Extend

Turn documents into structured data: parse, extract, classify, split, and fill PDF forms.

LLM Mart 11 views 104 listing impressions
Transport
Not stated
Package
Registry id
ai.extend/extend

No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.

The Extend MCP (Model Context Protocol) server lets AI clients use Extend directly from chat. The server exposes every tool by default, but you can limit available tools by appending a comma-separated list of group or tool names in the tools query parameter. The tool surface covers parsing, extraction, classification, splitting, PDF editing, workflows, files, webhooks, and evaluations.

All operations target a specific workspace and environment, and the agent must state both on every call. For chat clients that can't expose local files, the agent requests an upload link for you to drop files into the Extend dashboard. Tool errors are structured, with a message, a link to documentation, and a request ID, and you can contact support with the request ID.

MCP is best for chat and tool-calling clients, while SDKs are for durable integration code and the CLI for one-off shell jobs.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Related servers

vSphere with Tanzu (VKS): Namespace and TanzuKubernetesCluster lifecycle. Requires vSphere 8.x+.

17 views

VMware compliance scanning (CIS, vSphere SCG, GB/T 22239, PCI-DSS) with drift detection.

14 views

MCP server for Geargrafx PC Engine / TurboGrafx-16 emulator

14 views

Read-only discovery for NeuralNg Angular components, APIs, packages, icons and theme recipes.

14 views