Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Description from the maker (original English)
Verified music facts for agents: artists, releases, tracks, gigs, similar artists, discovery lists.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://mcp.hosaka.fm/mcpRun this in your terminal
claude mcp add --transport http ono-sendai https://mcp.hosaka.fm/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"ono-sendai": {
"url": "https://mcp.hosaka.fm/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"ono-sendai": {
"type": "http",
"url": "https://mcp.hosaka.fm/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://mcp.hosaka.fm/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
resolve_artistMap a name, URL or id to hosaka's verified artist identity (`cluster_id`) with an ambiguity verdict. Use: the user names an artist; you hold a Discogs / MusicBrainz / Bandcamp URL or id. Inputs: one of `q`, `url`, `cluster_id`, `discogs_id`, `mbid`. Returns: `cluster_id`, `displa
get_artistArtist card plus any published facet on request. Use: an artist's facts, releases or signals. Inputs: `key`: cluster_id from resolve_artist, or slug; `view`: summary | standard | full; `include`: ["similar", "gigs"] (linked, +1 unit each; 10 rows, 5 each when `view: full` carries
find_similar_artistsArtists adjacent to one artist, with the axes hosaka observed (co-appearance, radio co-play, DJ champions, lineage, credits, label mates) and counts — no composite score. Use: artists like X; a listening path from a verified artist. Inputs: `key`: cluster_id from resolve_artist,
get_labelRecord-label card (identity, allowlisted facets) with hosaka's over-merge signal when one label page may cover several labels. Use: the user asks about a label; an artist card names a label to expand. Inputs: `key`: label cluster_id (64-hex) or crate slug. Returns: label facets;
search_catalogSearch releases (masters) by text and facets, with cursor pagination. Use: releases matching a description; candidate names (rows carry artist_cluster_id). Inputs: `q` and/or `genre`, `style`, `format`, `country`, `label`, `year_from`, `year_to`; `limit` 1–100 (default 10); `curs
find_tracksFind tracks by title, resolve artist + track, or a batch of up to 25 tracks in one call — release facts, durations, cluster_id. Use: the user names a song; a tracklist. Inputs: `title` OR `artist` + `track` OR `tracks: [...]` (≤ 25); `limit` 1–25 (default 10). Returns: `data.resu
get_upcoming_gigsUpcoming gigs for one artist, or in one city within a date window. Use: where or when an artist plays; what is on in a city. Inputs: `key`: cluster_id from resolve_artist or slug, OR `city` (exact spelling); `from`, `to` YYYY-MM-DD. Returns: `data.gigs[]` {date, time, name, event
get_profileThe linked account's stable, opaque profile id (and display name if set); never ask the user for it. Use: the host needs a stable user handle; after sign-in to confirm the link. Inputs: none. Returns: `data.id`, `data.name`, `data.account_mode`, `data.linked_since`. Auth: linked.
get_usageThe linked account's current-period usage against its temporary allowance, with the 80 % warning and reset time. Use: the user asks how much is left; after quota_exceeded or a quota warning. Inputs: `period`: only "current" in v1. Returns: `allowance`, `used`, `warning_80`, `rese
list_breakoutsArtists breaking out or rising per hosaka, with the corroboration observed (press, or bookings ahead of press). Use: who is breaking through now. Inputs: `limit` 1–50 (default 8); `tier`: breakout | rising; `corroboration`: corroborated | booking_ahead. Returns: `data.items[]` {c
list_ones_to_watchThe ones-to-watch slice of hosaka's tastemaker index: rising names with emergence and momentum tiers from early-moving curators and DJs. Use: up-and-coming artists; a discovery playlist. Inputs: `limit` 1–50 (default 8). Returns: `data.items[]` {rank, name, slug, emergenceTier, m
get_auraAura: signal dimensions converging on an artist within 18 months, with measured 12-month break odds. Use: is an artist about to break. Inputs: `cluster_id` from resolve_artist (omit for the index); `limit` 1–50 (default 20). Returns: `data.items[]` or `data.aura` {cluster_id, art
browse_artistsBrowse hosaka's artist grid by Discogs genre and style, emergence tier and sort. Use: artists in a genre or style, by emergence tier. Inputs: `genre`, `style`: exact Discogs vocabulary (`Electronic`); `tier`: breakout | rising | steady; `sort`: discovery | reach; `limit` 1–30; `c
list_tastemakersA section of hosaka's tastemaker index: ones_to_watch is served; leaderboard and early_spinners are withheld until crate classifies them. Use: up-and-coming artists, or who moves a scene. Inputs: `section`: ones_to_watch | leaderboard | early_spinners; `limit` 1–50 (default 12).
get_festivalA festival card: header facts, identity and lineup as crate publishes them, acts linked to artist cards where a cluster_id exists. Use: a festival whose slug you have. Inputs: `key`: the festival slug (crate publishes no festival index — ask for the key). Returns: `display`, `slu
get_releaseOne release under an artist: a Discogs master (header, sections, artwork links, freshness) or a Bandcamp release (facts, track list). Use: a discography row names the release; one specific release. Inputs: `key`: artist cluster_id from resolve_artist, or slug; one of `master_id`
read_surfacehosaka's cluster-keyed surface registry (signal tables behind the facets) and one surface's rows for one cluster. Use: row-level detail behind a facet; which surfaces exist. Inputs: no arguments → the registry listing; `name` + `cluster` (64-hex) → rows; `limit`; `cursor`. Return
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 9, 2026
The registry lists no source repo, so we cannot match the publisher (hosaka.fm) to the code
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 299 ms (HTTP 200)
No sign-in needed
Read 17 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.6.0) reached the registry 10 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
No README found in the repo