Reflect App reflect
0
AI ReadinessNon-Ready (F)0/100
Official vendor OpenAPI document · agent-readyProductivityNote Takingoauth27 EndpointsREST
For Agents
Append entries to a Reflect daily note, create a new markdown note, save a link, and list a graph's saved links and books, scoped to a graph id.
Use for: Add a meeting takeaway to today's daily note in Reflect, I want to log a task under the Updates list in my daily note, Create a new Reflect note with my research summary in markdown, Save this article link to my Reflect graph
Not supported: Does not return note contents, edit or delete existing notes, or manage tasks and calendars. Use for appending to Reflect notes and reading saved links and books only.
The Reflect API appends text to daily notes, creates new notes, and saves bookmarked links in a Reflect graph, the note-taking app's personal knowledge base. It also lists the graphs a user can reach, returns saved links with their highlights, and returns books with their authors and notes. Note endpoints are append-only by design: Reflect encrypts note contents end to end, so its servers cannot read notes back and the API never returns them. Authentication is OAuth with authorization code and PKCE, using read:graph and write:graph scopes.
Install Jentic One Beta
Connect the reflect to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the reflect, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Freflect.app%2Freflect" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Freflect.app%2Freflect" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with reflect API.
Append a line to a Reflect daily note with PUT /graphs/{graphId}/daily-notes using transform_type list-append
Append under a named list in the daily note by passing list_name, using [[List Name]] to backlink
Create a new note from a subject and content_markdown, optionally pinned, with POST /graphs/{graphId}/notes
Save a bookmarked link with its url, title, and description to a graph via POST /graphs/{graphId}/links
List saved links with their highlights from GET /graphs/{graphId}/links
Return books with their title, authors, and notes from GET /graphs/{graphId}/books
Find the graph ids a user can write to with GET /graphs and GET /users/me
Use Cases
Patterns agents use reflect API for, with concrete tasks.
★ Agent journaling into Reflect through Jentic
A personal assistant agent that ends each work session by writing what happened needs a safe path into the user's notes. Through Jentic the agent searches for 'append to my daily note', loads PUT /graphs/{graphId}/daily-notes, and sends the text with transform_type list-append and an optional list_name such as Updates. Because Reflect's note endpoints are append-only, the agent can add entries but cannot read or overwrite existing note contents.
Call GET /graphs to find the graphId, then PUT /graphs/{graphId}/daily-notes with text 'Shipped the billing fix', transform_type 'list-append', and list_name '[[Updates]]'
Capturing research as new notes
A research agent that has summarised a set of sources can file the result as its own note. POST /graphs/{graphId}/notes takes a subject and content_markdown, with pinned set to true for notes that should stay at the top, and returns the new note's id and timestamps. The markdown body keeps headings, lists, and backlinks intact inside Reflect.
POST /graphs/{graphId}/notes with subject 'Vector database comparison' and content_markdown containing the summary, with pinned set to true
Read-later link capture
Links shared in chat or found while browsing can go straight into Reflect. POST /graphs/{graphId}/links saves a link object with its url, title, and description, and GET /graphs/{graphId}/links returns saved links with their highlights and updated_at timestamps, so an agent can build a weekly digest of what was saved.
POST /graphs/{graphId}/links with url 'https://example.com/post' and title 'Post title', then GET /graphs/{graphId}/links and list links updated this week
Book notes digest
Readers who keep book notes in Reflect can have an agent surface them. GET /graphs/{graphId}/books returns each book's title, authors, and notes, where each note carries a type plus optional page, location, and value, which is enough to assemble a quote digest or flashcards.
Call GET /graphs/{graphId}/books and return the notes for the book whose title matches 'Thinking in Systems'
Key Endpoints
7 endpoints — the reflect api appends text to daily notes, creates new notes, and saves bookmarked links in a reflect graph, the note-taking app's personal knowledge base.
METHOD
PATH
DESCRIPTION
PUT
/graphs/{graphId}/daily-notes
Append to a daily note
POST
/graphs/{graphId}/notes
Create a note
POST
/graphs/{graphId}/links
Save a link
GET
/graphs/{graphId}/links
List saved links
GET
/graphs/{graphId}/books
List books and their notes
GET
/graphs
List graphs
GET
/users/me
Read the current user
PUT
/graphs/{graphId}/daily-notes
Append to a daily note
POST
/graphs/{graphId}/notes
Create a note
POST
/graphs/{graphId}/links
Save a link
GET
/graphs/{graphId}/links
List saved links
GET
/graphs/{graphId}/books
List books and their notes
GET
/graphs
List graphs
GET
/users/me
Read the current user
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
R
reflect
- Non-Ready (F)0/100
100
Foundational Compliance57
Developer Experience & Jentic Compatibility10
AI-Readiness & Agent Experience94
Agent Usability90
Security0
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
100
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
98%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
57
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: C+Signals: 4
4%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
25%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
10
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
41%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
0%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
0%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
90
Security
Trust, risk posture, and security compliance.
Grade: A+Signals: 1
90%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
0
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: FSignals: 1
0%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Reflect by hand means registering OAuth credentials in its developer settings, running the authorization-code flow with PKCE or generating a token, and resolving the graph id before any write. Through Jentic you install once, import Reflect from the API Directory, store the token once, and your agent calls it.
Permission scoping
Reflect puts the graph id in the URL path (/graphs/{graphId}/...), so a rule can pin your agent to one graph and the operations you pick. You choose the operations it may call, so writes like creating notes or saving links are not included unless you add them.
Credential isolation
Your Reflect access token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'append to my daily note' or 'save a link to Reflect', and Jentic returns the matching Reflect operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using reflect API through Jentic.
What authentication does the Reflect API use?
Per its OpenAPI spec, the Reflect API uses OAuth with the authorization code flow, declared as the reflect_auth scheme with read:graph and write:graph scopes, and PKCE is supported. Reflect's developer settings can also generate an access token directly, which works much like an API key and is sent as a bearer token. Through Jentic, that token is stored encrypted by your own Jentic One instance and injected at call time.
Can I read my Reflect notes with the API?
No. Reflect encrypts note contents end to end, so its servers cannot read them and the note endpoints are append-only: you can append to a daily note or create a new note, but not fetch note text. The read endpoints cover graphs, saved links, books, and the current user.
What are the rate limits for the Reflect API?
The OpenAPI spec does not specify rate limits. Check Reflect's developer pages at https://reflect.app/developer/oauth for current guidance before running bulk link imports.
Is there a Reflect MCP server?
You don't need an MCP server to give your agent Reflect. Jentic connects it directly from the API Directory: import it, store your access token once, and your agent calls the note and link operations it needs, discovered on demand rather than loaded into its context up front.
How do I append to today's daily note through Jentic?
Search Jentic for 'append to my daily note', load PUT /graphs/{graphId}/daily-notes, and send text with transform_type set to list-append; date defaults to today and list_name is optional. Get the graphId first from GET /graphs. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Reflect API?
Yes. Write a rule that allows only PUT on /graphs/abc123/daily-notes, and the agent can add entries to that graph's daily notes and nothing else: no new notes, no link writes, no other graph. Every call it makes is logged.
GET STARTED