Connect Orvo to Claude Code

Add Orvo to Claude Code with one command and keep your relationship context next to your work: prep for a 1:1, log what was agreed, plan the follow-up, without leaving the terminal.

Sign in with Orvo or token Last verified 10 October 2026

Who this is for

Developers and technical leads who live in the terminal and want their stakeholder notes, open actions and people context available to Claude Code.

Before you start

  • Claude Code installed and signed in.
  • An Orvo account with web access (the free trial works).
  • Optional: a personal token from Orvo Settings → Integrations, only if browser sign-in doesn’t work.
https://www.getorvo.com/api/mcp

Your Orvo MCP server URL.

Fastest: paste a setup prompt into Claude Code

Claude Code can add Orvo to its own MCP configuration. Paste this prompt, then sign in with Orvo when your browser opens. No token needed.

  1. Copy the prompt below. It’s also in Orvo under Settings → Integrations when you choose Claude Code.
  2. Paste it into Claude Code’s chat and send it. Claude Code adds Orvo to its configuration. Approve its changes when it asks, and restart it if it tells you to.
  3. When your browser opens Orvo, sign in, choose Read only (recommended) or Read and make changes, and click Authorise & Connect. Adding notes, actions or other changes needs Read and make changes.
Setup prompt
Please connect Orvo, my personal CRM, to this app as a remote MCP server by adding it to your own MCP configuration.

- Server name: orvo
- URL: https://www.getorvo.com/api/mcp
- Transport: Streamable HTTP
- Authentication: OAuth sign-in through my browser. Orvo needs no API key or token, so do not add an Authorization header.

How to do it in Claude Code: run this command. User scope makes Orvo available in every project:
claude mcp add --transport http --scope user orvo https://www.getorvo.com/api/mcp
If orvo already exists, first remove it with: claude mcp remove orvo --scope user
Then run "claude mcp list" to check that orvo is there, and tell me to type /mcp in Claude Code, select orvo and choose to authenticate. My browser opens on Orvo. If orvo isn't listed in /mcp yet, tell me to restart Claude Code first.

Please also:
- Replace any existing server called orvo instead of adding a second one, and keep it in my own user-level settings, not in a project file.
- When the sign-in starts, tell me what happens next: my browser opens an Orvo page where I sign in and choose "Read only (recommended)" or "Read and make changes", then click "Authorise & Connect". Adding notes, actions or other changes needs "Read and make changes".
- After I have signed in, check the connection and list the Orvo tools you can see. If they only appear after a restart, tell me.

If sign-in doesn’t work: a setup prompt with a token

Use this only where Claude Code can’t sign in through a browser, for example on a remote machine.

The token is visible to the AI app. Pasting this prompt sends your token to Claude Code and its AI provider, and it stays in that chat’s history. Anyone with the token can read your Orvo data, and change it if Allow changes with this token is on. Generate a new token in Orvo Settings → Integrations at any time to revoke it.
  1. In Orvo, open Settings → Integrations, find AI assistants (MCP), choose Claude Code and open Use a token instead.
  2. Click Generate token, then Copy setup prompt with token. The token is shown once, and generating a new one turns off the old one.
  3. Paste the prompt into Claude Code’s chat and send it.
Setup prompt with token (preview)
Please connect Orvo, my personal CRM, to this app as a remote MCP server by adding it to your own MCP configuration.

- Server name: orvo
- URL: https://www.getorvo.com/api/mcp
- Transport: Streamable HTTP
- Authentication: send the header "Authorization: Bearer YOUR_ORVO_TOKEN"

How to do it in Claude Code: run this command. User scope makes Orvo available in every project and keeps the token out of project .mcp.json files:
claude mcp add --transport http --scope user orvo https://www.getorvo.com/api/mcp --header "Authorization: Bearer YOUR_ORVO_TOKEN"
If orvo already exists, first remove it with: claude mcp remove orvo --scope user
Then run "claude mcp list" and check that orvo shows as connected.

Please also:
- Replace any existing server called orvo instead of adding a second one.
- Keep the token in my own user-level settings only, never in a project file, a repository or anything that is shared. Do not repeat the token in your replies.
- When you are done, check the connection and list the Orvo tools you can see. If they only appear after a restart, tell me.
- The token may be read-only. If Orvo refuses a change later, tell me to switch on "Allow changes with this token" in Orvo under Settings > Integrations (https://www.getorvo.com/setting?tab=integrations).
Orvo Settings fills in your token for you. If you copy this preview instead, replace YOUR_ORVO_TOKEN with your token. New tokens are read-only until you switch on Allow changes with this token.

Set it up by hand: sign in with Orvo

  1. Add the server. --scope user makes Orvo available in all your projects instead of only the current one:
    Terminal
    claude mcp add --transport http --scope user orvo https://www.getorvo.com/api/mcp
  2. Start Claude Code and type /mcp. Select orvo and choose to authenticate; your browser opens on Orvo.
  3. Sign in to Orvo if asked, choose Read only (recommended) or Read and make changes, and click Authorise & Connect. Claude Code stores and refreshes the sign-in for you.
  4. Check the connection with claude mcp list, then ask Claude Code something about your network.
Already connected Orvo on claude.ai? When you log in to Claude Code with the same Claude subscription, connectors from claude.ai can show up in Claude Code too, so you may not need to add it again.

Set it up by hand with a token

Also useful for scripts or machines where a browser sign-in isn’t possible.

  1. In Orvo, open Settings → Integrations, find AI assistants (MCP), choose Claude Code and click Generate token. Copy it right away; it’s shown once.
  2. Add the server with the token as a header:
    Terminal
    claude mcp add --transport http --scope user orvo https://www.getorvo.com/api/mcp --header "Authorization: Bearer YOUR_ORVO_TOKEN"
  3. Or, for a project-scoped .mcp.json, keep the token in an environment variable so it never lands in version control:
    .mcp.json
    {
      "mcpServers": {
        "orvo": {
          "type": "http",
          "url": "https://www.getorvo.com/api/mcp",
          "headers": {
            "Authorization": "Bearer ${ORVO_MCP_TOKEN}"
          }
        }
      }
    }
Treat the token like a password. New tokens are read-only; switch on Allow changes with this token in Orvo Settings → Integrations if you want Claude Code to make changes.

Read only, or read and make changes

With browser sign-in you pick Read only (recommended) or Read and make changes on Orvo’s page. To switch, run /mcp, clear the authentication for orvo, and sign in again.

With a token, the Allow changes with this token switch in Orvo Settings → Integrations decides. Claude Code’s own permission prompts still ask before tools run unless you allow them.

Either way, deleting never erases anything: People and notes go to Recently deleted for 30 days, daily limits cap how much an assistant can change, and changes to a person (their profile, tags, notes and linked actions) show in their activity as made via AI assistant. How Orvo keeps you in control.

Things to ask Claude Code

Before my 1:1 with Priya, summarise our last notes and her open actions. Works read-only
Who on the platform team haven’t I spoken to in six weeks? Works read-only
Search my notes for anything about the billing migration and who raised it. Works read-only
Add a note to Tom: reviewed the API proposal, he wants a demo on Friday. Needs read and make changes
Create an action due Thursday: send Priya the RFC. Needs read and make changes
Alex now reports to Jordan. Update my Network Map. Needs read and make changes

Troubleshooting

The browser doesn’t open during sign-in
Copy the sign-in URL Claude Code shows into your browser. If the redirect back fails, paste the full callback URL into the prompt as Claude Code asks.
${ORVO_MCP_TOKEN} shows up unexpanded
Export the variable in the shell that starts Claude Code. Use your own variable name; Claude Code deliberately leaves some credential variables (like Anthropic API keys) empty in remote server headers.
The project server isn’t loading
Claude Code asks you to approve servers from a project’s .mcp.json. If you declined, run claude mcp reset-project-choices and start again.
The sign-in page asks me to log in to Orvo first
That’s expected. Sign in with your Orvo account in that browser window and you’ll land on the Connect … to Orvo page. Pick an access level and click Authorise & Connect.
I chose the wrong access level
Disconnect Orvo in your assistant (or sign out of the connector) and connect again. The Orvo sign-in page appears again and you can pick the other option.
“Invalid or expired token” (HTTP 401)
Each Orvo account has one personal token, and generating a new one cancels the old one. If you regenerated it for another app, put the new token into every app that uses it.
The assistant says the connection is read-only
In Orvo, open Settings → Integrations, find AI assistants (MCP), choose your assistant, open Use a token instead and switch on Allow changes with this token. The change applies on the next request.
Orvo refuses every request although I signed in
Check that your Orvo account is active (trial not expired, subscription current) and that it has web access. The mobile-only plan doesn’t include MCP connections.
“Too many requests” or a daily limit message
Orvo allows about 60 MCP requests a minute per account, so wait a minute and try again. Daily limits on changes reset at midnight UTC.

Official documentation

Menus and plans change. If a step above doesn't match what you see, Anthropic's own documentation is the source of truth:

Steps last checked against these pages on 10 October 2026. Claude Code is a product of Anthropic; Orvo is not affiliated with Anthropic.

Claude Code and Orvo: FAQ

Should I use browser sign-in or a token with Claude Code?

Browser sign-in. The setup prompt sets it up in one paste, no token ends up in your chat or on your computer, it refreshes itself, and you pick read only or read and make changes on Orvo’s page. Use a token only where a browser isn’t available, and remember that a token pasted into a chat is visible to the AI app.

Which scope should I use?

User scope (--scope user) for a personal CRM, so Orvo is available in every project and never ends up in a shared repository.

Can the assistant read my emails or calendar through Orvo?

No. The Orvo MCP server works with your People, notes, actions, opportunities, tags, groups and relationship insights. Synced emails and calendar events are not exposed, and it can’t send messages.

What happens to things the assistant deletes?

They go to Recently deleted in Orvo, with their notes and actions, and can be restored for 30 days. Deleting is only possible on a connection you set to “Read and make changes”.

Related guides

All AI assistants

Try Orvo with Claude Code — free for 14 days

No credit card required. Your assistant connects read-only until you say otherwise.