io.github.thehesiod/psquare
Enables Claude to access ParentSquare school-parent communication platform, including feeds, calendar, conversations, and media files.
README
ParentSquare MCP Server
An MCP (Model Context Protocol) server that gives Claude access to ParentSquare, a school-parent communication platform. Since ParentSquare has no public API, this server scrapes the web interface using saved session cookies.
Available on the MCP Registry as io.github.thehesiod/psquare and on PyPI as parentsquare-mcp.
Disclaimer
This project is not affiliated with, endorsed by, or sponsored by ParentSquare, Inc. "ParentSquare" and all related names, logos, and trademarks are the property of ParentSquare, Inc.
This server communicates with ParentSquare's undocumented internal APIs (scraping the web UI and calling its non-public
/api/v2/JSON endpoints) — these are not published, not guaranteed to be stable, and may change or be blocked at any time without notice. Use of those interfaces may violate ParentSquare's Terms of Service; you are responsible for reviewing the ToS and deciding whether your use is acceptable.Use at your own risk. The authors and contributors accept no responsibility for any consequences of using this software, including but not limited to: account suspension or termination, data loss or corruption, missed or incorrect notifications, MFA lockouts, leaked session cookies, IP blocks, or any other direct or indirect damages. No warranty is provided — see LICENSE for the full MIT no-warranty clause.
If ParentSquare publishes an official API, this project should be considered deprecated in favor of that.
Features
Feed & Posts
get_feeds— Browse paginated school feed with titles, authors, summaries, and attachment namesget_post— Full post details with body text, comments, poll results, signup items, and inline image/PDF content (Claude can "see" attached calendars, flyers, etc.)get_group_feed— Posts from a specific group
Calendar
get_calendar_events— Events from ICS calendar as structured JSON (title, start/end, location, description)- Falls back to guiding Claude to search feed posts for image/PDF calendars when ICS is empty
Communication
list_conversations/get_conversation— Read message threadsget_directory— Staff directory as structured JSON (name, role, phone, user_id)get_staff_member— Full staff details with email, office hours, and inline profile photo
Media & Files
list_photos— Photo gallery with URLslist_files— Document filesdownload_file— Download any attachment to local disk
Participate
list_signups— Sign-up and RSVP posts with progress tracking (e.g. "53/103 Items")list_notices— Alerts and secure documentslist_polls— Polls with vote counts and winning optionslist_forms— Permission slips and signable formslist_payments— Payment items with prices and summary statslist_volunteer_hours— Logged volunteer hours with totals
Groups & Discovery
list_schools— Schools and students as structured JSONlist_school_features— Available sections per school (parsed from sidebar)list_groups— Groups with member counts, descriptions, and membership statuslist_links— Quick-access links (Google Drive, external sites)
Student
get_student_dashboard— School, grade, classes, and teachers as structured JSON
Authentication
submit_mfa_code— Complete MFA verification with a 6-digit code- Supports MCP elicitation for inline MFA prompts
- Session cookies persisted to
~/.parentsquare_cookies.json - Credentials loaded from environment variables or 1Password CLI on session expiry
Setup
Prerequisites
Credentials can be provided in either of two ways (checked in this order):
- Environment variables — set
PS_USERNAMEandPS_PASSWORD - 1Password CLI (
op) — with a "Parentsquare" item containingusernameandpasswordfields
Install in Claude Code
claude mcp add --transport stdio parentsquare -- uvx --from "parentsquare-mcp @ git+https://github.com/thehesiod/psquare-mcp" parentsquare-mcp
To enable PDF text extraction for post attachments (optional, AGPL-3.0 licensed):
claude mcp add --transport stdio parentsquare -- uvx --from "parentsquare-mcp[pdf] @ git+https://github.com/thehesiod/psquare-mcp" parentsquare-mcp
That's It
No further configuration needed. The server auto-discovers your schools, students, and user ID from ParentSquare on first use. Authentication is handled automatically — when the session expires, the server loads your credentials from environment variables (or 1Password CLI) and re-authenticates (including MFA if needed).
To use environment variables with Claude Code, add an env block to your MCP config:
{
"mcpServers": {
"parentsquare": {
"command": "uvx",
"args": ["parentsquare-mcp"],
"env": {
"PS_USERNAME": "your@email.com",
"PS_PASSWORD": "your-password"
}
}
}
}
Security note: environment variables place your password in plaintext inside your MCP config file. If you chose a password manager specifically to avoid that, prefer the 1Password CLI path.
How It Works
The server uses requests + BeautifulSoup to scrape ParentSquare's server-rendered HTML pages. Each tool follows the pattern:
- Fetch the HTML page via
PSClient.get_page()or JSON viaPSClient.get_json()(auto-relogins on session expiry) - Parse with a dedicated parser in
parsers/that extracts structured data into dataclasses - Return results as either structured JSON dicts (for data-lookup tools) or markdown text (for content-rich tools)
Data-lookup tools (list_schools, get_directory, get_calendar_events, get_student_dashboard, get_staff_member) return structured JSON for easy programmatic access. Content tools (get_post, get_feeds, get_conversation) return markdown.
On first use, the server auto-discovers your schools, students, and user ID from ParentSquare (no config file needed).
For get_post, image attachments are downloaded and returned as MCP Image objects (so Claude can see them), and PDF attachments have their text extracted via pymupdf. get_staff_member also returns inline profile photos.
Groups use a GraphQL endpoint (/graphql) instead of HTML scraping. The directory and staff details use the internal /api/v2/ JSON:API.
Dependencies
| Package | Purpose | License |
|---|---|---|
mcp |
Model Context Protocol SDK | MIT |
requests |
HTTP client | Apache 2.0 |
beautifulsoup4 |
HTML parsing | MIT |
icalendar |
ICS calendar parsing | BSD |
pymupdf |
PDF text extraction (optional) | AGPL-3.0 |
License
MIT — see LICENSE. Note: the optional pymupdf dependency is AGPL-3.0 licensed.
mcp-name: io.github.thehesiod/psquare
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.