Duvo

Hosted MCP server for Duvo — start runs, inspect approvals, and expose grocery/retail execution tools to compatible agents.

View on duvo.ai

Documentation

Connect to the Duvo MCP server

Connect Claude, Cursor, or ChatGPT to the Duvo MCP server. Every Public API endpoint becomes an LLM-callable tool.

Connecting an MCP host to the Duvo MCP server is the main way teams use MCP with Duvo — it's the conversational counterpart to the Duvo CLI.

Duvo exposes a hosted MCP server at https://api.duvo.ai/v2/mcp. Connect to it from any MCP-compatible host — Claude, Cursor, ChatGPT connectors, your own client — and every Duvo Public API endpoint becomes a tool the host can call.

[!TIP]

Using Claude? Duvo is listed in Claude's connector directory, so you don't need the server URL. Open Customize → Connectors, select the Discover tab, search for Duvo, and click Connect. See Setup by host.

Use this to:

  • Drive Duvo Agents from an AI assistant chat ("Start the invoice processor on yesterday's batch and tell me when it's done.")
  • Inspect Runs, Cases, and Files conversationally
  • Build hybrid workflows where one assistant orchestrates Duvo Agents alongside other tools

What you can do

Every endpoint registered in the Public API is auto-exposed as an MCP tool. That includes:

  • Agents — list, get, create, update
  • Runs — start, get status, send messages, respond to human-in-the-loop requests, stop
  • Connections — list and inspect your authorized accounts
  • Files — list, read, write, rename, delete
  • Cases and Queues — inspect, delegate, label
  • Clarity — create a process, invite people to interviews, see who has done theirs, and read the process summaries
  • Skills, Plugins, Sandboxes — list and reference

See the full list of available tools on the Available MCP Tools page.

When Duvo ships a new Public API endpoint, it automatically becomes an MCP tool on the next deploy. There's no separate maintenance step.

Server URL

https://api.duvo.ai/v2/mcp

The server uses MCP's Streamable HTTP transport (POST /v2/mcp). Most modern MCP hosts support this transport out of the box.

[!NOTE]

The earlier https://api.duvo.ai/v1/mcp endpoint still works and serves the same tools as /v2/mcp, so existing setups keep running unchanged — including after the /v1 API sunset. New connections should use /v2/mcp.

Authentication

The Duvo MCP server accepts two credential types:

Option 1 — OAuth (recommended for personal use)

Recommended for hosts that prompt you to sign in (Claude, Cursor, ChatGPT connectors). The host runs a one-time browser-based sign-in to Duvo, then handles token refresh and revocation for you. No API key to copy or rotate.

The exact steps depend on the host. In general:

1. Add the server URL

Add https://api.duvo.ai/v2/mcp as the MCP server URL in your host's settings. In Claude, skip this step: connect Duvo from the connector directory instead.

2. Trigger the OAuth challenge

The host detects the OAuth challenge and opens a browser tab to Duvo's sign-in page.

3. Sign in and approve

Sign in and approve the connection.

4. Tokens stored automatically

The host stores the OAuth tokens and uses them automatically on every tool call.

Duvo's MCP server publishes its OAuth metadata at https://api.duvo.ai/.well-known/oauth-protected-resource/v2/mcp (RFC 9728). Compliant MCP hosts use this to discover the authorization server and register themselves via Dynamic Client Registration automatically.

Option 2 — API key (recommended for scripts and service accounts)

Use API keys when the host doesn't support OAuth, or for non-interactive use (CI, service accounts).

1. Generate an API key

Generate a key in the Duvo dashboard at Your Profile → API keys, scoped to a single team or to all teams you can access. Users with the Manager role or above can also create keys that work only in one team at Team Settings → API keys.

2. Send the key as a bearer token

Configure the MCP host to send the key as a bearer token in the Authorization header:

Authorization: Bearer <your-api-key>

3. Call tools

The host can then call Duvo MCP tools without any further sign-in.

API keys are scoped to a single team or to all teams the owner can access. A key acts as the user who created it: it has their permissions and can use their personal Connections, Logins and Secrets.

Setup by host

In Claude, connect Duvo from the connector directory. Every other compliant host uses the same Duvo URL. Configuration syntax differs slightly between products, so check your host's MCP setup guide for the exact field names. Common patterns:

[tab] Claude

Duvo is an official connector in Claude's connector directory (see the Duvo listing), so there's no URL to paste. The steps are the same on claude.ai and in the Claude desktop app.

1. Open Connectors

In Claude, open Customize → Connectors.

2. Open the directory

Select the Discover tab.

3. Find Duvo

Search for Duvo.

4. Connect

Click Connect.

5. Sign in to Duvo

Sign in with your Duvo account in the browser tab that opens. Claude then uses the connection whenever it calls a Duvo tool.

[!NOTE]

On Team and Enterprise plans, an Owner or Primary Owner must first enable the Duvo connector for your organization under Organization settings → Connectors. Each person then connects and signs in to Duvo individually.

Need a manual setup instead? You can still add a custom connector with the URL https://api.duvo.ai/v2/mcp.

[tab] Claude Code

Add the Duvo server from your terminal with the claude mcp add command:

claude mcp add --transport http duvo https://api.duvo.ai/v2/mcp

The first time you call a Duvo tool, Claude Code runs the browser-based OAuth sign-in. To use an API key instead (for CI or service accounts), pass it as a bearer header:

claude mcp add --transport http duvo https://api.duvo.ai/v2/mcp \
  --header "Authorization: Bearer <your-api-key>"

[tab] Cursor

In Cursor settings, open the MCP servers section, add a new server with the URL https://api.duvo.ai/v2/mcp, and let Cursor run the OAuth flow.

[tab] ChatGPT (Custom Connector)

Add a Custom Connector pointing to https://api.duvo.ai/v2/mcp. ChatGPT handles Dynamic Client Registration and the OAuth flow automatically.

[tab] Custom MCP host or script

Any MCP-compatible client library (TypeScript, Python, etc.) can connect — point it at https://api.duvo.ai/v2/mcp, supply either an OAuth token or an API key, and call tools/list to discover what's available.

Tool ergonomics

Tools follow the underlying Public API:

  • Tool names map to OpenAPI operationIds (for example, listAgents, startRun, getConnection).
  • Tool descriptions come from each endpoint's OpenAPI description.
  • Input schemas are flat — path parameters, query parameters, and request body are merged into a single object so calls read naturally (startRun({ agent_id: "...", input: "..." }) rather than wrapping each section).
  • Responses match the corresponding API response. Use the Public API Reference for the exact shapes.
  • Every tool carries MCP annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint), so hosts can tell a read from a write and know which tools reach outside Duvo — for example startRun, probeMcpServer, or the OAuth start tools.
  • Not-found errors name the id parameter that failed and echo the value you sent (for example case_queue_id), so a call that takes several ids tells you which one to check.

Built-in skills

The server also ships Duvo's Agent Skills as MCP resources, so your host has the same guidance without installing anything. Each skill is a markdown file under duvo://skills/:

ResourceUse it to
duvo://skills/aop-writer/SKILL.mdDraft, rewrite, or critique an Agent's AOP
duvo://skills/run-debugger/SKILL.mdFind out why a Run failed or produced the wrong outcome
duvo://skills/workflow-debugger/SKILL.mdAudit an Agent or a Queue-connected workflow across many Runs
duvo://skills/improve-agent/SKILL.mdTake one Agent from where it is to an applied improvement
duvo://skills/improve-queue/SKILL.mdDo the same for a Queue and the producer/consumer workflow around it
duvo://skills/connection-doctor/SKILL.mdDiagnose the Connections and Logins an Agent relies on
duvo://skills/clarity-mapping/SKILL.mdMap how a process works with Clarity, from interviews to analysis
duvo://skills/operate-module/SKILL.mdAnswer questions about a running Module and change it safely, as Ask Duvo does

The server's instructions tell the host when to read each skill, and reference files sit next to each SKILL.md under references/. Hosts that surface MCP resources (Claude Desktop, Claude Code, Cursor) list them automatically.

[!NOTE]

The skills are the same content as the public duvoai/skills repository, which you can still install locally to use with the Duvo CLI.

Limits and behavior

  • All Public API rate limits apply to MCP tool calls.
  • Every tool call respects the permissions of the authenticating user, just like a direct API call.
  • Long-running Runs are not streamed over MCP today — start the Run via the tool, then poll getRun or listRunMessages to monitor progress.

Troubleshooting

[!WARNING]

401 Unauthorized — Your token is missing, expired, or for a different audience. Re-run OAuth, or regenerate the API key in the dashboard.

[!WARNING]

403 Forbidden — Your account doesn't have permission to call this endpoint. Check your team role and Connection permissions.

[!WARNING]

OAuth doesn't open a browser — The host may not support Dynamic Client Registration. Fall back to API key authentication, or check the host's docs for OAuth setup steps.

Privacy and terms

  • Privacy Policy — how Duvo handles data accessed through the MCP server.
  • Terms of Use — the terms that apply to Duvo API and MCP usage.

For platform-wide details (SOC 2 certification, encryption, Anthropic Zero Data Retention, sub-processors), see Security & Privacy.

Related

[card] Available MCP Tools

The full catalog of tools this server exposes.

[card] Connect a custom MCP to Duvo

The other direction: bring your own MCP server into Duvo.

[card] Public API Reference

The API the Duvo MCP server wraps.

[card] Duvo CLI

Terminal-first wrapper over the same API.

This documentation is built and hosted on Mintlify, a developer documentation platform.