glp1forum-mcp
glp1forum-mcp lets you search, browse, and read content from glp1forum.com (a XenForo-based forum focused on GLP-1 medications) via MCP tools. It requires system curl and enforces rate limits (2.5s gap between requests; automatic backoff on 403/429/503).
Search the forum (
search_forum): Full-text search with filters — keywords (AND-matched), forum sections (nodes), author, date range, minimum replies, sort order (relevance, date, replies), and up to 3 pages of results. Category nodes requireincludeChildNodes: true. Results can be grouped by thread.Read thread posts (
get_thread): Retrieve paginated thread content including author, datetime, post body, and permalink. Identify threads by URL orthreadId.Download thread images (
get_thread_images): Opt-in download of full-size image attachments (up to 5 per call) for vision-based reading of image-only content like pricing tables, stock boards, and COA purity figures that are invisible to plain text extraction.Browse a forum section (
list_threads): List threads within a specific section by its numericnodeId, with pagination.Discover forum sections (
list_forums): Get all forum sections and their numericnodeIds, used for targeted searches or thread listings.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@glp1forum-mcp search for semaglutide dosage discussions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
glp1forum-mcp
An MCP stdio server that searches and reads https://glp1forum.com (a XenForo forum) with no API keys. It shells out to system curl because Cloudflare there blocks Node's own TLS fingerprint but passes a real curl with a browser User-Agent.
⚠️ The one gotcha
Verified only with Windows curl 8.18 (Schannel). Linux/macOS curl presents a different TLS fingerprint and may get a 403 from Cloudflare. If every request 403s, this is almost certainly why.
Related MCP server: evo-scry
Requirements
Node 18+
System
curlon yourPATH(curl --versionshould work)
Tools
search_forum— full-text search with XenForo filters (keywords, nodes, author, date range, min replies, order, page,maxPagesup to 3). Keywords are AND-matched; category nodes needincludeChildNodes: true.get_thread— read a thread's posts (author, datetime, body, permalink), paginated.get_thread_images— opt-in: download a thread's image attachments at full size as image blocks so vision can read image-only pricing tables / stock boards / COA figures.maxcaps the count (default 4, max 5 — full-size images are token-expensive).list_threads— browse a forum section's thread list bynodeId, paginated.list_forums— list forum sections with their numeric node IDs (feed these tosearch_forum.nodesandlist_threads.nodeId).
Rate limiting
All requests share a global throttle: ≥2.5s between hits. On HTTP 403/429/503 the server backs off 8s plus up to 10s of jitter and retries once; if still blocked it throws glp1forum rate-limited or unavailable (HTTP 503) — wait ~60s before retrying.
The backoff is deliberately much shorter than the ~60s a Cloudflare 503 actually takes to clear: a handler that slept that long would trip the MCP client's own 60s timeout (-32001), and the sleep holds the search mutex. So it fails fast with a retryable error and asks the caller to wait instead — hence "wait ~60s" in the message.
Two env vars tune this:
GLP1_BACKOFF_MS(default8000) — the retry backoff. Raise it if one retry isn't enough.GLP1_INTERVAL_MS(default2500) — the global gap between requests. Raise it for heavy concurrent use; each search costs 2 requests, and 8-way concurrency trips Cloudflare at 2.5s.
Install
Option A — Claude Code plugin marketplace (recommended)
/plugin marketplace add Sedation6612/glp1forum-mcpThen install the glp1forum-mcp plugin. This auto-wires the MCP server; the plugin's config uses ${CLAUDE_PLUGIN_ROOT} so there are no paths to edit.
Option B — Desktop Extension (.mcpb, one-click Claude Desktop)
Download glp1forum-mcp.mcpb from the repo's Releases and double-click it — Claude Desktop
installs it with no paths to edit and no npm install (the server is bundled into a single
dependency-free dist/index.mjs). You still need system curl on your PATH.
Option C — manual (Claude Desktop)
Run npm install && npm run build first, then add to claude_desktop_config.json:
"glp1forum": { "command": "node", "args": ["C:\\path\\to\\glp1forum-mcp\\dist\\index.mjs"] }MSIX Claude Desktop installs put this config under
%LOCALAPPDATA%\Packages\Claude_pzs8sxrjxfjjc\LocalCache\Roaming\Claude\, not plain%APPDATA%.
Build (contributors)
The distributed artifact is a single bundled dist/index.mjs (esbuild). After editing anything
in src/, rebuild and commit dist/:
npm install
npm run build # -> dist/index.mjs (what the plugin & .mcpb run)
npm run pack # build + produce glp1forum-mcp.mcpb for Claude DesktopSelf-test
npm run selftest # or: node src/selftest.jsMakes a few dozen seconds of live requests under the throttle. Failure means curl is being blocked or the site's HTML drifted.
License
Source-available, not open source. You may install and run it; you may not redistribute or modify it. See LICENSE.
Available Tools
5 toolsget_threadARead-only
Read a thread's posts (paginated) for full context.
Inputs: url, page, threadId.
get_thread_imagesARead-only
Opt-in: download a thread's image attachments at full size so their text (pricing tables, per-warehouse stock boards, COA purity figures, payment pages) is readable by vision. Much of the vendor pricing on glp1forum is image-only and invisible to get_thread's text. Returns a summary plus the images as blocks; use max to cap how many download (default 4, max 5). Costs one throttled request per image.
Inputs: max, url, page, threadId.
list_forumsARead-only
List forum sections with numeric node IDs (feed these to search_forum.nodes).
Inputs: no named parameters.
list_threadsARead-only
Browse a forum section's threads (use list_forums for nodeIds).
Inputs: nodeId (required), page.
search_forumARead-only
Full-text search glp1forum.com with granular XenForo filters. Multi-word keywords are AND-matched (all terms must appear). Category/parent nodes (e.g. 45 Vendor Connection) return nothing unless includeChildNodes: true. A rate-limit error means wait ~60s before retrying. Result has truncated: true when more result pages exist than were fetched — re-search with a higher maxPages (max 3) to get the rest.
Inputs: keywords (required), page, nodes, order, +9 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clear and distinct purpose: listing forums, listing threads, reading a thread's posts, downloading images, and searching. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case (list_forums, list_threads, get_thread, get_thread_images, search_forum), making the set predictable.
With 5 tools, the server covers browsing, reading, and searching a forum without being excessive or insufficient. The count feels well-scoped for the domain.
The tool set provides a complete read-oriented interface for the forum: navigating sections, listing threads, reading posts with pagination, accessing images, and full-text search. No obvious gaps for a read-only use case.
Maintenance
Related MCP Connectors
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP registry & directory: search, find & install 31k+ MCP servers & tools. Catalog and marketplace.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for using various search tools like Tavily API. Planning to support various search tools (i.e. wiki search, searxng, etc)3MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for internet search via direct Google and DuckDuckGo HTML scraping with AI-powered result normalization and optional summarization, requiring no API keys for search.MIT
- FlicenseNot gradedqualityDmaintenanceAn experimental MCP server that provides web search capabilities using the Tavily API. Still in progress, not production-ready.-
- AlicenseAqualityDmaintenanceMCP server for Flarum forums that enables searching, reading, and posting discussions through Flarum's REST API.717 npmMIT