dsh-plugin-coaligne
Connects DeepSeek Harness agents to CoAligne's cloud project context. Provides MCP tools for searching synced files, managing comments, and creating review requests.
README
dsh-plugin-coaligne
Bring your team's shared https://www.coaligne.com project context into DeepSeek Harness.
CoAligne is a collaboration platform where teammates and their Agents share project context. CoAligne Desktop syncs local project files and Agent conversations into a cloud project; this plugin connects a DSH agent to that cloud context.
What you get
- CoAligne MCP tools (via the official
@deepseek-ai/dsh-mcp-client, streamable-http):list_projects,me,get_project_activity— project discovery and recent activitysearch— sandboxed read-only shell (grep,cat,find, …) over synced files and Agent session logsdownload_file,list_file_comments,reply_file_comment— file downloads and comment threadscreate_file_link,resolve_file_link,resolve_session_link— privateapp.coaligne.com/f/{code}andapp.coaligne.com/s/{code}locator linkslist_project_reviewers,create_review_request— send a file or Agent session to a teammate
coaligne-workflowskill, installed into your agents home (skills/under$DSH_AGENTS_HOME, default.agentsin your home directory): teaches the agent when and how to use those tools — collaboration queries, long-content search strategy, comment replies, sharing flows, and a single-project AI usage report.

Prerequisites
- A CoAligne account — sign up at https://www.coaligne.com.
- A CoAligne access token (
ca_...) from your account settings at https://app.coaligne.com. - To sync your own projects into the cloud: CoAligne Desktop, signed in, with your project imported.
Install
Install the package and list it in your DSH profile bundles (or use dsh-market):
npm install dsh-plugin-coaligne
The bundle patch (cordis.patch.yml) composes three rows into your profile:
| Row | Package | Purpose |
|---|---|---|
coaligne |
dsh-plugin-coaligne |
Installs the bundled coaligne-workflow skill into $DSH_AGENTS_HOME (default: .agents in your home directory) |
coaligne-invariant |
dsh-plugin-coaligne/invariant |
Package-owned invariant companion |
coaligne-mcp |
@deepseek-ai/dsh-mcp-client |
Streamable-HTTP MCP connection to https://app.coaligne.com/mcp |
Then set your token in the coaligne-mcp row:
headers:
Authorization: 'Bearer ca_your_token_here'
Configuration
The coaligne row accepts:
| Option | Default | Description |
|---|---|---|
installSkill |
true |
Install/refresh the bundled skill at activation |
agentsHome |
'' |
Override the agents home; empty resolves $DSH_AGENTS_HOME, then .agents in the home directory |
How it works
- The MCP connection is declarative: a config row for the host's own MCP client, no extra runtime code, tools appear as
mcp__coAligne__<tool>. - The skill install is an idempotent copy at plugin activation; disable it with
installSkill: falseif you manage skills yourself. - Your token only ever goes to
app.coaligne.comas a Bearer header on MCP requests.
Development
pnpm install
pnpm typecheck
pnpm test
pnpm build
License
BSD-3-Clause. Scaffolded from https://github.com/omdsh-dev/plugin-template.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.