Frappe MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 78 installs a week from pypi. Last commit 29 Jul 2026.
Interact with Frappe/ERPNext sites — document CRUD, search, and whitelisted method calls
Today is the operative word: we check Frappe MCP Server every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add frappe_mcp -- uvx frappe-mcp-server
{
"mcpServers": {
"frappe_mcp": {
"args": [
"frappe-mcp-server"
],
"command": "uvx"
}
}
}
[mcp_servers.frappe_mcp]
command = "uvx"
args = ["frappe-mcp-server"]
{
"mcpServers": {
"frappe_mcp": {
"args": [
"frappe-mcp-server"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"frappe_mcp": {
"args": [
"frappe-mcp-server"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
FRAPPE_URL (Base URL of your Frappe/ERPNext site, e.g. https://your-site.erpnext.com), FRAPPE_API_KEY (Frappe API key for token-based authentication), FRAPPE_API_SECRET (Frappe API secret paired with the API key), FRAPPE_VERIFY_SSL (Set to 'false' to skip TLS certificate verification. Defaults to 'true'.), FRAPPE_TIMEOUT (Per-request timeout in seconds. Defaults to 30.).
The author declared them in the registry entry; get the values from the project itself.
Official Egnyte MCP Server for AI integration with document search, analysis, and collaboration.
Search, document and execute authenticated API calls across 700+ apps via one MCP server
Offline MCP server for local Qt 4.8, Qt 5, and Qt 6 documentation with full-text search.
MCP server for GroupDocs.Metadata — read, search, write, and remove document metadata.
Extract structured data points from research papers and other documents with an LLM.
MCP server for self-hosted Laserfiche repositories — search and read documents from Claude.
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
PDF parsing server with text extraction, metadata, search, images, and TOC via MCP
Answers built from our own checks of this server.