About Partiful
Partiful exposes public event listings from its Explore pages for people browsing parties, pop-ups, panels, and meetups. It returns event details and aggregate RSVP counts without guest lists or contact information.
Key features
- 01Browse public event listings
- 02Filter Explore results by region
- 03Retrieve event descriptions and times
- 04View locations and host names
- 05See aggregate RSVP counts
Use cases
- 01Find public events in a listed city
- 02Review details before attending
- 03Check event locations and times
- 04Compare RSVP counts across events
MCP support
An MCP server exposing tools to browse Partiful's public Explore listings and retrieve individual public event details. It runs through Pipeworx or as a standalone local stdio server.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://gateway.pipeworx.io/partiful/mcpclaude mcp add --transport http pipeworx-io-partiful https://gateway.pipeworx.io/partiful/mcp{"mcpServers":{"pipeworx-io-partiful":{"type":"http","url":"https://gateway.pipeworx.io/partiful/mcp"}}}Open in Cursor{"servers":{"pipeworx-io-partiful":{"type":"http","url":"https://gateway.pipeworx.io/partiful/mcp"}}}Open in VS Code{"mcpServers":{"pipeworx-io-partiful":{"type":"http","url":"https://gateway.pipeworx.io/partiful/mcp"}}}{"mcpServers":{"pipeworx-io-partiful":{"serverUrl":"https://gateway.pipeworx.io/partiful/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
43| Parameter | Type | Required | Description |
|---|---|---|---|
| q | string | No | Alias for question. |
| ask | string | No | Alias for question. |
| text | string | No | Alias for question. |
| input | string | No | Alias for question. |
| packs | array | No | OPTIONAL. Restrict routing to these pack slugs (e.g. ["sec-form-d","sec-13f"]) — the router then picks only from tools in those packs. Omit for the default full-catalog routing. Slugs come from list_packs / search_packs / https://pipeworx.io/directory; unlisted or unknown slugs are ignored and named in _meta.pack_scope.ignored, and if none of them resolves the question is routed across the whole catalog with _meta.pack_scope.full_catalog:true (never an empty answer). |
| query | string | No | Alias for question. |
| prompt | string | No | Alias for question. |
| message | string | No | Alias for question. |
| question | string | Yes | Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases. |
Details
From the project README@pipeworx/partiful
Public event listings from Partiful's explore pages — titles, times, locations, host names, and aggregate RSVP counts for the parties, pop-ups, panels and meetups Partiful surfaces as crashable.
Part of Pipeworx — an MCP gateway connecting AI agents to 1807+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
partiful_explore(region?)— browse the public explore page. Pass a region code (nyc,la,sf,dc,chi,bos,atx,mia) for a richer set of themed sections for that city; omit it for the top-level cross-city trending overview (NYC/LA/SF only).partiful_event(event_id)— full public detail for one event: title, description, start/end time, location, image, host display names, and aggregate RSVP counts. Never returns a guest list or contact info.
Auth
Keyless. No account, login, or API key of any kind — the explore page and event pages are rendered for anonymous visitors.
Data sources
- Partiful, public event listings — the explore carousels and per-event pages Partiful serves to any visitor, logged in or not.
Notes
- Partiful server-renders
/exploreand its per-event pages as a Next.js app and ships the full public-field event data inside a__NEXT_DATA__JSON blob in the plain HTML. No separate API call, no JS execution needed — this pack parses that blob directly. /explorewith no region carries only a small baked NYC/LA/SF trending overview (~5 events per city). The per-region explore page is a separate, much richer per-city page with up to a dozen themed sections (Halloween Parties, Pop-Ups & Markets, Meet Someone New, etc.) — use it when you want real coverage for one city.- Only eight region codes resolve on that route (probed live 2026-10-13):
nyc,la,sf,dc,chi,bos,atx,mia. Every other candidate tried (chicago, seattle, london, philly, houston, san-diego, denver, atlanta, nashville, portland, toronto, …) 404s. There is no broader city/geo query parameter — this is the whole surface Partiful exposes. - Guest lists are never exposed, structurally: an unauthenticated request to
an event page gets
guest: nullfrom Partiful itself, so there is nothing to leak even if this pack tried to surface it. Host display names (shown publicly on the event page to any visitor) are returned; host photos, phone numbers, emails, and RSVP-form answers are never surfaced. locationnormalizes Partiful's two shapes:structured(neighborhood, display name, address lines, a Google Maps link) andfreeform(a single address string). A private/unlisted event, or an id that never existed, both 404 cleanly —partiful_eventraises a clear error rather than returning a half-filled record.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"partiful": {
"url": "https://gateway.pipeworx.io/partiful/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/partiful/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1807+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/partiful_explore \
-H 'Content-Type: application/json' \
-d '{"region":"la"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/partiful_explore. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"partiful": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-partiful"]
}
}
}
Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-partiful
It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call
for only this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Partiful data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.