ProspectingConnector
Origami
Build lead tables, launch email and LinkedIn campaigns and read results back from Claude or ChatGPT, through Tulina's MCP server, not Origami's own hosted one.
Official site: origami.chat
What it can do
2 read/1 send
- 01Read
Build lead tables from a CSV, and upsert rows into them
- 02Read
Draft a campaign and enroll people from a table
- 03Send
Launch across email and LinkedIn, and read the statistics back
Launching sends to real people, immediately, with nothing to recall it afterwards — so the dry run is not a formality here, it is the review. One quieter rule is worth knowing before it surprises anyone: by default a campaign excludes anyone enrolled in any earlier campaign, including a draft that was deleted without ever sending. That default protects against double-touching a list, and it also silently drops people you meant to reach.
How do you connect Origami to Claude and ChatGPT?
Through Tulina's own MCP server, not Origami's own hosted one. Build lead tables from a CSV, draft a campaign and enroll people from a table, launch it across email and LinkedIn, and read the statistics back — from the same chat as Claude or ChatGPT.
Why through Tulina
The connection was never the hard part.
Most systems now publish their own way for a model to reach them, and that is good: it is what Tulina connects to. The hard part is deciding who may use it, what it is allowed to return, and what the model knows before it asks.
The keys stay in one place
YouTeamOrganisation
Connect Origami once. The credential is encrypted in a vault, never held in clear, and never pasted into a chat or a workflow file. A person uses their own key where they have one, their team's where they do not, the organisation's after that, so nobody is blocked and nobody holds more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
fields droppedmasked or hashedpseudonymised
Roles decide who can reach Origami at all. Beyond that, a policy on the connector itself decides what comes back. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
whatwhowhen
Runs are logged for the organisation. That is what makes an automated action reviewable after the fact, and it is what a security review asks for first.
The run starts knowing your company
namingkey accountsdecisions
A direct connection gives a model access. It does not tell it how your company names things, which accounts matter, or what was decided last quarter. Tulina carries that across every tool, so the same request against Origami returns something usable instead of something generic.
Processes that run on Origami
None published yet.