Connect ChatGPT or Claude to Thegram with OAuth · r13

Archived revision r13, recorded 2026-10-16T01:26:30.055Z by portal-product-quickstarts. Current page: Connect ChatGPT or Claude to Thegram with OAuth.

Connect ChatGPT and Claude with OAuth

Both connect to https://vault.thegram.one/mcp using Streamable HTTP and OAuth. No running desktop app or DMG is required. The coding-agent API-key setup is separate: coding agent API setup.

Before connecting

The person signs in to the intended Thegram account, reviews resource permissions, and completes provider consent or account prompts. Do not authorize, accept terms, create accounts or grant permissions on their behalf.

ChatGPT install

Connect Thegram to ChatGPT

1. Open the official Thegram plugin page: https://chatgpt.com/plugins/plugin_asdk_app_6acc810ccabc8191acd3f457dc498d43
2. Select Install plugin and follow the installation and account-connection prompts shown in ChatGPT.
3. In a chat or dot, select Thegram from the available tools or apps.

Claude custom connector

In Claude, open Settings → Connectors → Add custom connector and use https://vault.thegram.one/mcp. Complete Claude’s own Thegram sign-in and permission flow. This documents the custom connector route, not an official Claude directory listing or a provider-account test completed by this release.

Other OAuth-capable clients

Use the same endpoint with Streamable HTTP and the client’s own OAuth flow. Do not paste a coding-agent API key into an OAuth sign-in prompt.

Storage and access

All current agent connections use Thegram Cloud. Local-only files are not uploaded or exposed automatically. API keys authorize selected vaults and separately selected Drive accounts, intersected with current membership and organization policy. A vault grant is not a document-only sandbox.

Review connected OAuth agents in Thegram Settings → Agents. API keys are managed separately in the API keys section.

One type, one dashboard

Core 2.0.1 resolves one dashboard per declared document type. The client renders its single ResolvedView/1 result; it does not choose another ViewSpec or compute its own recommendation.

Document type	Dashboard
schedule@1	Journal
project@1	Project Tracker
knowledge@1	Knowledge

Without a template declaration, Core recommends a dashboard and the dashboard is read-only. If no recommendation is eligible, it falls back to Project Tracker, still read-only. An unknown id/version or malformed declaration has no dashboard: show the document and Core diagnostics without automatically choosing another type.

A folder opens one home screen. There are no per-document screen tabs, sidebar screen lists, ViewSpec switchers or search/filter/sort/group query toolbar. Document and dashboard are representations of the same file, not separate copies.

Templates still choose a type when creating a document, validate governed writes, supply AI authoring rules and define typed actions. A read-only recommended dashboard does not forbid ordinary document editing through the normal authorized write path.

For declaration and writing rules, see View templates.

Verify access without writing

gram_capabilities({})
gram_projects({})
gram_brief({ "folder": "<project folder or mount key returned by gram_projects>" })
gram_read({ "path": "<exact document path in gram_brief docs>" })
gram_read({ "path": "<same document path>", "section": "<heading returned by gram_read outline>" })

Expected: the intended permitted mounts and an existing document are readable. Stop on an empty listing, missing permission or a provider prompt; do not create a vault or write a document as a connection test.

Optional first save and search

Keep installation and the checks above read-only. Save only after the person explicitly asks for this save, grants write access, approves the exact new path, and confirms that it does not already exist in that authorized folder. Never create a mount, overwrite a document, or use a write as a connection test.

Use the actual gram_create input shape; base_revision null creates a new document. Replace the path with a new path under the exact authorized project folder or mount, and use only text the person approved:

gram_create({
  "path": "<authorized-folder>/setup-notes.gram",
  "title": "Setup notes",
  "base_revision": null,
  "content": "# Setup notes"
})

Expected: the tool confirms the new document and returns its path/revision. Read it directly; search the same authorized folder with gram_recall when indexing is available:

gram_read({ "path": "<exact path returned by gram_create>" })
gram_recall({
  "query": "setup notes",
  "folder": "<same authorized folder or mount key>",
  "top_k": 5
})

Expected: gram_read returns the saved document; gram_recall returns matching indexed material or no result until indexing catches up. Both retrieval calls are read-only.

Sources and evidence limits

OAuth source package version 1.5.4 comes from owner manifests, not the ChatGPT provider release identifier. The existing published ChatGPT installation route is retained. This API-key release did not install either provider account or publish a Claude directory entry. Canonical ChatGPT guide: https://thegram.one/install/chatgpt.md

Source and renderer evidence

Canonical source SHA-256

2b81848fae488b837fd67778b4f2495e811f987a640171b20cc232242627fa34

Selected revision

r13 · sha256:03cf316a484a2248910291a7f5ac14f2c7d52c6316ebb6280bbac8330b6bbc59

Local renderer

configured local Thegram renderer · API thegram-web-render/1

Core source

git+https://github.com/clab-one/thegram-format.git?rev=b16489e1d0d77d38f82d2f61776524737aa31557#b16489e1d0d77d38f82d2f61776524737aa31557

Canonical source: 13.gram