FeaturesSecurityPricingCompareDevelopersBlogStart Free

Agent guide · 26 September 2026

How to set up a data room with ChatGPT

ChatGPT can run most of a data room from the chat once a data room's MCP server is connected in developer mode: creating it, organizing it, inviting investors, answering questions with citations. What it cannot do is move files, because its sandbox has no network access. This guide is honest about that part and shows the routes that work.

  1. Create
    create_data_room
  2. Add files
    link, inline, or you
  3. Organize
    folders + Smart Sort
  4. Invite
    held for your approval
  5. Ask
    cited answers, engagement
ChatGPT drives every step except moving your files; for that it hands you a link and waits.

Connect Sifrsys to ChatGPT

OpenAI renamed ChatGPT's connectors surface to Plugins; custom MCP servers are added there once developer mode is on. The steps below follow OpenAI's developer documentation as of 26 September 2026. Sifrsys signs ChatGPT in with OAuth, so there is no key to paste.

Step 1. Turn on developer mode

On chatgpt.com: Settings → Security and login, turn on Developer mode. OpenAI lists it for Plus, Pro, Business, Enterprise and Education accounts on the web. In a Business or Enterprise workspace an admin may need to allow it.

Step 2. Add the server on the Plugins page

Open chatgpt.com/plugins and select +. Give it a name (“Sifrsys”) and a short description, enter the server URL including the /mcp path, and choose OAuth for authentication.

Server URL
https://sifrsys.com/mcp

Step 3. Sign in and approve

ChatGPT opens Sifrsys's sign-in and consent screen. Pick the organization and approve. The connection then appears under Settings → Agents & API → Connected apps in Sifrsys, where you can revoke it.

Step 4. Use it in a conversation

Start a new conversation, choose Developer mode from the + menu and select the Sifrsys app. ChatGPT will ask you to confirm each write action; that confirmation is ChatGPT's, and it repeats in each new conversation.

Prompts to copy

OpenAI's guidance for developer mode is to be explicit about tool names, so the tool is written into each prompt.

Step 5. Create the room and add documents

Create the room
Use the Sifrsys create_data_room tool to create a data room called "Acme — Seed Round". Show me the upload_page_url it returns.
Files on my computer: hand the upload to me
I have 14 files on my laptop for this room. Send me the room's upload page link, wait while I upload them there, and check get_room_overview every 30 seconds until the document count reaches 14. Then carry on.
Files at a link (upload_from_url)
Use upload_from_url to add https://example.com/acme-deck.pdf to the room.
A document ChatGPT writes (upload_inline_document)
Write a data room index as plain text, one line per folder describing what belongs in it, and upload it with upload_inline_document as "00 Index.txt".

Step 6. Organize, invite, ask

Folders and Smart Sort (organize_documents)
Use organize_documents to create folders Corporate, Financials, Legal, Team and Product, and run Smart Sort as a preview. Show me the suggestions and wait for my go-ahead before running it with apply=true.
Group and invitations (invite_participants)
Use invite_participants to create a new group "Lead investors" with permission_level view, watermark_enabled true, can_download false, and invite Jane Doe (jane@fund.example) and Mark Lee (mark@capital.example). If it returns pending_approval, tell me and wait.
After you approve in Sifrsys (get_pending_approvals)
I approved it in Sifrsys. Check get_pending_approvals, then retry the same invite_participants call with the approval_id and the group_id it created.
Cited question (ask_room_ai)
Use ask_room_ai to ask: "What is the post-money valuation in the cap table, and what option pool does it assume?" Quote the citations exactly.
Engagement (get_engagement_report)
Use get_engagement_report with lookback_days 7 and tell me which invited investors have not opened anything.

Uploads when the agent has no network

Tool calls from ChatGPT to the Sifrsys MCP server travel through OpenAI's servers and are not affected by the sandbox. What the sandbox blocks is code sending data out on its own, and the signed-URL upload is exactly that: a PUT of the file bytes to auth.sifrsys.com. So in ChatGPT, three of the four paths are usable and one is not.

The four ways a document gets into a room. All four run the same validation, storage quota, duplicate detection and audit logging.
CriterionToolLimitNeeds outbound network from the agent?
Signed URLAgent PUTs the bytesrequest_upload_urls → HTTP PUT → finalize_uploads100 MB per file, 25 files per call, URL valid about 5 minutesYes, to auth.sifrsys.com
InlineContent inside the tool callupload_inline_document4 MB decodedNo
From a linkSifrsys fetches itupload_from_url20 MB, https only, no login or cookiesNo
Upload page hand-offYou upload, the agent waitsupload_page_url, then get_room_overview until document_count risesWhatever your plan's storage allowsNo
The four ways a document gets into a room. All four run the same validation, storage quota, duplicate detection and audit logging.

For a typical seed round, where the deck, model, cap table and legal documents sit in a folder on a founder's laptop, the upload page is the path that works: ChatGPT sends the link, you drop the files in, it continues. Links work when the files already live somewhere that can produce a direct https download without a login.

Which agent for which situation

Which agent fits which situation. Client behaviour checked against each vendor's documentation on 26 September 2026; Sifrsys limits from the MCP server source.
Criterionclaude.ai (web, desktop)ChatGPT (developer mode)Claude Code, Cursor, Codex CLI
Sign-in to SifrsysOAuth consent screen, no key to pasteOAuth consent screen, no key to pasteAPI key (sifr_live_…) in a header
Files on your own diskThe common case for a seed roundAttach them to the chat and allow auth.sifrsys.com in network settings, or use the upload pageUpload page: you drop the files in, the agent carries onWorks natively: the agent reads the folder and uploads it
Files at an https linkupload_from_url, up to 20 MBupload_from_url, up to 20 MBAny of the four paths
Documents the agent writes (index, FAQ, summary)upload_inline_document, up to 4 MBupload_inline_document, up to 4 MBupload_inline_document, or write the file and upload it
Large filesSigned URL (100 MB) only once egress to auth.sifrsys.com is allowedUpload pageSigned URL, up to 100 MB each
Client plans that can connectFree (one custom connector), Pro, Max, Team, EnterprisePlus, Pro, Business, Enterprise, Edu, on the webAny: the client runs on your machine
Best forFounders who live in Claude and have a handful of filesTeams already on ChatGPT; organizing, inviting and asking once files are inA folder of 30+ files, repeatable setups, anything scripted
Which agent fits which situation. Client behaviour checked against each vendor's documentation on 26 September 2026; Sifrsys limits from the MCP server source.

Where ChatGPT is weaker for this job is the first mile: it cannot move a folder of files. If that is most of the work, a local agent does it in one step; see Claude Code, Cursor and Codex. Once the files are in, ChatGPT is as capable as any other client at the rest.

What an agent is never allowed to do by default

Every Sifrsys organization has a policy matrix that sets each class of agent action to allow, require approval, or deny. The defaults below are the ones in the server code. An owner or admin can change them under Settings → Agents & API; nothing an agent says in a chat can.

Default agent policy per action class (DEFAULT_POLICIES in the gateway). A Q&A draft is never visible to the person who asked until it is published, and publishing needs your approval by default.
CriterionDefaultWhat it covers
DeniedRefused with denied_by_policyDeleting or suspending: documents, folders (and merging duplicate folders), participants, groups, and the room itself. Also changing room branding (configure_branding) and publishing the room's participant portal
Needs your approvalReturns a pending_approval handleSending or resending invitations (invite_participants, resend_invite); widening access: a permission on a specific document or folder (set_permissions), a more permissive group, a later or removed access expiry, reactivating a suspended participant; publishing a Q&A answer to the person who asked, assigning a question, changing its status
AllowedRuns immediately, loggedReading, creating rooms, uploading (including new versions of a document), renaming and moving documents and folders, removing empty folders, Smart Sort, creating groups, narrowing access, asking the room AI, drafting Q&A answers, restoring a suspended room
Default agent policy per action class (DEFAULT_POLICIES in the gateway). A Q&A draft is never visible to the person who asked until it is published, and publishing needs your approval by default.

An approval goes to the organization's admins by email and appears under Settings → Agents & API. It is single-use, matched to the exact request the agent made, and expires after 24 hours, so an approval for inviting two people cannot be replayed to invite a third. Every agent action, allowed or not, lands in the room's hash-chained audit log as actor_type=agent with the human who connected it. A key or connection can never do more than the person who created it, and an org-wide switch turns all agent access off at once.

Document text that comes back through ask_room_ai or list_qa is wrapped and labelled as untrusted data, because it was written by the other side of the deal. The threat model explains why.

Agent access is on every Sifrsys plan, the free one included. An agent works inside your plan's limits (the free plan is one room, 100 MB of storage and five participants per room), and the only agent meter is a monthly budget of room-AI questions: 250 on Free, 10,000 on Teams, 50,000 on Pro. Creating, uploading, organizing and inviting are not metered. Bursts are capped at 60 requests a minute per connection. Plans are on the pricing page.

Troubleshooting

ChatGPT tries request_upload_urls and the PUT fails

Expected: the sandbox has no egress. Ask it to use the upload page or a link instead. An upload that was started but never finalized is cleaned up automatically.

A tool is missing or its description is old

Open the Sifrsys connection on chatgpt.com/plugins, select Refresh, and start a new conversation.

Developer mode is not in Settings

It is web-only, not on the free ChatGPT plan, and can be disabled by workspace policy on Business and Enterprise.

denied_by_policy, limit_reached, or an expired approval

The first is the org policy (change it in Sifrsys under Settings → Agents & API), the second a plan limit, the third an approval older than 24 hours. Ask ChatGPT to request it again.

Sources

Client steps checked on 26 September 2026 against OpenAI's ChatGPT developer mode, Connect and test your plugin and Building MCP servers. OpenAI's help-centre article on developer mode refused automated access when we checked, so the menu names come from the developer documentation. Sifrsys tool names, limits and policy defaults are from the MCP server source; see the developers page.

The other agent guides: With Claude (claude.ai) · With Claude Code, Cursor, Codex · Developer reference · The walkthrough, with the real tool calls

FAQ

Data rooms with ChatGPT, answered.

Yes, through a custom MCP connection in developer mode. With Sifrsys connected, ChatGPT can create a room, add documents from links or text it writes, create folders and permission groups, invite participants after you approve, ask the room AI cited questions and pull an engagement report. It cannot upload files from your computer by itself, and it cannot delete, rebrand or publish anything under the default policy.
OpenAI's developer-mode documentation, checked 26 September 2026, lists Plus, Pro, Business, Enterprise and Education accounts on the web, and notes availability can depend on workspace policy. The free ChatGPT plan is not listed.
ChatGPT's code sandbox has no outbound network access, so it cannot send file bytes anywhere, and it cannot see your computer. Sifrsys offers three uploads that need no network from the agent: Sifrsys fetches an https link (upload_from_url, 20 MB), the content travels inside the tool call (upload_inline_document, 4 MB, sensible for text ChatGPT writes), or you upload the files on the room page ChatGPT links you to while it waits.
That is ChatGPT's own control: OpenAI's documentation says write actions require confirmation by default in each conversation. It is separate from Sifrsys's approval queue, which holds invitations and permission changes for an admin to approve in Sifrsys.
ChatGPT reads the tool list when the connection is created. Open the connection on chatgpt.com/plugins, select Refresh, and start a new conversation.

Free plan includes agent access

Connect it, then ask ChatGPT for the room.

Create a Sifrsys account, add https://sifrsys.com/mcp on the Plugins page, and start with the first prompt above.

Start Free