Get startedCLIAPIMCPWebDesktopAgentsSupportBillingChangelog
Connect
jetbrains-ai logo

JetBrains AI Assistant

JetBrains IDEs with the AI Assistant plugin support remote MCP servers as of the 2025.3 release. Add Dock once in any JetBrains IDE and it's available in IntelliJ, PyCharm, WebStorm, and the rest.

Client
JetBrains AI Assistant
IntelliJ, PyCharm, WebStorm. MCP via plugin settings.
HTTP JSON-RPC (streamable-http)
Dock MCP
trydock.ai/api/mcp
37 tools · OAuth 2.1 + DCR · Bearer
Auth path
1
Mint a dk_ key in Dock Settings → API keys.
2
Paste it as Authorization: Bearer dk_… in the client config.
3
Client calls Dock MCP directly on every request.

Prerequisites

  • JetBrains IDE 2025.3+ with AI Assistant enabled.
  • A Dock dk_ key.
UI path
Settings · Tools · AI Assistant · MCP Servers · Add
Config file (if editing directly)
~/Library/Application Support/JetBrains/<IDE>/options/ai-assistant-mcp.xml
UI form valuesjson
Name:   dock
URL:    https://trydock.ai/api/mcp
Headers:
  Authorization: Bearer dk_c914f1c6...

Verify

In AI Assistant chattext
List my Dock workspaces.

Troubleshooting

Symptom
Fix
MCP panel says "capability not available"
Upgrade the AI Assistant plugin to the latest build. MCP shipped mid-2025.

Frequently asked questions

How do I connect Dock to JetBrains AI Assistant?
Add Dock as a remote MCP server in JetBrains AI Assistant. Either let JetBrains AI Assistant's OAuth 2.1 + DCR flow handle auth (recommended; no credential ceremony), or paste a scoped Dock `dk_` API key in JetBrains AI Assistant's MCP config under the `Authorization: Bearer dk_…` header.
Does JetBrains AI Assistant work with Dock's MCP server?
Yes. Dock exposes 43 MCP tools at `https://trydock.ai/api/mcp` over HTTP transport with OAuth 2.1 + DCR and Bearer-token auth. Any MCP-spec-compliant client, including JetBrains AI Assistant, discovers them via the standard `tools/list` handshake. Learn more →
How do I limit which Dock workspaces JetBrains AI Assistant can write to?
When you mint the `dk_` key for JetBrains AI Assistant in Settings → API keys, pick the workspace from the dropdown. The key returns 403 on every other workspace regardless of what the prompt asks. To scope across multiple, mint multiple keys or add the agent as an explicit member of each. Learn more →
How do I see what JetBrains AI Assistant did in my Dock workspace?
Open the workspace in your browser. Every row JetBrains AI Assistant created or updated is stamped with the agent's identity (orb + name) in the createdBy / updatedBy field. The workspace activity feed shows every action chronologically. Learn more →
How do I undo a row JetBrains AI Assistant wrote to Dock?
Open the row, click the kebab menu, choose Delete (soft-delete preserves history). For bulk reverts use the activity feed to find the agent's session and delete its rows in batch. To prevent future writes, revoke JetBrains AI Assistant's `dk_` key in Settings → API keys.
Can multiple JetBrains AI Assistant sessions share state through Dock?
Yes. Every JetBrains AI Assistant session reads and writes the same workspace, so handoffs across machines or across long-running multi-session workflows just work. The Dock workspace IS the shared state; no separate message bus required.
Does JetBrains AI Assistant need OAuth or a dk_ API key for Dock?
Either works. OAuth 2.1 + DCR is the recommended path: JetBrains AI Assistant hits Dock's discovery endpoint at `/.well-known/oauth-authorization-server` and auto-registers as a client. The `dk_` Bearer token path is fine for owned-code agents and CI scripts; pick whichever fits your stack. Learn more →
How do I add Dock as an MCP server in JetBrains AI Assistant?
JetBrains AI Assistant's MCP support is plugin-based. Install the MCP plugin, then under Settings → Tools → AI Assistant → MCP Servers, add Dock with URL + Bearer. Restart the IDE.
Can JetBrains AI Assistant call Dock tools across IntelliJ, PyCharm, and WebStorm?
Yes, the same MCP config works across all JetBrains IDEs. Add Dock once; every JetBrains IDE you sign into with that account picks up the same MCP servers.
How do I let JetBrains AI Assistant write to a per-project Dock workspace?
Mint a per-project `dk_` key in Dock (one per repo, scoped to the matching workspace). Set `DOCK_API_KEY` in your IDE's run configurations per project. JetBrains AI then writes to the correct Dock workspace per repo.

Related

Updated