mcpbeat Sign in

Two Minute Toolkit MCP Server

by twominutetoolkit Your server? Claim it
not responding

Two Minute Toolkit is listed as active in the registry but did not answer our last check. It exposes 20 tools.

20 slide-ready chart tools: Gantt, SWOT, 2×2, RACI, org chart, mind map, fishbone. Free.

Uptime history 9 days of history · worst day 0%
9 days agonow
0.0%
Uptime 24h
0 of 92 checks
20
Tools
read from the server
111 ms
Response time
average over 24h
open, no key
Access
streamable-http

Two Minute Toolkit does not always answer

Over the last week it answered 0.6% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

run in your terminal
claude mcp add toolkit --transport http https://www.twominutetoolkit.com/mcp
Settings → Connectors → Add custom connector, then paste this address
https://www.twominutetoolkit.com/mcp
~/.codex/config.toml
[mcp_servers.toolkit]
url = "https://www.twominutetoolkit.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "toolkit": {
      "url": "https://www.twominutetoolkit.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "toolkit": {
      "type": "http",
      "url": "https://www.twominutetoolkit.com/mcp"
    }
  }
}

Available tools 20

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

cycle
create_cycle
Generate a slide-deck-quality cycle diagram: 3–8 stages evenly spaced around a loop, first stage at 12 o'clock running clockwise, joined by arrows that lead from the last stage back to the first, with an optional centre label and a short detail line beside each stage. Two looks: "nodes" (coloured circles on a ring with curved arrows) and "segments" (a ring cut into arrow-shaped segments). Choose it when the process repeats: improvement loops (plan-do-check-act), flywheels, product or customer lifecycles, feedback loops. Use a process diagram instead when steps run once from start to finish, a timeline when dates matter, and hub and spoke when the items surround a centre with no order. Limits: 3–8 stages, names of 1–3 words, details of about 12 words. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
decision
create_decision_tree
Generate a slide-deck-quality decision tree drawn left to right in clean columns of rounded boxes, in the decision-analysis convention: a square where a decision splits into options, a circle where chance splits into events, and a triangle at each end outcome. Branch lines carry an optional `label` ("Yes", "No", an option) and, under a chance node, the probability ("Strong demand · 60%"); end outcomes can carry a numeric `payoff`, lined up in a column at the right (`prefix` "$", `suffix` "m"). Expected values are rolled back automatically once the tree has payoffs and probabilities: every decision and chance node shows its EV, each decision's best option is drawn in the accent colour and the rejected ones are muted with a ‖ prune mark; probabilities that don't add up to 100% are warned about and drawn as given. Node types are inferred (branches with probabilities make a chance node, no branches an outcome, otherwise a decision), so a plain yes/no troubleshooting or eligibility flowchart is just questions with "Yes"/"No" labels and no numbers. Choose it for choosing between options under uncertainty (launch, invest, build vs buy, litigate or settle), expected-value and decision-analysis homework, and yes/no question flowcharts; use an issue tree instead to break a problem or metric into its parts, a chevron process for steps in order, and a Harvey ball matrix to score options against criteria. Limits: 5 levels including the root, up to 5 branches per node, 40 nodes; keep names to a few words. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
ecomap
create_ecomap
Generate a clean ecomap (ecological map, Hartman style) for social work, family therapy, case management and school counselling: the client or household in a solid centre circle with its members listed inside, and 2–12 system circles around it (school, work, extended family, church, health care, probation, friends…), each joined to the centre by a line whose style shows the relationship: strong (thick line), moderate (plain line, the default), tenuous (dashed) or stressful (hatched red line). Arrowheads show the flow of energy or resources: to the system, from it, or both ways. Each system may carry a short detail outside its circle, and a legend of the line styles sits underneath. Choose it to map a person's or family's relationships with outside systems; use a hub and spoke for neutral parts around a centre with no relationship quality, a mind map when the items branch further, and an org chart for reporting lines. Limits: 2–12 systems, 0–8 household members, system names of 1–3 words, details of about 10 words. Use first names or roles only; never put identifying client details in the chart. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
fishbone
create_fishbone
Generate a slide-deck-quality fishbone diagram (Ishikawa or cause-and-effect diagram) for root-cause analysis: a horizontal spine ending in a head box that holds the problem, with 1–8 category bones angled off it, alternating above and below, each named in a coloured pill and carrying up to 6 causes, and each cause up to 3 sub-causes. Standard category sets fill in unnamed categories: 6M for manufacturing (People, Machine, Method, Material, Measurement, Environment), 8P for services and 4S for the service industry. Choose it for quality, Lean and Six Sigma (DMAIC Analyze) work, healthcare quality improvement, incident reviews and any "why does this keep happening" slide; use an issue tree for a MECE logic or KPI breakdown, a mind map for an open brainstorm, a SIPOC to scope a process, and the lab fishbone (create_lab_fishbone) for lab value skeletons such as BMP or CBC, which is a different thing. Infer 4–6 categories and 2–4 causes each from the problem rather than asking. Limits: 1–8 categories, 6 causes per category of about 2–7 words, 3 sub-causes per cause. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
five
create_five_forces
Generate a slide-deck-quality Porter's five forces diagram laid out as the classic cross: competitive rivalry in the centre, threat of new entrants above, threat of substitutes below, bargaining power of suppliers on the left and of buyers on the right, with arrows pointing in at the centre. Each box has a header band with the force's name, an optional rating pill (very low, low, medium, high, very high; green, amber or red) and up to 5 short bullets of evidence; an optional conclusion line sits underneath. Choose it to assess an industry's attractiveness or competitive pressure for a strategy, market-entry, investment or case-interview slide. Use a Harvey ball matrix to score several options against criteria, a hub and spoke for items around a centre with no fixed meaning, and a mind map for open-ended brainstorming. All five forces are required (an empty object {} is fine); infer sensible ratings and bullets from the industry rather than asking. Limits: 5 bullets per force of about 4–10 words, a conclusion of one sentence. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
football
create_football_field
Generate a slide-deck-quality football field chart, the valuation summary used in banking and corporate-development decks: one floating horizontal bar per method from its low to its high value on a shared axis with round gridlines, the method name and an optional assumption line ("8.0x–10.0x EV/EBITDA") on the left, low and high values printed at the bar ends, up to 3 dashed marker lines (current share price, offer price) and an optional shaded implied range. Choose it for valuation ranges (DCF, trading comps, precedent transactions, 52-week range, analyst targets, LBO) and for any comparison of low–high ranges on one scale, such as salary bands, cost or estimate ranges, or price ranges by scenario. Use a timeline (Gantt) when the ranges are dates, a Harvey ball matrix for scores against criteria, and a pyramid/funnel for stage volumes. Values are plain numbers; set prefix ("$", default), suffix ("m", "/sh", "x") and decimals for display. Limits: 1–12 rows, 0–3 markers; a low above its high is swapped with a warning. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
harvey
create_harvey_matrix
Generate a slide-deck-quality Harvey ball matrix: options as rows scored against criteria as columns, every cell drawn in one style (Harvey balls 0–4 from empty to full, ticks 0/1, or 0–5 dots), with an optional highlighted 'Recommended' row, an optional notes column (appears when any row has notes) and a legend. Choose it to compare vendors, tools, plans or features side by side; use a timeline when the point is WHEN work happens, a process for ordered steps, a pyramid/funnel for a hierarchy or narrowing stages, and a hub and spoke, mind map or org chart for relationships. Limits: 2–12 rows, 1–8 criteria, row names up to 40 characters; scores outside the style's range are clamped and null leaves a cell blank. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
hub
create_hub_spoke
Generate a slide-deck-quality hub and spoke diagram: a large central hub circle with 3–10 coloured satellite cards evenly spaced around it, each joined to the hub by a spoke, with an optional short detail beside each satellite and optional arrowheads (out from the hub, or both ways). Choose it when several items relate to one centre with no order between them: a platform and its products or integrations, a team and its stakeholders, a core value and its pillars, a company and its partners. Use a cycle when the items form a repeating sequence, a process diagram for one-way steps, a mind map when the satellites branch further, and an org chart for reporting lines. Limits: 3–10 spokes, one level only, names of 1–3 words, details of about 12 words. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
issue
create_issue_tree
Generate a slide-deck-quality issue tree or driver tree: a key question, problem or top-line metric on the left, broken down left to right into drivers, sub-drivers and hypotheses in clean columns of rounded boxes joined by elbow connectors. Each first-level branch takes its own palette colour. Any box can carry a `value` ("$12.4m", "+3% YoY") and any parent an `operator` ("+", "-", "x", "/", drawn as + − × ÷ where its children join) for KPI and value driver trees (Profit = Revenue − Costs; Revenue = Customers × Revenue per customer); `levels` labels the columns and `numbered` adds 1, 1.1, 1.1.1. Choose it for consulting issue trees and MECE breakdowns, hypothesis trees, KPI, value and driver trees, root-cause and problem trees: anything where a parent is logically made up of its children. Use a mind map instead for loose brainstorms radiating from a centre with no hierarchy logic or values, and an org chart for people and reporting lines. Limits: 4 levels including the root, up to 6 children per box, 40 boxes; keep labels to a few words. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
lab
create_lab_fishbone
Generate clean lab fishbone diagrams (lab value skeletons), the shorthand nurses, residents and students use in notes and case presentations: BMP / Chem-7 (Na | Cl | BUN over K | HCO3 | Cr with glucose in the tail), CBC (WBC > Hgb over Hct < Plt), coags (PT | PTT over INR), LFT (TP | AST | T bili over Alb | ALT | ALP), ABG (pH / pCO2 / pO2 / HCO3) and Ca/Mg/Phos, each with an optional caption such as a time, in a tidy grid. Numeric values outside adult reference ranges are flagged red with ↑ or blue with ↓ (US or SI ranges; overridable per value), and the result also includes a plain-text version to paste into a note. Choose it whenever lab results should be shown in fishbone form; it is not a cause-and-effect (Ishikawa) diagram, for which use create_fishbone. Values are strings of up to 8 characters; 1–8 panels. A drawing aid only, not clinical decision support: never include patient names or identifiers, because links carry the data. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
mind
create_mind_map
Generate a slide-deck-quality mind map: a central topic pill with up to 8 colour-coded branches of sub-topics radiating left and right (or all to the right, like an outline), joined by smooth tapered curves. Choose it for brainstorms, idea or theme breakdowns, workshop outputs, feature or research groupings and anything that unpacks ONE central idea into related topics with no order or reporting line; use an org chart instead for people and who reports to whom, a hub and spoke for one centre with a single ring of peers, and a process or cycle when the order matters. Nest sub-topics in `children` under each branch. Limits: 8 branches, 3 levels below the centre, 50 topics; keep labels to a few words. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
org
create_org_chart
Generate a slide-deck-quality org chart: a tree of people cards (name, role, initials circle) joined by elbow connectors, top-down or left-right. Colour is automatic: each team under the root (each of the root's direct reports and everyone below them) gets its own palette colour; set `color` on a card only to override that. Choose it whenever the point is WHO reports to or works with whom: reporting lines, project or engagement teams, governance and steering structures. Use a mind map instead for ideas or topics radiating from a central theme, and a hub and spoke for one centre with peers around it. Nest people in `children` under `root`; more than 4 reports with no reports of their own are stacked in a column automatically. Limits: 60 people, 5 levels. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
process
create_process
Generate a slide-deck-quality chevron process diagram: 2–7 phases drawn as arrow-shaped chevrons left to right, each with an optional timing line ("Weeks 1–2") and up to 5 short bullets beneath it, and an optional "you are here" highlight on one phase. Choose it for an "our approach" or methodology slide, delivery phases, a sales or onboarding process, or any short linear sequence where the ORDER of the phases matters; use a timeline instead when exact dates and overlapping durations matter, a cycle diagram when the last step loops back to the first, and an org chart or mind map for branching structures. Limits: 2–7 steps, up to 5 bullets per step; keep step names to one to three words and bullets to a short phrase. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
pyramid
create_pyramid
Generate a slide-deck-quality pyramid or funnel: 2–8 stacked layers in even steps, narrow at the top in pyramid mode (a hierarchy of needs, a strategy pyramid, foundations to vision) or wide at the top in funnel mode (sales, marketing or hiring funnels). Each layer has a name and an optional detail line beside it. Choose it when items stack in a ranked order or narrow down stage by stage; use a process diagram for a sequence of phases of equal weight, a cycle for a loop, a hub and spoke for parts around a centre, and a timeline when dates matter. Limits: 2–8 layers; keep names to one to four words and details to one short sentence. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
quadrant
create_quadrant_matrix
Generate a slide-deck-quality 2×2 matrix, the classic consulting quadrant slide: two labelled axes (name plus low and high ends, rotated on the left) and four quadrants tinted in one accent colour. Two modes: "plot" places items as dots at x and y on 0–10 scales (or bubbles sized by `size`), with every label placed automatically so none overlap and quadrant names faint in the corners; "list" gives each quadrant a bold name and up to 6 bullets. Choose it to prioritise or position things on two dimensions: tasks, initiatives, features, products, brands, stakeholders or risks. Pick the preset that matches the request and let it supply the standard axes, quadrant names and mode: impactEffort for impact vs effort, quick wins or an action priority matrix; eisenhower for urgent vs important or a to-do list; bcg for a growth-share or product portfolio matrix (give revenue as size); ansoff for growth strategy (products × markets); powerInterest for a stakeholder map; perceptual for a perceptual or competitive positioning map (rename the axes to the user's attributes); riskLikelihood for a likelihood vs impact risk grid; none for any other 2×2 (name the axes and quadrants yourself; an omitted preset means none). Quadrants are keyed by position: topLeft, topRight, bottomLeft, bottomRight; with normal axes topRight is high x, high y. Use a Harvey ball matrix to score options against several criteria, create_five_forces for one industry's competitive forces, and create_swot for strengths, weaknesses, opportunities and threats. Infer realistic positions from context rather than asking. Limits: 30 items, names up to 40 characters (1–4 words read best), 6 bullets per quadrant. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
raci
create_raci
Generate a slide-deck-quality RACI matrix (responsibility assignment matrix): tasks or deliverables as rows, roles or teams as columns, and each cell a rounded letter chip, R Responsible, A Accountable, C Consulted or I Informed, with "A/R" for an owner who also does the work and `model: "RASCI"` adding S for Support. Rows can be grouped into phases with `type: "section"` rows; a legend explains the letters. With `checks` (default on), tasks without exactly one A or without an R get an amber note at the row end ("No A", "2 As", "No R") and every broken rule is returned in `warnings`; give every task exactly one A and at least one R unless the user's data says otherwise. Choose it for project roles and responsibilities, PMO governance, onboarding and handover plans, and any "who does what" slide; use a Harvey ball matrix instead to score options against criteria, an org chart for reporting lines, and a timeline when the point is when work happens. Limits: 1–10 roles and up to 30 rows (tasks plus sections); keep task names to a short verb phrase and roles to a job title. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
sipoc
create_sipoc
Generate a slide-deck-quality SIPOC diagram: five equal columns headed by big coloured letters, Suppliers, Inputs, Process, Outputs and Customers, with chevrons between them for the flow. Suppliers, inputs, outputs and customers are stacked cards; the process is 2–7 numbered step boxes joined by down arrows, with an optional process name and optional "Starts when" and "Ends when" boundaries. Choose it for Lean and Six Sigma project scoping (the Define phase of DMAIC), process-improvement kick-offs, quality and ISO documentation, and any slide that frames a process by who feeds it and who it serves; use a chevron process instead for a simple left-to-right sequence of phases with no inputs or outputs, an issue tree to break a problem into causes, and a timeline when dates matter. Limits: 1–7 steps (2 or more expected), up to 8 items in each of the other four columns; keep each item to a short phrase and start steps with a verb. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
stop
create_stop_start_continue
Generate a slide-deck-quality Stop Start Continue chart: three equal columns, Stop (red, a stop-sign marker), Start (emerald, a play marker) and Continue (sky, a circular-arrow marker), each a softly tinted panel with up to 8 bullets, plus an optional subject ("Sprint 14 retro") and an optional conclusion band for the agreed actions. Set `order: "start-stop-continue"` when the user puts Start first; rename columns with `labels` (e.g. { "continue": "Keep doing" }). Choose it for sprint and project retrospectives, team or manager feedback, and reviews of a process, project or habit; use create_swot for a strategic assessment of a company or product, a Harvey ball matrix to score options against criteria, and a mind map for an open-ended brainstorm. All three lists are optional, but fill all three; infer 3–5 bullets each from context rather than asking. Limits: 8 bullets per column of about 3–8 words, column names of 1–3 words, a conclusion of one sentence. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
swot
create_swot
Generate a slide-deck-quality SWOT analysis laid out as the classic 2×2 grid: Strengths (top left) and Weaknesses (top right) as the internal row, Opportunities (bottom left) and Threats (bottom right) as the external row, each a softly tinted panel with its big coloured letter and up to 8 bullets, with optional Helpful / Harmful and Internal / External axis labels, an optional subject ("Acme Coffee, FY26") and an optional one-line conclusion underneath. Choose it to assess a company, product, team, project or person for a strategy, business-plan, marketing or coursework slide; use Porter's five forces (create_five_forces) for the pressures on a whole industry, a Harvey ball matrix to score options against criteria, and an issue tree to break one problem down. Only `strengths` is required (an empty [] is fine), but fill all four; infer 3–5 bullets each from context rather than asking. Limits: 8 bullets per quadrant of about 3–8 words, a conclusion of one sentence. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.
timeline
create_timeline
Generate a slide-deck-quality Gantt timeline: task bars and milestone diamonds laid out across numbered time columns (weeks, sprints, months), with optional labelled section bands that group tasks into phases. Choose it for project plans, roadmaps, launch schedules and anything where WHEN each piece of work happens is the point; use a process diagram instead when only the order of phases matters. Limits: 2–52 columns, up to 100 rows. Set duration 0.25 for a milestone. Infer missing details rather than asking; the user can adjust the chart in the builder through the Edit link. ALWAYS give the user the image link: inline chat images usually cannot be saved, but the link renders the exact chart on demand and can be pasted into a slide or Markdown.

Endpoints

URLTransportStateLatencyChecked
https://www.twominutetoolkit.com/mcp streamable-http answering 111 ms 1 min ago

Alternatives to Two Minute Toolkit

same job, measured the same way
Dirtsmith outside-tools rate sheet
by workers-bfurrow26-dirtsmith-go

Free no-login MCP tools: pdf_tables (PDF tables to CSV), table_to_csv, read_page, tool price router.

15 tools answering
R
ReadyKit File Diagnostics and Repair
by valentinechuu

Free CSV and SRT diagnostics with deterministic $3 one-file repairs.

8 tools answering
ApexCharts
by apexcharts

Generates and validates configs for ApexCharts charts, grid, gantt, tree, sankey, stock and maps.

1 876 installs/wk 23 tools answering
Jeda AI
by jeda

Visual AI for strategic thinking — SWOT, flowcharts, mindmaps, Gantt diagrams as polished SVG.

5 tools answering
OndaCast
by ondacast

Find live radio stations, podcasts, free audiobooks, song charts and the radio guide on OndaCast.

9 tools answering
Fxabsolute
by varsansri

Five years of 1-minute forex, index and crypto candles, plus a live bridge to a trader's chart.

47 installs/wk local only
Ciro Cesar Maciel — Free Tools
by ciromaciel

Free, no sign-in: favicons, web to Markdown, CSV to chart, text to speech, time zones, passwords.

9 tools answering
Zovo Project Timeline
by theluckystrike

A Gantt chart maker and project timeline planner that works inside the chat.

2 tools answering

Two Minute Toolkit — questions

Answers built from our own checks of this server.

What can Two Minute Toolkit do?
It exposes 20 tools, read directly from the server on our last check. Among them: create_cycle, create_decision_tree, create_ecomap, create_fishbone, create_five_forces, create_football_field and 14 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Two Minute Toolkit working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 92 checks got a reply (0.0%), average response time 111 ms. The bar chart above shows every period we have measured.
The registry lists Two Minute Toolkit as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect Two Minute Toolkit?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Two Minute Toolkit need an API key?
No. Two Minute Toolkit completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 20 of them are readable on this page. This is what we observed, not what the docs claim.