Hecher MCP Server

Hecher MCP Server

Enables AI assistants to search donors, record donations, run reports, and manage tasks across multiple organizations (Mosads) in the Hecher CRM.

Category
Visit Server

README

Hecher MCP Server

The official Model Context Protocol (MCP) server for Hecher — the multi-tenant CRM for Chabad shluchim by Grow Gelt.

Connect Claude Desktop, ChatGPT, Cursor, or any other MCP‑compatible AI assistant to your Hecher account and let it search donors, record donations, run reports, and manage tasks for you — across all of your organizations (mosads).

Heads up: This repository is the public listing and documentation for the Hecher MCP server. The server itself runs as a managed remote service at https://api.hecher.app/mcp — there is nothing to install or self-host.


Quick start

  1. In your MCP‑compatible client (Claude Desktop, ChatGPT, Cursor, etc.), add a new remote MCP server with this URL:

    https://api.hecher.app/mcp
    
  2. The first time you use it, your browser will open and ask you to sign in to Hecher and approve the connection.

  3. Once approved, the assistant can act on your account.

You can review and revoke connected assistants anytime under Settings → AI Connections inside Hecher.


What it can do

The server exposes 20 tools that wrap the Hecher API. Every call runs as you, in whichever Mosad you've selected as active — RLS, billing gates, and audit logging all apply exactly as in the web app.

Organizations (Mosads)

  • list_tenants — list the Mosads you have access to
  • set_active_tenant — choose which Mosad subsequent calls operate on
  • get_active_tenant — show the currently active Mosad

Donors

  • search_donors — search by name, email, phone, tag, or status
  • get_donor — full profile with stats and contact info
  • create_donor / update_donor / delete_donor
  • add_donor_tag / remove_donor_tag / bulk_tag_donors

Donations

  • list_donations — optionally filtered by donor or date
  • create_donation / update_donation / delete_donation

Activities & tasks

  • list_activities — optionally filtered by donor, status, or assignee
  • create_activity — task, call, meeting, or note
  • complete_activity

Reporting

  • get_dashboard_stats — KPIs for the active Mosad
  • run_report — execute a saved report

Authentication

The server speaks OAuth 2.1 with dynamic client registration, so any compliant MCP client can connect with no manual API keys.

Endpoint URL
Discovery https://api.hecher.app/.well-known/oauth-authorization-server
Authorization https://api.hecher.app/oauth/authorize
Token https://api.hecher.app/oauth/token
Dynamic registration https://api.hecher.app/oauth/register

Each authorization issues an access token bound to your user account and the Mosad you pick during the consent flow. Tokens can be revoked at any time from Settings → AI Connections.


Permissions & limits

  • Tools act with the permissions of the signed‑in user in the active Mosad — no privilege escalation.
  • All write operations honor Hecher's billing gates and audit log.
  • Per‑user rate limits from the Hecher API gateway apply.
  • Bulk mutations (e.g. bulk_tag_donors) flow through Hecher's background operation queue, the same as in the web UI.

Compatible clients

Any MCP client that supports remote servers over Streamable HTTP with OAuth 2.1, including:


Support

  • Product: hecher.app
  • Issues with this listing or the MCP server: open an issue in this repository
  • General Hecher support: through the in‑app feedback button

License

MIT © Grow Gelt Solutions

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured