Fresh Jots MCP Server
This server connects Fresh Jots notes with clients
README
freshjots-mcp
A Model Context Protocol (MCP) server for Fresh Jots. It exposes your Fresh Jots notes as MCP tools, so any MCP client — Claude Desktop, Claude Code, Cursor, and others — can read and write them directly. Point your AI agent's output at a Fresh Jots note, log your coding sessions, or let an assistant search and update your notebook, all through the API.
MCP is an open standard for connecting AI assistants to external tools and data — think of it as a universal adapter, so one integration works across every compatible client.
What you can do
The server talks to the Fresh Jots REST API over a bearer token and exposes these tools:
Notes — list_notes, read_note, create_note, append_to_note, update_note, delete_note, move_note
Folders — list_folders, create_folder, rename_folder, delete_folder
The standout is append_to_note: it appends to a note addressed by an exact filename (e.g. ai-sessions.txt) and creates the note on first write. Call it repeatedly to accumulate a log — AI session transcripts, cron output, a running journal — in one place.
Notes are plain text through the API: rich (Trix) notes can be listed and read, but only plain notes can be created or edited here.
Requirements
- Node.js 18 or newer
- A Fresh Jots API token (Pro or Team plan). Create one at https://freshjots.com/settings/api_tokens. Tokens look like
mn_….
Install
Until this is published to npm, build it from source:
git clone https://github.com/Goran-Arsov/freshjots-mcp.git
cd freshjots-mcp
npm install # also builds via the prepare script
npm run build # or build explicitly
The runnable server is then dist/index.js.
Configuration
The server reads its token from the environment:
FRESHJOTS_TOKEN(required) — yourmn_…API token.FRESHJOTS_API_TOKENis also accepted.FRESHJOTS_BASE_URL(optional) — defaults tohttps://freshjots.com/api/v1. Override for a self-hosted or staging instance.
Claude Desktop
Add to claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"freshjots": {
"command": "node",
"args": ["/absolute/path/to/freshjots-mcp/dist/index.js"],
"env": { "FRESHJOTS_TOKEN": "mn_your_token_here" }
}
}
}
Claude Code
claude mcp add freshjots --scope user \
-e FRESHJOTS_TOKEN='${FRESHJOTS_TOKEN}' \
-- node /absolute/path/to/freshjots-mcp/dist/index.js
Using '${FRESHJOTS_TOKEN}' (single-quoted) stores the reference, not the secret — Claude Code expands it from your shell environment at launch, so keep export FRESHJOTS_TOKEN=mn_… in your shell profile. Or pass the literal token with -e FRESHJOTS_TOKEN=mn_… if you prefer it in the config.
Cursor
Add to ~/.cursor/mcp.json (or a project .cursor/mcp.json):
{
"mcpServers": {
"freshjots": {
"command": "node",
"args": ["/absolute/path/to/freshjots-mcp/dist/index.js"],
"env": { "FRESHJOTS_TOKEN": "mn_your_token_here" }
}
}
}
Once published to npm, command: "npx", args: ["-y", "freshjots-mcp"] will replace the local path in any of the above.
Development
npm run build # compile TypeScript to dist/
npm test # unit tests (fetch stubbed; no network)
node smoke.mjs # live end-to-end test against the real API — needs FRESHJOTS_TOKEN;
# creates only clearly-marked [mcp-test] notes/folders and deletes them
License
MIT © Goran Arsov
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.