A local MCP server for creating and editing Excalidraw documents
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"exca-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Excalidraw MCP Server <!-- TODO: mcp-name marker (server.json not found in repository) --> [](https://www.python.org/) [](https://pypi.org/project/exca-mcp/) [](https://github.com/jlowin/fastmcp) [](https://github.com/Dharshan2208/excalidraw-mcp/actions/workflows/ci.yml) [](https://github.com/Dharshan2208/excalidraw-mcp/blob/main/LICENSE) [](https://hatch.pypa.io/) Excalidraw MCP is a backend oriented Model Context Protocol (MCP) server that enables AI agents to create, inspect, edit, diagnose, and export native [Excalidraw](https://excalidraw.com) diagrams over standard `stdio`. Unlike browser automation wrappers, Excalidraw MCP operates directly on scene graphs and element trees in memory. AI coding agents can construct complex architectures, generate flowcharts from Mermaid syntax, inspect element hierarchies, and apply deterministic layout repairs without requiring a running web browser or graphical interface. Diagrams are serialized in native Excalidraw Schema v2 format, ensuring immediate compatibility with excalidraw.com, standard Excalidraw desktop extensions, and headless image export pipelines. --- ## Demo  *This diagram was generated with Excalidraw MCP itself. Editable source: [docs/architecture.excalidraw](https://github.com/Dharshan2208/excalidraw-mcp/blob/main/docs/architecture.excalidraw).* <details> <summary>View agent generation workflow and tool calls</summary> ```python # 1. Create architectural tier fr…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.