Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SVMMON_API_KEYYesYour svm_ key from Svmmon API settings. Required.
SVMMON_BASE_URLNoOverride base URL for self-host/staging. Default: https://app.svmmonapp.comhttps://app.svmmonapp.com

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_usageA

Check the Svmmon account's current usage and limits: subscription tier, monthly slideshows used vs. cap, when the counter resets, and per-TikTok-account inbox draft slots (used/cap/available). Use this to answer "how many slideshows do I have left", "check my Svmmon usage", or "how many TikTok slots are free" — and call it before a batch of generations to confirm there is quota and TikTok slot headroom. Consumes no quota.

list_profilesA

List the Svmmon account's profiles (personas) with their id, name, niche, generation readiness, and whether a TikTok account is linked. Use this for "what profiles do I have" or "list my Svmmon personas". IMPORTANT: only profiles where ready is true can generate a slideshow — if a profile is not ready, the missing list says which image collection it still needs. Never invent a profile id; call this first to get a real one. Consumes no quota.

list_presetsA

List the slide presets you can pass as preset_id to generate_slideshow. Use this for "what slide presets can I use" or before generating a slideshow when the user wants a specific structure. Every id returned is a valid preset_id. Consumes no quota.

generate_hooksA

Generate scored TikTok hook candidates for one of the user's Svmmon profiles. Use when the user asks for hooks, openers, or angles for a profile (e.g. "give me 5 hooks for my Marcus profile about staying consistent"). Returns hooks ranked by a 0-100 virality score and persists them to the profile's hook library. COST: each batch of 3 candidates spends one AI credit (count=5 → 2 credits). May return FEWER hooks than requested if the AI-credit cap is hit mid-request — that is expected, not an error. Requires a valid profile_id: call list_profiles first and never invent one.

generate_slideshowA

Generate ONE complete TikTok slideshow from a Svmmon profile and a hook, render it, and optionally deliver it to TikTok or Telegram. The profile is the source of truth for tone, preset, images, slide counts, and CTA. Use when the user asks to make/create/build a slideshow or post from a hook. CONSUMES ONE SLIDESHOW from the monthly cap and is NOT idempotent — never call it twice for the same request; if it times out, check list_slideshows before retrying (the slideshow may already exist). Takes 30-120 seconds. Check get_usage first if you may be near the monthly cap. Returns a slideshow_id and a signed ZIP download_url valid for 24 hours. Delivery failures never fail generation — a failed TikTok/Telegram send comes back as a reason, not an error. Requires a ready profile_id (call list_profiles; only ready:true profiles can generate).

list_slideshowsA

List the most recent slideshows on this Svmmon account, newest first. Use this when the user asks to "show my recent slideshows", "what have I generated", or wants a slideshow id to fetch its download link with get_slideshow. Returns id, hook text, profile_id, and created_at for each. Read-only — consumes no quota. Optional limit (1–100, default 20).

get_slideshowA

Fetch one slideshow by its id, including fresh 1-hour signed download URLs for its export ZIP. Use this when the user asks to "get the download link for slideshow X", "re-download a slideshow", or "get the link again" (the link from generate_slideshow expires after 24h; this mints fresh 1h links). Get the id from list_slideshows first. Read-only — consumes no quota. Download links may be empty if the slideshow has no export file (e.g. a Telegram-only export).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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/coreywessel/svmmon-mcp'

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