Harvest
This MCP server provides AI assistants with complete Harvest time tracking integration, built by standardbeagle using TypeScript and the official Harvest API v2 to enable natural language control over time entries, project management, and reporting workflows. The implementation offers 17 specialized tools covering time entry CRUD operations, timer controls (start/stop/restart), project and task management, user and client administration, detailed reporting with date ranges, and assignment management, featuring comprehensive error handling, pagination support, and self-documenting help system with CLI compatibility. Built with fetch-based API client, environment-based authentication, extensive test coverage including integration tests, and published as an npm package for easy installation via npx, it serves freelancers and teams needing conversational access to Harvest workflows, project managers requiring AI-driven time tracking and reporting, and development teams where natural language interfaces enhance productivity tracking without direct Harvest web interface usage.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- data-analytics
- Source
- PulseMCP
- Repository
- github.com/standardbeagle/harvest-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Harvest 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.