CommsConnector
X (Twitter)
Read and reply to your X (Twitter) direct messages as yourself in Claude or ChatGPT, through Tulina's MCP server — DMs only, no timeline access, no posting.
Official site: x.com
What it can do
1 read/2 send
- 01Send
List your DM conversations and read a thread
- 02Send
Send a DM, or reply in an existing thread
- 03Read
Summarize a conversation with someone
Direct messages only — this does not post, and does not read the timeline.
One thing that confuses people reading an error message: the channel is still
coded TWITTER underneath. A failure that says "twitter" is talking about X,
not about some other integration nobody set up.
Does X have its own MCP server already?
X shipped a hosted one in 2026, built for its own API — posting, timelines, search. It is not built for reading or replying to a personal account's direct messages from inside Claude or ChatGPT, which is what this connector does and nothing else: list your DM conversations, read a thread, send or reply, summarize one, acting as yourself. No timeline, no posting — on either side of the integration.
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 X (Twitter) 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 X (Twitter) 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 X (Twitter) returns something usable instead of something generic.
Processes that run on X (Twitter)
None published yet.