dsh-harness-mcp-server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dsh-harness-mcp-serverRefactor the payment module to use the new API and run tests"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
dsh-harness-mcp-server
Expose DeepSeek Harness agent capabilities as an MCP server, letting any MCP client (e.g. Hermes) drive Harness to execute real coding tasks.
Hermes is the brain (pro), Harness is the arms (flash) — 1+1>2.
Why this exists
Harness ships a powerful agent runtime (tools, LLM, agents, sessions), but it is a Cordis app, not something another agent can call. This plugin turns Harness inside-out: it starts a real MCP server (StreamableHTTP) inside Harness and bridges Harness's core services — ctx.agents, ctx.agentPresets, ctx.tools — so an external "brain" can delegate real work to Harness's "arms".
Hermes (MCP client, brain)
│ agent_run / task_inbox (HTTP)
▼
dsh-harness-mcp-server (MCP server, :8090)
│ ctx.agents.create → mount 'standard' preset
▼
Harness agent (flash) — full toolset: bash, fs, todo, web…Related MCP server: local-skills-mcp
Tools
Tool | Direction | Purpose |
| — | Verify MCP connectivity |
| — | List Harness's registered tool names |
| Hermes → Harness | Run a task synchronously and return a structured result |
| Hermes → Harness | Push a structured task (task + memory context + cwd) to an async queue |
| Hermes ← Harness | Poll a queued task's structured result |
Every task result is structured:
{
"sessionId": "...",
"assistantText": "final answer",
"toolCalls": [{ "name": "bash", "args": "..." }],
"toolResults": ["command output"],
"changes": "what was changed",
"verification": "how it was verified",
"leftovers": "open issues"
}This closes the loop between the client's persistent memory and Harness's coding: memory is fed into each task as context, and the result (changes / verification / leftovers) can be persisted back to the client's memory for the next run.
Install
Option A — from npm (recommended)
npm install @chushixixin/dsh-harness-mcp-serverThen reference the plugin from your Harness workspace (see the cordis patch below).
Option B — from source
Clone this repo inside your Harness workspace under packages/mcp/harness-mcp-server/ (the pnpm workspace matches packages/*/*, two levels deep):
cd /path/to/deepseek-harness
mkdir -p packages/mcp/harness-mcp-server
# copy this repo's files there, then:
corepack pnpm installRegister it in tsconfig.host.json references and tsconfig.base.json paths (see the Harness plugin docs), then build:
corepack pnpm exec tsc -b packages/mcp/harness-mcp-server
corepack pnpm run build:lib:hostRun
export DEEPSEEK_API_KEY=...
corepack pnpm dsh web --patch ./packages/mcp/harness-mcp-server/cordis.ymlThe MCP server listens on 0.0.0.0:8090 (StreamableHTTP). Point any MCP client at http://127.0.0.1:8090/mcp.
Hermes client config
printf 'n\nY\n' | hermes mcp add harness_plugin --url http://127.0.0.1:8090/mcpcordis.yml (patch format)
- insert:
- id: harness-mcp-server
name: '@chushixixin/dsh-harness-mcp-server'
config: { http: true, port: 8090, host: 0.0.0.0 }Positioning
This is best used as a fallback tool, not a daily driver: for everyday code edits, drive your primary agent directly. Reach for this when you need context isolation (huge refactors that would blow the client's context) or parallel execution of unrelated tasks.
The agent session is reused per cwd (avoids re-loading project context on every call — roughly 15–20× cheaper than one-shot
dsh headless).Bash runs sandboxed (
workspace-write): installbubblewrapon the host, or the sandbox will refuse write commands.Each new MCP session gets its own
McpServer+ transport (an MCPMcpServerconnects to a single transport).
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
AlicenseAqualityAmaintenanceMCP server that gives AI coding agents direct access to evaluation tools.22Apache 2.0- AlicenseAqualityCmaintenanceA universal MCP server that enables any LLM or AI agent to access expert skills from your local filesystem.34234MIT
- AlicenseAqualityFmaintenanceMCP server for running external coding agents as background tasks inside Claude Code. Supports multiple backends including Codex, Grok, GLM, DeepSeek, and more.7MIT
- AlicenseAqualityAmaintenanceA local MCP server that delegates coding tasks to a temporary OpenCode session and returns a completion report with changed files, tool calls, cost, and the subagent's reply.157561MIT
Related MCP Connectors
MCP server exposing the Backtest360 engine API as tools for AI agents.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
ArcAgent MCP server for bounty discovery, workspace execution, and verified coding submissions.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/chushixixin/dsh-harness-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server