Workforce Orchestrator MCP
by dotfrankruan
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WORKFORCE_DB | No | SQLite database path. | <root>/workers.db |
| OPENAI_API_KEY | No | Alternate OpenAI API key environment variable. | |
| WORKFORCE_ROOT | No | State root for worktrees, task workspaces, and database. | ~/.workforce/workers |
| WORKFORCE_CONFIG | No | Config file path; created on first start if absent. | ~/.workforce/config.json |
| ANTHROPIC_API_KEY | No | Alternate Anthropic API key environment variable. | |
| WORKFORCE_BACKEND | No | Backend selection: auto, dsh, opencode, openai, anthropic, or fake. | auto |
| WORKFORCE_OPENAI_API | No | OpenAI API mode: chat_completions or responses. | chat_completions |
| WORKFORCE_DSH_COMMAND | No | DeepSeek Harness executable path or command. | /usr/local/bin/dsh or PATH |
| WORKFORCE_DSH_PROFILE | No | DeepSeek Harness profile. | headless |
| WORKFORCE_MAX_TIMEOUT | No | Timeout ceiling in seconds. | 21600 |
| WORKFORCE_OPENAI_MODEL | No | OpenAI model. | gpt-4.1 |
| WORKFORCE_LOG_MAX_BYTES | No | Cap for get_worker_log output in bytes. | 32768 |
| WORKFORCE_OPENCODE_ARGS | No | Extra OpenCode CLI flags, space-separated. | |
| WORKFORCE_OPENCODE_AUTO | No | Whether to pass --auto to OpenCode. | true |
| WORKFORCE_DIFF_MAX_BYTES | No | Cap for full diff output in bytes. | 65536 |
| WORKFORCE_MAX_CONCURRENT | No | Maximum number of parallel tasks. | 4 |
| WORKFORCE_OPENAI_API_KEY | No | OpenAI API key. | |
| WORKFORCE_OPENCODE_AGENT | No | OpenCode agent name. | OpenCode default |
| WORKFORCE_OPENCODE_MODEL | No | OpenCode provider/model. | OpenCode default |
| WORKFORCE_ANTHROPIC_MODEL | No | Anthropic model. | claude-sonnet-4-5 |
| WORKFORCE_DEFAULT_BACKEND | No | Routing default backend; overrides WORKFORCE_BACKEND. | |
| WORKFORCE_DEFAULT_TIMEOUT | No | Default per-task timeout in seconds. | 3600 |
| WORKFORCE_OPENAI_BASE_URL | No | OpenAI API base URL. | https://api.openai.com/v1 |
| WORKFORCE_ENABLE_SUBAGENTS | No | Allow research/general subagent delegation. | false |
| WORKFORCE_OPENCODE_COMMAND | No | OpenCode executable path or command. | opencode |
| WORKFORCE_ANTHROPIC_API_KEY | No | Anthropic API key. | |
| WORKFORCE_ANTHROPIC_VERSION | No | Anthropic API version header. | 2023-06-01 |
| WORKFORCE_ANTHROPIC_BASE_URL | No | Anthropic API base URL. | https://api.anthropic.com |
| WORKFORCE_MAX_SUBAGENT_DEPTH | No | Subagent depth limit. | 1 |
| WORKFORCE_TERMINATE_GRACE_MS | No | Grace period between SIGTERM and SIGKILL in milliseconds. | 5000 |
| WORKFORCE_FINAL_TEXT_MAX_CHARS | No | Cap for final report text in characters. | 8000 |
| WORKFORCE_MAX_SUBAGENTS_PER_TASK | No | Subagent count limit per task. | 3 |
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 |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues