Harvest Natural Language Time Entry MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TIMEZONE | No | Your timezone | Australia/Perth |
| HARVEST_ACCOUNT_ID | Yes | Your Harvest account ID | |
| HARVEST_ACCESS_TOKEN | Yes | Your Harvest personal access token from Harvest Developer Tools | |
| STANDARD_WORK_DAY_HOURS | No | Default hours for a full work day | 7.5 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| log_timeC | Log time entry using natural language |
| list_projectsB | List available Harvest projects |
| list_tasksC | List available tasks for a project |
| list_entriesC | List recent time entries |
| get_time_reportC | Get time reports using natural language |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a distinct purpose: get_time_report retrieves reports via natural language, list_entries shows recent entries, list_projects and list_tasks enumerate available resources, and log_time creates entries via natural language. There is no overlap or ambiguity between these functions.
All tools follow a consistent verb_noun pattern (e.g., get_time_report, list_entries, log_time) with clear, descriptive names. There are no deviations in naming conventions or styles.
With 5 tools, this server is well-scoped for its purpose of natural language time entry management. Each tool serves a specific role in the workflow, from listing resources to reporting and logging, making the count appropriate and efficient.
The toolset covers core operations like listing projects/tasks, logging time, and getting reports, which supports natural language interactions. A minor gap exists in update or delete functionality for time entries, but agents can likely work around this given the server's focus on natural language entry and reporting.