Dijin · OAuth Scopes

Dijin OAuth Scopes

OAuth 2.0 searched

Dijin publishes 13 OAuth 2.0 scopes. Scopes are the fine-grained permissions an application requests at authorization time to act against the Dijin API on a user’s behalf.

This index is generated from the provider’s OpenAPI security definitions (and, where available, its documented scope reference) and refreshes on every APIs.io network build. Browse every provider’s scopes at scopes.apis.io.

CompanyAI AgentsMemoryMCPPersonal DataPrivacyOAuth

Scopes: 13 Flows: Method: searched

Scopes (13)

Scope	Description	Flows
memory.summary	Read high-level summaries only.
memory.decisions	Read confirmed decisions and their rationale.
memory.entities	Read people, projects, and things in your memory graph.
memory.evidence	Read the evidence pack behind an answer.
memory.conflicts	Read where claims disagree or were superseded.
memory.audit	Read the tamper-evident access log.
memory.raw_source.read	Read raw source text. Highest-trust scope. Pro-gated, device-confirmed, and never granted by default.
memory.write	memory.write proposes memory, corrections, or links. It never silently mutates the graph; proposals pass through the worker, policy checks, and review gates.
memory.summary.read	Daily/weekly summaries, action items, decisions extracted from the user’s memory.
memory.evidence.read	Short quoted passages tied to specific insights and decisions.
memory.entities.read	People, organisations, places, concepts extracted across sessions.
memory.audit.read	The user’s connector access ledger — every OAuth grant, scope-denied event, rate-limit hit, tool call.
memory.conflicts.read	Flagged contradictions across the user’s memory (same subject + same predicate but different facts).

📄 Provider scope reference: https://dijin.co/en/mcp

Source

OAuth Scopes

generated: '2026-11-05'
method: searched
source: https://dijin.co/en/mcp ; https://dijin.co/docs/connector
docs: https://dijin.co/en/mcp
scopes:
- name: memory.summary
  description: Read high-level summaries only.
  source: https://dijin.co/en/mcp
- name: memory.decisions
  description: Read confirmed decisions and their rationale.
  source: https://dijin.co/en/mcp
- name: memory.entities
  description: Read people, projects, and things in your memory graph.
  source: https://dijin.co/en/mcp
- name: memory.evidence
  description: Read the evidence pack behind an answer.
  source: https://dijin.co/en/mcp
- name: memory.conflicts
  description: Read where claims disagree or were superseded.
  source: https://dijin.co/en/mcp
- name: memory.audit
  description: Read the tamper-evident access log.
  source: https://dijin.co/en/mcp
- name: memory.raw_source.read
  description: Read raw source text. Highest-trust scope. Pro-gated, device-confirmed, and never granted
    by default.
  source: https://dijin.co/en/mcp
  gated: Pro
- name: memory.write
  description: memory.write proposes memory, corrections, or links. It never silently mutates the graph;
    proposals pass through the worker, policy checks, and review gates.
  source: https://dijin.co/en/mcp
  gated: Pro
- name: memory.summary.read
  description: Daily/weekly summaries, action items, decisions extracted from the user’s memory.
  source: https://dijin.co/docs/connector
- name: memory.evidence.read
  description: Short quoted passages tied to specific insights and decisions.
  source: https://dijin.co/docs/connector
- name: memory.entities.read
  description: People, organisations, places, concepts extracted across sessions.
  source: https://dijin.co/docs/connector
- name: memory.audit.read
  description: The user’s connector access ledger — every OAuth grant, scope-denied event, rate-limit
    hit, tool call.
  source: https://dijin.co/docs/connector
- name: memory.conflicts.read
  description: Flagged contradictions across the user’s memory (same subject + same predicate but different
    facts).
  source: https://dijin.co/docs/connector
note: 'Dijin documents two scope vocabularies: the "8 canonical scopes" on the MCP reference / developers
  page (memory.summary ...), and the connector guide catalogue with a .read suffix (memory.summary.read
  ...). Recorded both verbatim; llms-full.txt states "external AI clients are read-only — memory.write
  stays internal".'

Work with this as data

Every scope set here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for oauth scopes

4 MCP tools reach this

find_scopesBrowse and filter every scope set in the catalog.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This scope set

curl "https://apis.io/api/v1/scopes/dijin-co-scopes"

All oauth scopes

curl "https://apis.io/api/v1/scopes?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.