Needt

io.github.teenxgrailedPublished by GitHub account teenxgrailedv1.0.0Updated Nov 6, 2026

Your planner in every AI chat: tasks, calendar, docs, habits, goals and memory, over MCP.

Overview

AI-generated overview

Needt connects an AI assistant to a personal planner over MCP, so it can manage tasks, calendar, habits, pages, mail and memory in chat.

What you can do
  • Add, move and finish tasks, and break plans into steps
  • Read the day across calendars and log habits
  • Write pages and turn mail into tasks
  • Save and recall standing memory lines about how you work
  • Run project roadmaps with milestones, blockers and handoffs
  • Pair with free skills for research, prompt building, plan critique and YouTube reading
When to use it
Useful if you keep your tasks, calendar and notes in Needt and want the assistant to read and update them directly from a chat, including multi-session project roadmaps and remembered preferences.
Requirements
A remote MCP endpoint (streamable HTTP) with OAuth sign-in to a Needt account. The planner tools need a Needt Pro account; the other bundled skills work without one. No environment variables or headers are declared.
Before you install
The assistant reads and writes your own Needt data after OAuth sign-in, including tasks, calendar, pages and mail. Memory lines persist across chats and devices until turned off in the app. Sending, posting, paying and deleting are described as waiting for confirmation, but review changes before approving them.

Installation

In SourceWeft

  1. Open Needt in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.teenxgrailed%2Fneedt/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "needt": {
      "type": "http",
      "url": "https://mcp.needt.app/mcp"
    }
  }
}

README

[Needt Plugin icon]

Needt Plugin

Ten skills that make your AI sharper — and one that runs your day inside Needt.

A business partner, a researcher, a prompt builder, a grill-me, a plan critic, a project roadmap and a YouTube reader, free. Plus /needt, which gives your AI your whole planner: tasks, calendar, habits, pages, mail and memory.

[Version] [License: MIT] [MCP] [Works with]

Install · Skills · How it works · Privacy · needt.app


[Needt home] [Needt tasks] [Needt calendar] [Needt habits] [Needt mail]

Real Needt screens. /needt calls Needt's own tools over MCP — the same ones the app uses.

Install

Claude Code — one line:

sh
claude plugin marketplace add teenxgrailed/needt-plugin && claude plugin install needt@needt

(or inside Claude Code: /plugin install needt --marketplace teenxgrailed/needt-plugin; update later with claude plugin update needt@needt)

Claude (web, Desktop) — download needt.plugin, then Customize → Plugins → Add → Upload plugin.

WhereHow
Codexcodex plugin marketplace add teenxgrailed/needt-plugin
Single skills (Claude, Cursor, any agent that reads SKILL.md)npx skills add teenxgrailed/needt-plugin and pick the ones you want, or download a skill zip from the latest release → Customize → Skills → Upload
Any MCP clientRemote server https://mcp.needt.app/mcp (streamable HTTP, OAuth)

Then start a new chat and just talk — "what's on today?", "help me think about pricing", "find the best way to…", "roadmap for my app". You never have to name a skill.

The skills

SkillWhat it does
/needtYour planner in every chat. Adds, moves and finishes tasks, breaks plans into steps, reads your day across calendars, logs habits, writes pages, turns mail into tasks, remembers how you work. Starts on its own when you say "add…", "remind me…", "what's today", "move…", "done" — in English, Russian, Ukrainian, German, Spanish and French.Pro
/needt:partnerBusiness partner. Reads your real numbers from whatever your AI is connected to, finds the real question, picks the best of two or three moves, does the work and lands it in Needt. Calls the other skills itself. Money ends in a verdict: take, take if X, walk.Free
/needt:searchResearch that finds the good option, not the first one. Web, YouTube transcripts, X and GitHub, wide first then deep. Opens with the Find — the non-obvious thing — and dates every source.Free
/needt:promptA rough wish becomes one prompt of the right size, with stages that use the other skills — then one click: Use prompt, Change something or Copy only.Free
/needt:askingGrill-me: clickable questions in rounds until nothing is assumed. A short mode the other skills use to clarify.Free
/needt:criticTakes a plan apart before launch, gently: every finding is problem → solution → cost → confidence, then the fixed plan in full.Free
/needt:roadmapA project roadmap that survives sessions: milestones as tasks in Needt with blockers, next computed, done only on evidence (a merged PR, a file, your word), an append-only log and a handoff for the next session. In Claude Desktop it is a clickable metro map; "where are we", "what's left", "handoff" all land here.Pro
/needt:learnExplains one thing so it sticks: the mechanism at your level, an example from your own world, a clickable diagram or a map of the subject with what you have already passed, and one check question. No quiz loop.Free
/needt:youtubeAny YouTube link in any message is read first — title, chapters, description, timestamped transcript — and the skill that owns the request works from it. Ask about it, make tasks from it, critique the plan in it.Free
/needt:setupFirst-run interview (plan, connectors, language, memory) and the Needt · readiness line every skill reuses.Free

/needt and /needt:roadmap need a Needt Pro account — it connects to your planner over MCP. Every other skill works without an account.

How it works

Widgets. In Claude Desktop, where the chat can render widgets, the skills show what has a shape as one — today's list with Done buttons, option cards, money metrics, finding cards with Accept fix, a subject map, a project roadmap as a metro map. Everywhere else the same answer arrives as text. Rules: plugins/needt/skills/setup/references/widgets.md.

A first run that asks. The first time a skill fires, setup asks up to four clickable questions — which plan this AI app is on, what to connect, language and tone, memory — and saves the answers as one memory line. Say "у меня Max" or "switch memory off" later and it updates. /needt:setup runs it on demand.

Fits your plan. The readiness line carries budget: pro | max | ultra | …, and every skill scales to it: on Pro, research runs inline and no sub-agents start unless you ask; on Max, independent sweeps run in parallel on Sonnet; on Ultra, up to eight agents with the main model synthesising. Table: plugins/needt/skills/setup/references/delegation.md.

One readiness line. The first skill you use in a chat prints a line like Needt · ready · project: Acme · tone: casual · search: web, youtube, github · questions: click · agents: yes · memory: 12. Every other skill reads it instead of checking again; the first time it appears it says in one line what it is.

Memory that follows you. When you say "remember…", "never do X again", or correct how something was done, the plugin saves one line to your Needt memory (Saved: …) and every skill treats it as a standing instruction — in any chat, on any device. Secrets, health details and one-off facts are never saved. Turn it off any time in the Needt app.

The skills call each other. One skill owns each kind of request and the others hand over in the same reply: a YouTube link → youtube, an unsure fact → search, a missing answer → asking, a sequence that spans sessions → roadmap, work for today → needt. The map of owners and hand-offs: plugins/needt/skills/setup/references/skills-map.md.

Uses your own skills too. The readiness line counts the other skills in your catalog (skills: n), and every Needt skill hands the part they own to them — a deck to your pptx skill, a deploy to your runbook, a campaign to your marketing skill — briefed from what is already known and delivered in the Needt skill's voice. Rules: plugins/needt/skills/setup/references/user-skills.md.

Uses what your AI already has. Skills route to the tools your host exposes — web search, Firecrawl, Exa, GitHub, Context7, YouTube — and say so when something is missing instead of faking it. On first run, setup lists free ways to add the missing ones in a few lines.

Parallel and cheap. Independent research runs in parallel sub-agents on a faster model; synthesis, judgement and verdicts stay with the main model.

Checks what it installs — and itself. Every release passes a 30-scenario eval (eval/), its own SkillSpector scan (risk 25/100, no high findings) and size caps (each skill under 8 KB, each description under 600 characters). Before recommending a new skill, plugin or MCP server, the plugin scans it with NVIDIA SkillSpector when it is installed (risk 51+ means it is not installed), or reads its files for known red flags.

Asks only when it matters. Reversible actions run and get reported in one line. Sending, posting, paying and deleting always wait for your yes.

What's in this repo

plugins/needt/                 the plugin (skills, manifests, MCP connection)eval/                          release gate: scenarios and results per versionrelease.sh, build-standalone.py  gate + build  skills/<name>/SKILL.md       one folder per skill  .mcp.json                    https://mcp.needt.app/mcp.claude-plugin/marketplace.json   Claude Code marketplace.agents/plugins/marketplace.json  Codex marketplaceserver.json                    MCP Registry entryglama.json                     Glama listingassets/                        icon and screenshots

Privacy

The plugin is Markdown instructions, one small Python script for YouTube transcripts (runs only if yt-dlp is installed), and one MCP connection to https://mcp.needt.app/mcp. No hooks, no telemetry. Your assistant reads and writes your own Needt data through that server after you sign in with OAuth; nothing else is sent anywhere by the plugin.

Privacy policy · Terms

Support and contributing

Questions and bugs: open an issue or write to [email protected]. Ideas for a skill, a better trigger phrase in your language, a sharper rule — pull requests are welcome. Run claude plugin validate plugins/needt before sending one.

Changelog: plugins/needt/README.md.

Made by Needt · MIT License

Source: README.md at commit a1e1a5e

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestOct 29, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts