AI product Open source
Model Context Protocol (MCP) is an open, standardized protocol layer for connecting large language models and AI agents with external data sources, hosted infrastructure tools, and other contextual data. It defines formats, metadata, protocol schemas, and APIs for sharing information and tools, attaching, referencing, and validating context such as documents, embeddings, and provenance, while supporting scoped authentication and permissions. MCP translates JSON requests from an agent into calls to service APIs, including CRM, container-management, and GKE capabilities, and can provide design-system context and related tools for generating consistent applications. The official project publishes its specification, documentation, and protocol schema; the schema is defined first in TypeScript and also provided as JSON Schema for broader compatibility. The protocol was created by David Soria Parra and Justin Spahr-Summers, is hosted at modelcontextprotocol.io, and is licensed under the MIT License.
18 uses taken from transcripts — each links to the moment in the video.
Provides a standardized layer between an LLM or AI agent and external data sources such as a CRM; handles scoped authentication and permissions and translates JSON requests into service API calls.
Connected Google Drive, Claude, and Fable so the agent could access data and modify code across systems.
Provides a reusable, model-agnostic protocol for connecting agents and LLM hosts to external tools and data, including APIs, databases, files, repositories, test runners, and issue trackers.
Open protocol used to connect agents and tools and to support integrations into the orchestration platform.
Shares design-system information and tools with an AI agent in a format the agent can consume while building software.
Interface used for controlled note, endpoint, and email-agent access.
Connects the AI agent to hosted infrastructure tools and context, including GKE or container-management capabilities.
Exposes lemalog memory to agent clients.
Connects AI agents to tools, task managers, and shared design canvases.
Provides external tools for Fuxi and direct agent control for fx and moli.
Connects an AI agent to external systems such as logging stacks, dashboards, metrics, and other services so it can retrieve information and perform actions.
MCP, or the Model Context Protocol, connects an AI agent to external systems so it can look up information and perform actions. MCP servers expose systems such as logging stacks, metrics, and dashboards for the agent to call.
A communication and orchestration layer that connects AI models to tools, coordinating the actions an AI agent takes.
Exposes the local video-editing tools to agents.
A mechanism customers can use to access or extend the Lightfield system of record.
Connects agents to Design Studio AI and arsumbris projects.
Carries a coding agent's focused diff to the code-review workflow.
Connects repository indexes and Markdown knowledge vaults to AI agents.
19 in the library.