Ask it to install the Fulcra CLI on its cloud computer, approve the connection, and start with a simple read-only check. You handle sign-in. Your dot handles the setup.
Connect to my Fulcra account using the Fulcra CLI on your cloud computer.
Install the official fulcra-api Python package from PyPI in an isolated environment, following https://docs.fulcradynamics.com/cli/. Check the installed CLI help before choosing commands.
I authorize saving the Fulcra login credentials on your cloud computer for continued use with my account. Explain where they will be stored and let me personally approve the connection on Fulcra's sign-in page. Don't ask me to paste a password, access token, or refresh token into chat.
Use the CLI's two-step device login. Send me the official sign-in link and its verification code, keep the device code private, and start polling for completion while I sign in. Tell me you're polling so I don't need to send a separate “done” message.
After authorization succeeds, run user-info to verify the account connection. Confirm success without exposing credentials or unnecessary account details. Stop after this read-only check; don't upload files or create, change, or delete Fulcra records as part of setup.
If installation, credential storage, or authentication is blocked, explain the specific blocker and the smallest next step.Ready to connect? Copy the prompt above and send it to your dot.
Your dot checks its cloud computer and installs Fulcra's official Python package. Nothing needs to be installed on your laptop for this route.
Your dot sends a sign-in link and a short verification code. Open the link, check that the code matches, and complete Fulcra's sign-in and authorization steps yourself. Your dot can wait for the approval in the background. Keep passwords and account recovery details on the sign-in page.
Your dot can see and add to your data, connect with the other agents in your life, and the agents in your friends' and coworkers' lives.
They don't know what changed since your last conversation, and they can't build on what another agent learned.
Scattered across apps. What each agent learns stays trapped inside one app, one agent, or one model provider. Each system keeps its fragment separate.
Updates you can't see or steer. What an agent knows about you changes without you. You don't see when, or why, it updates.
Start over with every switch. Every agent keeps its own private record of you. Switch tools, and the relationship starts over.
Fulcra brings real-world data, recorded knowledge, files, and agent work into one context you own — and your agents connect to it.
One context, every agent. Instead of every agent building its own private record of who you are, your agents read from and write to one context you control.
Readable and controllable. Agents read from it, contribute to it, and learn from it. You can see what they know, trace how they learned it, and revoke access whenever you want.
It travels with you. Carry your context across AI products. Change agents, change models — and never have to start over.
The Fulcra CLI can discover data types, query records, inspect updates with fulcra data-updates, and work with files. What's useful depends on what you've added to Fulcra and what the connection can access. Try one of these after setup:
Show me which data types are available in my Fulcra account and suggest one useful question we can answer with them.
Check Fulcra for data and file updates from the last 24 hours. Summarize what changed and flag anything that needs a closer look.
Find the project brief I keep in Fulcra. Summarize its open decisions and tell me where the information is incomplete.
If Fulcra has my daily step counts, compare this week with last week. Include the dates covered and call out missing days.
You can also ask your dot to save specific files or record specific information to Fulcra. Make the content and destination clear when you request a write. Setup itself does not authorize uploads or ongoing data sharing.
You approve access. Review the account and permissions shown during sign-in before continuing.
Credentials stay out of chat. The CLI saves credentials on your dot's cloud computer so it can authenticate subsequent requests. Your dot should not print those credentials or include them in documents.
You choose what to save. Connecting does not automatically copy your conversations, files, or preferences into Fulcra.
Other agents need their own setup. Information saved in Fulcra is useful to another agent only if it has access and is instructed to retrieve and use it.
Review Fulcra's privacy information before connecting. To stop access, use the account's available access controls or ask Fulcra support for the current revocation steps; removing a local credential file is not a substitute for server-side revocation.
The sign-in link expired. Ask your dot for a fresh link and code. Use the new link rather than reopening an expired authorization request.
Sign-in finished but your dot has not confirmed. Your dot should check the device-flow result and then run the read-only account check. If authorization was denied or the request expired, it should explain that before starting another attempt.
Your dot cannot save credentials. Some cloud environments restrict the default home directory. Your dot can check for an authorized, private, writable location and use it consistently for the CLI. It should explain the location before sign-in and keep credentials out of shared files and source control. If no suitable location exists, it should stop and tell you.
The cloud computer cannot reach Fulcra. Your dot should report the connection error. A network restriction needs a supported access route; repeatedly restarting sign-in will not fix it.
You already connected Fulcra through MCP. The CLI and the MCP connection authenticate separately. A working MCP connection does not prove the CLI is signed in, and CLI setup does not test MCP writes.
The connection worked before but no longer does. Ask your dot to check the installed CLI and its credential location first. A replaced or reset cloud environment may need installation and sign-in again.
Sharing context with an AI — letting it know about you, your work, and your world — should be a two-way door. Grant access. Revoke it. Change agents. Keep the context. Keep what your agents make.
Fulcra was built by founders with 15 years in security infrastructure including HUMAN, Veracode, Verisign. Your vault is encrypted at rest and in transit, with per-agent scoped access and a full audit log on every read.
Per-agent scoped tokens · Full read audit log · One-tap revoke · Encrypted at rest and in transit · No shared passwords · HSM-backed token provisioning
.png){kind=logo}
