Connect
AnythingLLM
AnythingLLM's agent-skills framework accepts MCP servers. Add Dock as a skill and every workspace inside AnythingLLM can call its tools.
Client
AnythingLLM
Desktop + self-hosted RAG UI. MCP via Agent Skills panel.
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
- AnythingLLM installed (desktop or Docker).
- A Dock
dk_key.
UI path
Settings · Agent Skills · MCP Servers · Add
Server entryjson
{
"name": "dock",
"type": "http",
"url": "https://trydock.ai/api/mcp",
"headers": {
"Authorization": "Bearer dk_c914f1c6..."
}
}Troubleshooting
Symptom
Fix
Agent can't invoke tools
Enable the agent-mode toggle on the AnythingLLM workspace. MCP skills only fire when the workspace is in agent mode.
Frequently asked questions
- How do I connect Dock to AnythingLLM?
- Add Dock as a remote MCP server in AnythingLLM. Either let AnythingLLM's OAuth 2.1 + DCR flow handle auth (recommended; no credential ceremony), or paste a scoped Dock `dk_` API key in AnythingLLM's MCP config under the `Authorization: Bearer dk_…` header.
- Does AnythingLLM 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 AnythingLLM, discovers them via the standard `tools/list` handshake. Learn more →
- How do I limit which Dock workspaces AnythingLLM can write to?
- When you mint the `dk_` key for AnythingLLM 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 AnythingLLM did in my Dock workspace?
- Open the workspace in your browser. Every row AnythingLLM 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 AnythingLLM 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 AnythingLLM's `dk_` key in Settings → API keys.
- Can multiple AnythingLLM sessions share state through Dock?
- Yes. Every AnythingLLM 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 AnythingLLM need OAuth or a dk_ API key for Dock?
- Either works. OAuth 2.1 + DCR is the recommended path: AnythingLLM 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 AnythingLLM?
- AnythingLLM 1.6+ has MCP plugin support. Settings → Tools → MCP Servers → Add. Set URL to `https://trydock.ai/api/mcp` and paste your `dk_` Bearer. The 43 Dock tools surface in your AnythingLLM workspace.
- Can AnythingLLM agents write to a Dock workspace?
- Yes, once Dock's MCP server is added. Configure your AnythingLLM agent skill to call `create_row` or `append_doc_section`; the agent can then maintain a Dock workspace as durable state across conversations.
- How is Dock different from AnythingLLM's built-in workspaces?
- AnythingLLM workspaces are LLM-context containers (which docs the model can see). Dock workspaces are SHARED state your team and your agents read+write together with attribution. Use both: AnythingLLM for retrieval, Dock for the team-visible artifacts the agent produces.