Synchronizes memory, preferences, and specialized agent teams across multiple AI clients like Claude Code, Cursor, and Codex.
Also known as JevonsCode/fuli, fuli-context
- Stars
- 10
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- Apache-2.0
What is fuli MCP?
fuli synchronizes memory, preferences, and specialized agent teams across multiple AI clients like Claude Code, Cursor, and Codex.
Summary generated from the project's README
About fuli MCP server
Synchronizing memory, preferences, and specialized agent teams across different AI clients is what FULI enables for developers using tools like Claude Code, Cursor, Codex, and OpenCode. By acting as a local service and console, it ensures that a rule or preference stated in one client is immediately available in others. This allows you to switch between different agentic environments without repeating context or instructions.
The system introduces a team of specialized agents known as FLAs, including Jefa for project management, Bole for staffing, Tonborg for preference confirmation, and Astro for general conversations. These agents can form a roundtable to review, test, and hand over work to one another. Because FULI runs locally on your computer and manages data through a local service, your personal graphs and conversation records remain private.
Setup is handled via a desktop application for Windows and macOS or through npm for Linux and cloud environments. It integrates with your existing models and subscriptions, adding only its own entries to your clients. This approach helps reduce token usage by providing only the necessary facts for a specific task rather than sending entire histories.
What you can do with it
- 1Synchronize preferences across clientsEnsure a rule defined in Claude Code is automatically respected when you switch to Cursor.
- 2Deploy specialized agent teamsAssign a project manager and a staffing agent to coordinate complex development tasks.
- 3Automate preference confirmationUse Tonborg to verify everyday items against your established preferences and learn from your feedback.
- 4Reduce token consumptionMinimize the amount of context sent to your model by only providing relevant facts for the current task.
Written from the project's README. Every use case is checked against a quote from it.
How to install fuli MCP
Formats verified 10 Nov 2026Install fuli MCP in Claude Code
$ claude mcp add fuli -- npx -y fuli-contextInstall fuli MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"fuli": {
"command": "npx",
"args": [
"-y",
"fuli-context"
]
}
}
}Install fuli MCP in VS Code
.vscode/mcp.json
{
"servers": {
"fuli": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"fuli-context"
]
}
}
}Install fuli MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"fuli": {
"command": "npx",
"args": [
"-y",
"fuli-context"
]
}
}
}Install fuli MCP in Codex
~/.codex/config.toml
[mcp_servers.fuli] command = "npx" args = ["-y", "fuli-context"]
Install fuli MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"fuli": {
"command": "npx",
"args": [
"-y",
"fuli-context"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablejevonscode/fuli is public and reachablegithub.com/jevonscode/fuli ↗Pass
- Package names this repository as its sourcefuli-context names jevonscode/fuli as sourcenpmjs.com/package/fuli-context ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for fuli-contextnpmjs.com/package/fuli-context/v/0.27.3#provenance ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-14github.com/jevonscode/fuli ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from fuli-contextPass
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubEach task gets only the small slice it needs. Your judgment and experience keep adding up, so FULI knows you better the more you use it. That is the compound interest. Little by little, what your AI makes starts to carry your taste.
What FULI does
Four FLAs come built in:
How it works
flowchart LR
U[You] -->|ask inside a project| A[Agent client]
A -->|task starts| F[FULI on your computer]
F -->|preferences and a small recall| A
A -->|look up more if needed| F
A -->|write back what is reusable| F
A task starts with the preferences in effect and a few related facts. The Agent looks up the rest when it needs it, and at the end writes back only what the next task can reuse.
Install
FULI runs a small service and a console on your own computer.
Desktop client (recommended). Download from the latest release:
| System | File |
|---|---|
| Windows | FULI-Setup-<version>.exe. No terminal and no administrator rights. |
| macOS (Apple silicon, 13.5 or later) | fuli-macos-arm64-<version>.dmg. Drag FULI onto Applications. |
On first launch FULI finds the AI clients on this computer and connects each with one click. The installers are not signed yet, so each system holds FULI back once; Install and run shows the two clicks that let it through.
Servers, VMs and the cloud. Without a desktop, and on Intel Macs and Linux, install with npm (Node.js 24.12 or later):
npm install --global fuli-context
fuli setup
fuli open
fuli setup shows its plan and changes nothing until you confirm.
The console
The console opens on what matters now: questions waiting for you, the FLAs at work and what they
finished. Everything runs on 127.0.0.1; there is no account and no sign-in.
FAQ
On your computer. Your personal graph and conversation records stay local. External knowledge (Notion, Lark, MCP or RAG sources) is read-only: FULI never writes back.
Claude Code, Codex, OpenCode, Cursor, DeepSeek Harness, Claude Desktop, Gemini CLI, Qwen Code, Kiro
and Antigravity connect from the console (Settings › Clients) with one click. Other MCP clients run
fuli connect for a standard configuration. What each client supports, such as capturing
conversations, is in Connect a client.
Start a message with #FLA and its name. In Claude Code, OpenCode and Cursor you can also type
/fla and pick one from the menu; in the Codex app, type /prompts:fla. Turn the menu off in Settings › Clients.
A session starts with only the preferences in effect and a few related facts; the Agent looks up the rest when it needs it. Facts that only you know, such as a sandbox URL you mentioned once, come back later without a search through the code. The numbers are in the benchmark (section 8.9.4).
By default the built-in FLAs work inside your client's session. Only when you connect a model for them do they use their own model, so nothing spends money behind your back.
No. Without one, FULI finds knowledge by its words, retrieval terms and relations. To find it by meaning, open Models and usage and choose Built-in models on Semantic search: FULI downloads a small model (GTE Small 中文 is recommended) and runs it on this computer. It needs no endpoint and no key, and your knowledge stays on the computer.
On the project's page, click Organise and pick one of your connected AI clients. Astro reads the project with that client's own model and fills in what is missing. You can add where the existing material is: folders, files or links. When several projects share a preference, it asks whether that preference should apply everywhere.
In the console, open Settings › Clients and choose Remove for that client. fuli uninstall and the
Windows uninstaller do the same for every connected client. FULI takes out only its own entries
(the MCP server, hooks, Skills and its permission lines), backs up each file first, and keeps a
Skill you edited yourself. Your FULI data stays until you delete it. On macOS, remove the clients
in the console before you move FULI.app to the Trash: the Trash alone leaves those entries in place.
The program is, your data is not: both use the same data folder. When the desktop client starts, it runs the one FULI
service and points your connected clients at itself. The console then offers to remove the npm copy with one click;
until it is removed, a bare fl in a terminal is still the npm version.
Details
You do: AI looks things up and does the work, and humans retain final authority. Each task ends with one check that keeps only reusable knowledge. A preference an Agent guessed counts once you, or Tonborg within the autonomy you set, confirm it. Older answers stay in the history with their source and reason.
Learn more
| Topic | Read |
|---|---|
| Install details, CLI commands, ports | Install and run |
| Principles and what is stored where | How FULI works |
| Connecting each client | Connect a client |
| Skills, hooks and MCP tools | Agent integrations |
| Notion, Lark and other knowledge bases | External knowledge |
| Tonborg and autonomy | Judgment and autonomy |
| The roundtable | Roundtable |
| What is proven so far | Capabilities and limits · Measured report |
| Running the source | Develop and verify · Contributing |
The FULI mark and wordmarks come from the FULI 复利 brand system; see brand/README.md.
Licensed under Apache-2.0.
fuli MCP questions
How do I add fuli MCP to Claude Code?
Run claude mcp add fuli -- npx -y fuli-context in your terminal. Add --scope user to make it available in every project.
How do I add fuli MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Where is my data?
All personal graphs and conversation records are stored locally on your computer. External knowledge sources are read-only.
Which clients work with FULI?
Fuli supports Claude Code, Codex, OpenCode, Cursor, and Claude Desktop via a one-click connection, and other MCP clients via standard configuration.
Do the built-in FLAs cost extra?
The built-in FLAs operate within your existing client's session by default, so they only use your own model connections.
How do I take FULI out of a client?
You can remove FULI from a client through the console settings or by using the uninstall command, which removes its specific entries and backs up files.