Click on "Deploy 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., "@Dock list rows from my marketing workspace"
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.
Local stdio bridge to the Dock MCP server. Point any MCP-capable agent (Claude Desktop, Cursor, Windsurf, Zed, Cline, Continue) at your Dock workspaces in one config change.
Do you need this package?
If your agent supports remote MCP connectors (Claude.ai web, Claude.ai Projects), you don't need this — add
https://trydock.ai/api/mcpas a custom connector and follow the OAuth flow. See the MCP reference.This package is for agents that only speak local stdio MCP — the dominant pattern for Claude Desktop and most code-editor agents today.
Get an API key in Dock's Settings → API keys (trydock.ai).
Add the config for your agent below.
Restart the agent. You'll see Dock's 8 tools appear.
Related MCP server: knowledgeops-ai
All clients follow the same pattern: run npx -y @trydock/mcp, pass
DOCK_API_KEY in env. Per-client JSON snippets are in
configs/:
Client | File | Typical config path |
Claude Desktop |
| |
Cursor |
| |
Windsurf |
| |
Zed |
| |
Cline (VS Code) | VS Code settings → | |
Continue |
|
Example (Claude Desktop):
{
"mcpServers": {
"dock": {
"command": "npx",
"args": ["-y", "@trydock/mcp"],
"env": {
"DOCK_API_KEY": "dk_..."
}
}
}
}All 8 tools are forwarded to the hosted Dock server. JSON schemas live
in schemas/.
Tool | Purpose |
Enumerate workspaces you can access | |
Fetch a workspace by slug | |
Read rows from a table-mode workspace | |
Append a row | |
Partial-merge update | |
Remove a row | |
Create a new workspace | |
Read the activity log |
Full reference with examples: trydock.ai/docs/mcp.
The bridge is a ~100-line Node process (src/bridge.js).
Every JSON-RPC message your agent writes on stdin is forwarded over HTTPS
to https://trydock.ai/api/mcp with your DOCK_API_KEY as Bearer auth.
The hosted server owns authentication, rate limits, audit, and tool
execution. The bridge stores no state and logs no request bodies.
Environment variables:
Variable | Required? | Purpose |
| yes | Bearer token (get one from Settings → API keys) |
| no | Override the upstream endpoint (staging / self-host). Default: |
Your API key is only held in the agent's environment and passed on each HTTPS call. It's never logged, never written to disk by this bridge.
Rotate keys any time in Dock's Settings → API keys. Old keys return 401 immediately on revocation.
Keys are stored as SHA-256 hashes on Dock's side, not plaintext. A Dock DB leak wouldn't expose usable credentials.
See the full security doc for the threat model, the revocation runbook, and what data is audited.
MIT. Copyright © 2026 Vector Apps, Inc.
This server cannot be deployed
Workspace knowledge bases agents ingest, search, and query over MCP.
Agent-complete, permission-scoped product operations for Priorify workspaces.
Let AI agents query data and act across all your business apps via MCP.
Work with shared spaces, threads, documents, skills, apps, automations, and connected tools.
