# Sparka (remote · sparka.io) Your AI sets up live quizzes, polls and word clouds. People join on their phones with a PIN or QR. - Trust score: 60/100 (medium) - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-11-05 ## Components - remote · `sparka.io`: 60/100 (this document), [markdown](https://verifymcp.io/servers/io-sparka-sparka/sparka.md), [page](https://verifymcp.io/servers/io-sparka-sparka/sparka) ## Channel facts - Endpoint: `https://sparka.io/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `0.1.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-11-05. - **Endpoint Security**: 46/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (sparka_presentation_delete). - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 403, which proves neither a plaintext path nor enforcement. - HSTS check failed: the Strict-Transport-Security header is absent. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 77/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (good). - Context-footprint check failed: tool/resource definitions use about 1365 tokens (~151/item across 9 items; 8 tools + 1 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 10/100 - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 80/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 31% of tool parameters carry a description. - Structured output schemas are declared (100% of tools); any adoption earns full credit. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a current MCP spec version (2026-07-28). ## Install ### How do I install the Sparka MCP server? Sparka is a hosted endpoint at https://sparka.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http io-sparka-sparka 'https://sparka.io/mcp' ``` ### Cursor ```json { "mcpServers": { "io-sparka-sparka": { "url": "https://sparka.io/mcp" } } } ``` ### VS Code ```json { "servers": { "io-sparka-sparka": { "type": "http", "url": "https://sparka.io/mcp" } } } ``` ### Codex ```toml [mcp_servers.io-sparka-sparka] url = "https://sparka.io/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "io-sparka-sparka": { "type": "remote", "url": "https://sparka.io/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add io-sparka-sparka --url 'https://sparka.io/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: io-sparka-sparka: url: "https://sparka.io/mcp" ``` ### Netclaw ```json { "McpServers": { "io-sparka-sparka": { "Transport": "http", "Url": "https://sparka.io/mcp" } } } ``` ### Vellum ```bash assistant mcp add io-sparka-sparka -t streamable-http -u 'https://sparka.io/mcp' ``` ### Other ```json { "mcpServers": { "io-sparka-sparka": { "type": "http", "url": "https://sparka.io/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-11-04 (score 60, +1) No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-11-03 (score 59, 0) - [functional improvement] Stability: unverified → 0.03 ### 2026-11-02 (score 59) First indexed and scored. ## MCP tools (8) ### `sparka_account_get` (~147 tokens) Get account and plan Returns the account's plan, limits (participants per session, sessions per month, presentations, concurrent live sessions), usage this period, a `summary` sentence with the same numbers, and `pricing_url`, the public page listing the plans. A session counts toward sessions per month only once `counted_session_min_participants` (3) or more participants join, so rehearsals with fewer are free, and resuming a live session never counts again. Use it to check limits before writing a deck, or when a quota or participant-limit error occurs. Billing is managed on the Sparka account page, not through this tool. Share links with the user; never open them yourself. Output parameters: - `account_id` (string) - `counted_session_min_participants` (integer): A session counts toward sessions_per_month only once this many participants have joined it. - `limits` (object) - `plan` - `pricing_url` (string): Public page listing the plans. - `summary` (string): The plan's limits, usage and counting rule in one plain paragraph. - `usage` (object) ### `sparka_deck_guide` (~147 tokens) Get the deck guide Returns the rules and a reference JavaScript pattern for making an HTML presentation interactive with Sparka: Start/End buttons and their labels, a lobby with the QR code, PIN and join URL that can be opened from any slide, switching the live question when slides change, Reveal, live answer counts, countdowns that stop when a question closes, animated results, leaderboard and podium slides, reconnecting, and graceful offline behavior. The reference code's look can be adapted to the deck; its behavior is what makes a deck work with Sparka. Sparka ships no script library — the deck's own code is the integration. No account key needed. Input parameters: - `part` Output parameters: - `text` (string): Markdown. - `version` (string) ### `sparka_presentation_delete` (~111 tokens) Delete a presentation Permanently deletes a presentation and ends its live session if one is running. Results of past sessions stay readable with `sparka_results_get` by `session_id` until their retention ends. Decks using this `presentation_id` stop working. This is also how an ID that was shared too widely is retired (IDs are never rotated: delete, then save the questions again to get a new ID and update the deck). Confirm with the user before calling. Input parameters: - `presentation_id` (string, required) Output parameters: - `deleted` - `ended_session_id` (string|null) - `presentation_id` (string) ### `sparka_presentation_get` (~101 tokens) Get a presentation Returns one presentation: title, settings, questions (with correct answers unless `include_answers` is false), the live session if one is running (PIN, participants), and the most recent sessions. Useful for editing an existing presentation (get, modify, then `sparka_presentation_save` with the same `presentation_id`) or for checking what a deck is using. Input parameters: - `include_answers` (boolean) - `presentation_id` (string, required) Output parameters: - `created_at` (string) - `embed_block` (string) - `live_session` (object|null) - `presentation_id` (string) - `questions` (array) - `recent_sessions` (array) - `settings` - `title` (string) - `updated_at` (string) ### `sparka_presentation_list` (~78 tokens) List presentations Lists the account's presentations, newest first, with title, question count, last update and last session time. Useful when the user refers to a presentation without giving its ID ("results from yesterday's talk"). Paginated with `cursor`. Input parameters: - `cursor` (string): next_cursor from the previous call. - `limit` (integer) Output parameters: - `items` (array) - `next_cursor` (string|null) ### `sparka_presentation_save` (~310 tokens) Save a presentation Creates or fully replaces a presentation's interactive questions in one call. Each call carries the COMPLETE presentation: title, optional settings, and the ordered list of all questions including correct answers for scored types (valid types and fields: `sparka_question_types_list`). Without `presentation_id` it creates a new presentation; with it, it replaces that presentation entirely — the ID stays the same, so a deck already using it keeps working, and unchanged question IDs keep matching the deck's slides. The questions without answers are readable by anyone who has the `presentation_id`; that is how decks and participants' phones load them. Returns `presentation_id`, the stored questions WITHOUT answers, and `embed_block`: a ready-to-paste `