Get startedCLIAPIMCPWebDesktopAgentsSupportBillingChangelog
Connect
agno logo

Agno

Agno (formerly Phidata) ships a clean MCP toolkit. Wire Dock in and any Agno agent can read and write Dock workspaces as part of its workflow.

Client
Agno
Ex-Phidata. Multi-agent framework with MCP support.
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

  • Python 3.10+.
  • agno installed.
  • A Dock dk_ key.
agent.pypython
import os
from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.mcp import MCPTools

dock = MCPTools(
    url="https://trydock.ai/api/mcp",
    transport="streamable-http",
    headers={"Authorization": f"Bearer {os.environ['DOCK_API_KEY']}"},
)

async with dock:
    agent = Agent(
        # Agno supports Claude(), OpenAIChat(), Gemini(), and more.
        model=model,
        tools=[dock],
    )
    agent.print_response("List my Dock workspaces.")

Troubleshooting

Symptom
Fix
Import error agno.tools.mcp
Upgrade: pip install --upgrade agno. MCP support landed in Agno 1.2+.

Frequently asked questions

How do I connect Dock to Agno?
Add Dock as a remote MCP server in Agno. Either let Agno's OAuth 2.1 + DCR flow handle auth (recommended; no credential ceremony), or paste a scoped Dock `dk_` API key in Agno's MCP config under the `Authorization: Bearer dk_…` header.
Does Agno 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 Agno, discovers them via the standard `tools/list` handshake. Learn more →
How do I limit which Dock workspaces Agno can write to?
When you mint the `dk_` key for Agno 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 Agno did in my Dock workspace?
Open the workspace in your browser. Every row Agno 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 Agno 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 Agno's `dk_` key in Settings → API keys.
Can multiple Agno sessions share state through Dock?
Yes. Every Agno 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 Agno need OAuth or a dk_ API key for Dock?
Either works. OAuth 2.1 + DCR is the recommended path: Agno 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 use Dock with Agno?
Agno supports MCP servers via the `MCPServerHTTP` adapter. Configure with `https://trydock.ai/api/mcp` and your `dk_` Bearer header; pass to your Agno Agent's tool list.
Can multiple Agno agents collaborate via a shared Dock workspace?
Yes. Each Agno agent authenticates with its own `dk_` key (one per agent for clean attribution). Real-time SSE means each agent sees the others' writes within ~400ms.
Does Agno's Team mode work with Dock's principal attribution?
Yes. Mint one `dk_` per team member (Researcher, Coder, Reviewer). Each writes attribute correctly to its agent identity in Dock; you can see the team's work split by agent in the activity feed.

Related

Updated