Reflect MCP. Build and map your networked knowledge graph.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Reflect MCP Server lets your AI client read and write directly to your personal networked thought graph. Use it to manage notes, save web links, track book highlights, and explore connected ideas across all your workspaces without leaving your chat interface.
What your AI agents can do
Append daily note
Adds Markdown text to today's daily note. You can specify a heading name for organization.
Create link
Saves a new web link or bookmark into your Reflect graph, automatically extracting metadata where possible.
Create note
Creates a brand new note in a specified Reflect graph using provided subject and Markdown content.
The agent uses get_backlinks to find all existing notes that reference a specific topic, building a map of related thoughts.
Use create_note to generate and save structured Markdown content as new, standalone notes within your Reflect graphs.
The agent executes append_daily_note to automatically dump conversation summaries or action items into today's running journal entry.
You can save new links via create_link, list all saved bookmarks (list_links), or check your library of imported book highlights using list_books.
Use get_note to retrieve the full text and metadata for any specific note you reference by its ID.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Reflect Notes: 10 Tools for Thought Graph Management
These tools give your AI agent the ability to manage notes, links, graphs, and daily thoughts across your entire Reflect knowledge graph.
019d75feappend daily note
Adds Markdown text to today's daily note. You can specify a heading name for organization.
019d75fecreate link
Saves a new web link or bookmark into your Reflect graph, automatically extracting metadata where possible.
019d75fecreate note
Creates a brand new note in a specified Reflect graph using provided subject and Markdown content.
019d75feget backlinks
Retrieves all notes within your system that contain links pointing to (or reference) a specific target note.
019d75feget current user
Fetches and returns profile details for the Reflect user currently authenticated in the service.
019d75feget note
Retrieves the complete content and metadata of a specific Reflect note, provided you know its ID or title.
019d75felist books
Returns a list of all books that have been saved or imported into your Reflect library.
019d75felist graphs
Lists every distinct workspace (graph) available to you in your Reflect account, allowing you to target specific projects.
019d75felist links
Shows all the web links or bookmarks that have been saved within a designated graph.
019d75felist notes
Provides a list of notes contained within a specific Reflect graph, allowing you to browse existing content by location.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Reflect, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You connect your Reflect account to your AI agent via their developer API. This integration gives your agent the ability to talk directly to your personal networked thought graph, letting you manage notes, bookmark web links, track book highlights, and explore connected ideas across all your workspaces without leaving this chat window.
Graph Navigation & Idea Mapping
Need to figure out where a topic lives? You can run list_graphs to see every distinct workspace—every graph—you've got in your Reflect account. Once you know the project, use list_notes to pull up a list of notes contained within that specific graph, helping you browse existing content by location. If you know a note’s title or ID, get_note grabs the full text and metadata for that single piece of work.
To map out related thoughts, just call get_backlinks; this pulls every note in your system that references a target topic, building a complete map of connected ideas.
Knowledge Capture & Archiving
Want to build permanent knowledge records? Use create_note to generate and save structured Markdown content as brand new notes within any specified Reflect graph. When you wrap up a conversation or an action item list, the agent executes append_daily_note, which dumps summaries or tasks directly into today's running journal entry.
For quick captures, you can also call create_link to save a new web link or bookmark right into your Reflect graph; this automatically extracts metadata where it can.
Resources and User Data
For keeping track of external resources, the agent shows all saved bookmarks using list_links, and it lets you review your library of imported book highlights with list_books. You also get access to user data by calling get_current_user, which fetches and returns profile details for the Reflect user currently authenticated in the service.
How It Works
Your agent handles all this complexity. If you tell it, 'Check everything related to Project X,' it knows to use list_graphs first, then focus on specific notes using get_note. If you drop a bunch of links during a meeting, the agent uses create_link to save them and keeps tabs on what's already saved via list_links.
You don't have to copy-paste or switch apps; your AI client does it all for ya. It builds out connections using get_backlinks, ensuring nothing gets lost in the shuffle.
How Reflect MCP Works
- 1 Authorize the Reflect MCP plugin in your extension. You'll need to grab your OAuth Access Token from reflect.app/developer/oauth and embed it.
- 2 Prompt your AI client naturally, like: "List all notes connected to 'AI Strategy.'" or "Append a summary of this conversation to my daily note."
- 3 The agent runs the necessary Reflect tools (e.g.,
get_backlinksorappend_daily_note) and returns the structured data directly to your chat.
The bottom line is, you talk naturally to your AI client, and it handles all the graph reading, writing, and linking in the background using Reflect's API.
Who Is Reflect MCP For?
This setup is for knowledge workers—researchers, writers, and executives who spend too much time switching between a note-taking app, a browser, and a task manager. If you need your AI to act like an extension of your own brain, this is it.
Uses the agent to run get_backlinks on key papers or concepts, instantly seeing every other note in their graph that mentions that subject.
Directs the AI to capture meeting summaries and decision points using append_daily_note, ensuring all action items are logged immediately without manual copy/pasting.
Asks the assistant to find all notes related to a specific feature or market segment by calling list_notes within the 'Project' graph, keeping context centralized.
What Changes When You Connect
- Stop losing ideas. You can instantly capture insights using
append_daily_note, ensuring that every conversation summary or action item gets logged to today's record without manual effort. - Go beyond simple searching. Instead of just finding a note, use
get_backlinksto see the entire web of related concepts—every single place you’ve mentioned 'AI Strategy', for example. - Context is king. Use
list_graphsfirst to pinpoint which workspace holds your data before running any other tool, guaranteeing you read from the right project graph. - Capture external resources without friction. With
create_link, you can bookmark a URL and have the agent automatically clean up and tag the metadata for later retrieval in the graph. - Keep everything centralized. By having tools like
get_noteandlist_notes, your AI client acts as a personal knowledge broker, pulling content from deep within Reflect without you leaving your chat window.
Real-World Use Cases
The Brainstorming Session Recap
You finish a long brainstorming call. Instead of copying bullet points into a separate document, you ask your agent to 'Append the main takeaways and action items to my daily note.' The agent runs append_daily_note, dumping everything correctly formatted in Markdown.
Following an Old Idea Thread
You're working on a new feature and remember mentioning 'Microservices Architecture' six months ago. You ask your agent to find all related notes by running get_backlinks. The agent returns three specific documents, letting you instantly restart the thread.
Project Audit Check
You need to see everything saved for 'Q3 Marketing.' First, you run list_graphs and select the correct workspace. Then, you use list_links to gather every external resource or bookmark ever added to that specific project graph.
Onboarding a New Team Member
A new hire needs context on 'Product History.' You ask the agent to find all notes connected to 'V1 Launch' by running get_backlinks. The agent provides a comprehensive list of foundational documents, skipping weeks of manual setup.
The Tradeoffs
Asking for raw data dumps.
Prompting: 'Give me all my notes and links.' This is too broad. The agent will fail or return a massive, unreadable list that requires manual filtering and context switching.
→
You must scope the request. First, run list_graphs to confirm your target workspace. Then use tools like list_notes on that specific graph ID to narrow down what you need.
Ignoring link metadata.
Just pasting a URL and hoping it sticks. The agent treats it as plain text, losing the context of when or why you saved the link in your knowledge graph.
→
Always use create_link. This tool specifically handles saving web bookmarks while attempting to extract useful metadata for better searching later.
Assuming one note covers everything.
Thinking that writing a new note with create_note is enough. If the idea relates to an existing concept, you lose the valuable link between them.
→
After creating content using create_note, ask your AI client to check related ideas by running get_backlinks on the core concepts in that new note.
When It Fits, When It Doesn't
Use this if you need an AI agent to act as a knowledge broker, synthesizing information across structured notes and external resources. The system shines when your process involves reading, connecting, summarizing, and archiving thoughts—it's built for the interconnected mind.
Don't use it if your workflow is purely linear or transactional (e.g., 'send this email,' or 'run a SQL query'). For those tasks, dedicated messaging or database tools are better. If you only need to read one specific document and nothing else, simply using an API call to get_note might suffice, but the MCP Server allows for complex multi-step operations like: 1) Listing graphs (list_graphs), 2) Getting backlinks on a note (get_backlinks), and 3) Appending the results to today's journal (append_daily_note). The power is in the sequence.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Reflect Notes. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Finding connected ideas shouldn't require opening multiple tabs.
Today, figuring out how a new idea connects to your existing knowledge means jumping through hoops: checking your 'Ideas' folder, then searching your old meeting notes, and finally cross-referencing bookmarks in a separate tool. It’s copy-pasting until you feel like you've hit the wall.
With this MCP server, you just ask your agent to map out connections using `get_backlinks`. You tell it: 'Show me everything connected to X.' The agent runs the query and gives you a clean list of references. Done.
Reflect Notes MCP Server makes content creation immediate.
Before, summarizing a call meant stopping what you were doing—opening your notes app, manually typing 'Meeting Summary,' and then formatting the bullet points. It was a mandatory time sink that broke concentration.
Now, simply ask the agent to dump the summary using `append_daily_note`. The content flows directly into today's note, perfectly formatted, without you lifting a finger or switching applications.
Common Questions About Reflect MCP
How do I list all my available knowledge workspaces using list_graphs? +
Call list_graphs with no parameters. This returns every distinct graph (workspace) you've set up in Reflect, allowing you to target the right context for your queries.
Can I find all notes that mention a specific topic using get_backlinks? +
Yes, pass the note ID or title of the concept into get_backlinks. This retrieves every other piece of content in your graph that has linked back to that subject.
What is the difference between list_notes and get_note? +
Use list_notes when you want a directory—a simple listing of all note titles within a graph. Use get_note when you already know the specific ID and need the full content to read or process.
How do I save a new web link using create_link? +
Pass the URL into create_link. Reflect tries its best to automatically pull metadata (like article title/source) and saves it as a structured bookmark in your graph.
How do I verify my profile details using get_current_user? +
It retrieves your authenticated user's basic profile information. This function pulls non-sensitive metadata, like your name and email address, into the agent's context for reference.
When using create_note, what specific format must I provide for the subject and Markdown content? +
The tool requires two distinct parameters: a string for the note's title (subject) and a dedicated block of text for the body. Providing clear Markdown helps structure bullet points and formatting within the new note.
How does using append_daily_note differ from creating a standalone note with create_note? +
It appends content directly to your existing daily journal entry, rather than generating a brand-new, separate file. Use it for quick summaries and chronological logging of conversation insights.
What kind of data does list_books return when I run the command? +
It lists all books you have saved or imported into your Reflect account. This function pulls content from your external library, keeping it separate from notes and links.
Can the agent create new graphs from scratch? +
No. The AI via the MCP can fully manage notes, generate fresh links, and organize entries, but you must create top-level workspaces (Graphs) directly within the native Reflect desktop or web applications first.
Will `append_daily_note` overwrite my existing notes for today? +
No, append_daily_note strictly adds the provided Markdown blocks to the very bottom of today's Daily Note section in Reflect. It is a completely safe, non-destructive operation preserving your older notes intact.
Can I search notes by standard keywords instead of IDs? +
The underlying Reflect API largely focuses on ID-based lookups (note_id). You can request the AI to first list_notes which provides titles for semantic checking, and then it can dynamically chain the ID lookup to read your specific content immediately after.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Giftpack
Send corporate gifts at scale with AI-curated selections that match recipient preferences and company budget guidelines.
NameSilo (Domain Registrar Developer API)
Manage your domain portfolio, DNS records, and registrations directly through NameSilo's developer API.
QR Code Generator
Generate and decode QR codes for URLs, text, and data directly within your AI workflow.
You might also like
Amazon Bedrock KB
Connect your AI agent to AWS Bedrock Knowledge Bases — execute semantic searches, managed RAG, and sync vector datasources natively.
Workload
Build visual workflow automations that connect your favorite apps and eliminate repetitive manual tasks across your business.
PaperQuotes
Access a vast library of quotes, search by author or tags, and get the quote of the day directly in your AI agent.