Exposes DeepSeek Harness tools to any MCP-compatible client over streamable HTTP, allowing allowlisted operations such as file read, glob, grep, and web search while preserving the harness's sandbox and approval pipeline.
Exposes a DeepSeek Harness instance — either the whole runtime or one session chosen in the UI — as an MCP Streamable HTTP endpoint on the Harness Web server's origin. Lets other MCP-speaking agents such as Codex or Claude Code delegate tasks, list and read session transcripts, and cancel or inspect running turns using the Harness's own model, tools, workspace and sandbox policy.
Lets any MCP-capable coding harness (Cursor, Claude Code, Codex, Gemini CLI, VS Code/Copilot, opencode, and others) hand a self-contained task to a real, isolated DeepSeek Harness process that works in a chosen workspace with its own context window, model, and toolchain, then returns the final answer. Exposes task submission with time estimates and acceptance criteria, status polling with live progress and process-tree telemetry, graceful cancel and forced kill of whole process trees, and a health probe reporting concurrency, deadlines, and recent jobs.
Exposes a local loopback MCP endpoint that lets Codex spawn, wait on, follow up with, and close DeepSeek Harness sessions as workers and read back their final answers, while letting DSH agents dispatch work back to Codex in return. Includes delegation-depth and rate-limit guardrails, per-working-directory worker quotas, and persisted worker state that survives restarts.
Enables MCP clients to hand tasks to DeepSeek Harness as an execution subagent, creating sessions, submitting work, waiting for results, and retrieving outputs.
Enables MCP clients like Codex CLI and Claude Code to delegate tasks to a local DeepSeek Harness (dsh), with native Web transport for visible progress, model selection, and persistent long-running jobs, plus an ACP-compatible transport.
