deepseek_harness
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NO_PROXY | No | Comma-separated list of hosts to exclude from proxy. | |
| HTTP_PROXY | No | HTTP proxy URL. | |
| HTTPS_PROXY | No | HTTPS proxy URL. | |
| DEEPSEEK_API_KEY | Yes | Model credentials. | |
| HARNESS_MCP_ROOT | Yes | Required root directory; the launcher's --root takes precedence over this value. | |
| DEEPSEEK_BASE_URL | No | Optional service address, must be compatible with Harness provider. | |
| HARNESS_MCP_MODEL | No | deepseek-v4-flash, can be adjusted according to available models for the account. | deepseek-v4-flash |
| HARNESS_MCP_RUNTIME | No | Windows default node, Linux default bundled. | |
| HARNESS_MCP_TIMEOUT | No | Single round timeout, default 1800 seconds, range 1..86400. | 1800 |
| HARNESS_MCP_MAX_CONCURRENCY | No | 8, range 1..64, clients with the same root directory should have consistent configuration. | 8 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| submit_taskB | Start a coding task and return immediately. Multiple tasks may queue or run. |
| get_taskC | Read task status and paginated evidence. Completed is not independent test verification. |
| wait_taskC | Wait for task events or a terminal state, then return the same task view. |
| continue_taskB | Send review feedback to the same Harness session. Rejects concurrent execution. |
| cancel_taskB | Stop the owned worker tree. Check stopped_confirmed; edits are never rolled back. |
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 maps to a clearly distinct lifecycle action: start (submit_task), read (get_task), wait (wait_task), interact (continue_task), and stop (cancel_task). The descriptions clarify subtle differences such as immediate read versus waiting for events, and starting a new task versus continuing an existing session.
All five tool names follow a consistent snake_case verb_noun pattern: submit_task, get_task, wait_task, continue_task, cancel_task. There are no deviations or mixed conventions.
Five tools is well-scoped for a task harness, covering the essential lifecycle operations (start, monitor, wait, continue, cancel) without redundancy or missing core actions. Each tool earns its place.
The core task lifecycle is covered: submission, status retrieval, waiting, feedback continuation, and cancellation. However, there is no list_tasks operation to discover queued or running tasks, and no delete/archive operation, which are minor gaps that agents can work around if task IDs are known.