Todo Markdown
This MCP server provides AI assistants with todo list management capabilities backed by markdown file storage, built by Daniel Dewhurst using TypeScript with persistent UUID tracking for reliable item updates. The implementation offers five core tools for complete CRUD operations: listing todos with statistics, adding new items, updating text or completion status, deleting specific todos, and bulk clearing completed items, all stored in standard markdown checkbox format with hidden HTML comment IDs for persistence. Built with comprehensive error handling for file permissions, configurable file paths via environment variables, and full test coverage using Vitest, it serves developers needing simple task management integrated into their AI workflows, teams requiring persistent todo tracking in human-readable markdown format, and users wanting to maintain todo lists that can be easily edited both programmatically through AI assistants and manually in any text editor.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- productivity
- Source
- PulseMCP
- Repository
- github.com/danjdewhurst/todo-md-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Todo Markdown from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.