n`]; lines.push(`**Sequence:** ${data.draft_sequence ?? "unknown"}`); if (parsedDraft.title) lines.push(`**Title:** ${parsedDraft.title}`); if (parsedDraft.categoryId) lines.push(`**Category ID:** ${parsedDraft.categoryId}`); if (parsedDraft.tags && Array.isArray(parsedDraft.tags)) { lines.push(`**Tags:** ${(parsedDraft.tags as string[]).join(", ")}`); } if (parsedDraft.action) lines.push(`**Action:** ${parsedDraft.action}`); if (parsedDraft.reply) { lines.push(`\n**Content:**\n${parsedDraft.reply}`); } lines.push("\n```json"); lines.push( JSON.stringify( { draft_key, draft_sequence: data.draft_sequence, data: parsedDraft, }, null, 2 ) ); lines.push("```"); return { content: [{ type: "text", text: lines.join("\n") }] }; } catch (e: unknown) { const msg = e instanceof Error ? e.message : String(e); return { content: [{ type: "text", text: `Failed to get draft: ${msg}` }], isError: true }; } } );

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/discourse/discourse-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server