Actuent vs Next AI Draw IO
A side-by-side look at the Actuent and Next AI Draw IO MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Actuent for developer tools work over a hosted endpoint; choose Next AI Draw IO for developer tools as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Actuent when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a remote HTTP/SSE transport.
- Its auth model fits you: other.
- You want tools like
actuent_search, actuent_account, actuent_actions.
Choose Next AI Draw IO when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You want tools like
get_drawing_guide, get_shape_library, start_session.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Developer Tools | Developer Tools |
| Quality signal | 75/100 · Great | 73/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | other | API key required |
| Pricing | Freemium | BYOK (pay the provider) |
| Required env vars | None listed | None listed |
| Verified owner | Verified | Community listing |
| GitHub stars | — | 36,391 |
| Directory activity | 5 views 0 installs 1 upvotes | 6 views 0 installs 0 upvotes |
| Tools | 13 | 16 |
| Full listing | View Actuent | View Next AI Draw IO |
Tools & capabilities
Actuent tools 13
actuent_searchUse this for anything current or real-world the user asks about: places, opening hours, prices, products and shops, events, what a company or website offers, comparisons ('X vs Y'), or checking a fact on a site. Search Actuent for any topic, keyword, domain or page, in any language — plain questions work too ('where can I buy running shoes in London?'). Returns ranked LAWP (structured JSON for websites, in English), each with a snippet, a match score (0-100) and why it matched; for shopping searches, products with prices; for local searches, businesses in that city (or OpenStreetMap places); for event searches, upcoming events. May include did_you_mean, related searches, an answer (sentences from a site's own pages, for questions like 'does basecamp have a free plan'), a comparison (for 'notion vs obsidian'), for Pro a short summary answer with numbered sources (for question searches), and a message to pass on to the user. Prices in searches ('shoes under 500 dkk in copenhagen') find products from shops in that market. When you give the user a link to a site or product, use its visit_url. Also: • kind "similar" + domain: sites like a given one ("alternatives to mailchimp.com"). • kind "trending": the most searched sites and queries on Actuent right now. • kind "news" + query: the latest news articles on a topic, with sources, links and dates.actuent_accountThe user's own Actuent data. Pro. With kind "preferences", only when the user asks you to remember (or forget) something: their preferences (vegan, wheelchair, jazz…), home city or currency are then used on their later searches whenever you don't pass your own. • Get the search history for this API key — every query made through Actuent. Pro only. • The user's site accounts connected to Actuent (for actions like 'reorder my last order'). action: list (default), connect (returns a link for the user to sign in to the site once), or disconnect. Pro only.actuent_actionsWhat an AI agent can do on a site, and doing it. domain alone: list the site's actions. domain + action_id (+ input): perform one (book, contact, sign up…; confirm with the user first when it costs money or sends something). domain + status_url: check an action that returned pending (Pro). • Get all available actions for a specific site. Returns what an AI agent can actually do on that site. • g. book, contact, sign up). Sites that publish LAWP action endpoints are called directly and the site's response is returned; for other sites it returns where the user can complete it (executed: false). • Check a long-running action that returned pending, using its status_url. Pro only.actuent_aboutEverything Actuent knows about one named thing (a band or artist, company, brand, venue, landmark or place), joined up in one record: what it is, genres, country, official website, a short Wikipedia summary, its site in Actuent's index, its upcoming events (e.g. a band's concerts) and its products with prices (e.g. a shoe brand). For "tell me about Cat Power and when she's playing", "what is Hoka and what do their shoes cost". Add a word when a name is ambiguous ("Patagonia clothing").actuent_get_pageRead a web page or a whole site. Give url to read one page live; domain alone for a short summary of a site; domain (or url) plus question to answer a question from the site's own pages. • "). Returns the page as structured data: clean text, products with price and stock (on Shopify shops also each size or colour with a cart link that opens the cart with it), events, the business with opening hours and whether it's open now, recipe, FAQ, article details and the page's main links. txt. • Get a single plain English paragraph summarising any website. Faster than actuent_search when you just need the gist, not the full LAWP. • g. '). Returns the matching pages and sentences in the site's own words, plus related actions.actuent_compareCompare two or more sites side by side using their LAWP data, or two or more products (URLs from actuent_search products): price, stock, price history and cheaper shops.actuent_nearbyPlaces near the user or in a city, with opening hours and whether they're open right now: cafés, restaurants, bars, shops, pharmacies, gyms and more. For questions like "coffee near me", "is anything open now?", "where can I eat tonight in Brooklyn?", "bars open late", "dog-friendly café in Copenhagen" or a chain's branches ("what time does Trader Joe's close in Brooklyn?": query the chain's name, each branch has today's hours and closes_at). Also returns businesses from Actuent's index with details from their own websites (rating, services with prices, booking). Also: • kind "service": a specific service or menu item with its price at local businesses, from their own websites (max_price, currency).actuent_planPlan a timed itinerary of places to go: e.g. "plan my evening", "dinner then drinks in Nørrebro", "brunch and a museum on Sunday". Chooses restaurants, bars, cafés and sights that are open when you'd arrive and close to each other, with walking times. For finding or listing events ("what's on today", "find events") actuent_events is the tool. Also: • kind "trip" (or days): a 1–4 day city trip — where to stay and a timed plan for each day.actuent_cartPut products (URLs from actuent_search products) in a basket: returns one link per shop that opens the shop's checkout with the items in it, so the user just reviews and pays. Nothing is bought.actuent_eventsFind events and what's on: concerts, comedy, theatre, club nights, festivals, markets, exhibitions, classes, walks and other events today, tonight, this weekend or on any date, in a city. For questions like "find events in cph today", "what's on in cph today?", "anything fun tonight?", "concerts in New York this weekend", "things to do in London on Saturday" or "when is Ray LaMontagne playing?". Returns current listings from venues' own websites (listings change daily): name, time, venue, price, ticket link and, for concerts, the genre. Each event has tickets_url, add_to_calendar (a calendar file) and add_to_google_calendar links, and directions: to put an event in the user's calendar, give them the link to tap (you can't add it yourself), no need to search again. A genre in the query finds concerts of that kind ("jazz in copenhagen this weekend", "techno tonight"). Use when: "tonight" for what's on tonight.actuent_watchWatch something for the user and email them (optionally a webhook) when it changes. Pro. Set kind; action list shows what's watched, remove stops one. • Watch a product (from actuent_search products) and get an email, and optionally a webhook, when its price drops or when it's back in stock. Also lists or removes watches. Pro only. • Watch any web page and get an email (and optionally a webhook) when it changes, or when certain words appear or disappear: "tell me when tickets for Cat Power go on sale" (phrase 'tickets on sale', appears), "tell me when this is back in stock" ('sold out', disappears), "let me know when this page changes". Checked daily. Also list and remove watches. • g. 'vegan café copenhagen' or 'ai note taking app'. Checked daily.actuent_feedbackWhen the user says an Actuent answer was wrong, outdated or missing something ("that place closed", "those times are wrong", "it missed the obvious one"), report it here so it gets fixed: which tool, the question, what was wrong and what the right answer would be. Takes a second; tell the user it was passed on.- +1 more on the listing page
Next AI Draw IO tools 16
get_drawing_guideReturn the drawing guide: XML format, layout, edge routing, style and editing rules. start_session already returns it; call this only if the guide is no longer in your context. With topic, returns a short XML reference for tables, layers or groups.get_shape_libraryGet the style syntax and shape names of a draw.io icon library. Call this BEFORE drawing with cloud, network or other icon shapes, and use the exact names it returns; never guess them. Libraries: - Cloud: aws4, azure2, gcp2, alibaba_cloud, openstack, salesforce - Networking: cisco19, network, kubernetes, vvd, rack - Business: bpmn, lean_mapping - General: flowchart, basic, arrows2, infographic, sitemap - UI/Mockups: android, material_design - Enterprise: citrix, sap, mscae, atlassian - Engineering: fluidpower, electrical, pid, cabinets, floorplan - Icons: webiconsstart_sessionStart a new diagram session, or continue a saved one with session_id, and open the browser for real-time preview. Starts an embedded server and opens a browser window with draw.io. The browser will show diagram updates as they happen. The result includes the drawing guide; follow it when drawing.list_saved_diagramsList the diagrams saved by earlier sessions (auto-save files), newest first, with their pages. Continue one with start_session session_id=<id>; the file path also works with load_diagram.create_new_diagramCreate a NEW diagram, REPLACING the whole document: every page and any unsaved user changes (the previous state stays in History). To add a tab use add_page; to change cells use edit_diagram. Before using icon shapes (AWS, Azure, GCP, Kubernetes, Cisco...), call get_shape_library first. Follow the drawing guide returned by start_session (call get_drawing_guide if it is no longer in your context). Pass screenshot: true on the last call of a complex diagram to check the result. Accepted xml: 1) Only the mxCell elements of one page (recommended). The server adds <mxfile>, <mxGraphModel>, <root> and the root cells "0" and "1": <mxCell id="2" value="Shape" style="rounded=1;" x="40" y="40" w="120" h="60"/> 2) A bare <mxGraphModel> with <root> (one page). 3) A full <mxfile> with one or more <diagram> pages. Every page's <root> must start with <mxCell id="0"/><mxCell id="1" parent="0"/>. Rules: cells are siblings (never nested), ids are unique per page and start from "2", parent only for shapes inside a container, no XML comments, and shapes stay within x 0 to 800 and y 0 to 600. A style used by several cells is defined once with <mxStyle name="..." value="..."/> before the cells and used by name (see the drawing guide); html=1 and whiteSpace=wrap are added automatically. To clear the canvas to one blank page, send only the two root cells <mxCell id="0"/><mxCell id="1" parent="0"/>; the previous diagram stays in History.load_diagramLoad a .drawio diagram into the current session, REPLACING the entire diagram (all pages). To change an existing file, load it here, edit with edit_diagram, then export_diagram to the same path; never rewrite the file by hand. Provide ONE of two mutually exclusive sources: 'path' (the server reads the file from disk — you do NOT need to read the file yourself or pass its XML through create_new_diagram) or 'xml' (the raw file content you already have — from another tool, a repository read, or an API response — so no temporary file needs to be written first). Both accept plain XML and draw.io's compressed save format. .drawio.svg (Editable SVG, the format export_diagram writes) is accepted too; .png files (also draw.io's editable PNG) and plain .svg files cannot be loaded. After loading from 'path' (or from compressed 'xml'), call get_diagram before edit_diagram — you haven't seen the file's cell IDs yet. Plain-XML 'xml' content you supplied yourself is already known and can be edited immediately.edit_diagramEdit a specific page in the current diagram by ID-based operations (update/add/delete cells). All-or-nothing: if any operation fails, nothing is applied and every failure is listed. Freshness: the server remembers the last diagram state you have seen, and rejects this call only if the user edited the diagram in the browser since then. You do NOT need to call get_diagram before every edit: a rejected call changes nothing and includes the current XML of the page, so you can rebuild your operations and retry. Call get_diagram first only when you don't know the current diagram content (cell IDs, structure) — e.g. the diagram wasn't created in this conversation, or you're unsure your memory of it is accurate. Multi-page targeting: - page_id / page_name / page_index are optional; when all omitted, the FIRST page is targeted - Use list_pages to discover what pages exist Operations: - add: Add a new cell. Provide cell_id (new unique id within the page) and new_xml. One cell per operation. - update: Replace an existing cell by its id. Provide cell_id and complete new_xml. - delete: Remove a cell by its id. Only cell_id is needed. Its children and connected edges are deleted too, so give only a container's id. For add/update, new_xml is the complete mxCell (inside its <object> wrapper when it has custom data, see the drawing guide) in the compact form (a shape with x, y, w, h; an edge with source and target). No XML comments. Every " inside new_xml must be escaped as \" in the JSON. Example - Add a rectangle on the default (first) page: {"operations": [{"operation": "add", "cell_id": "rect-1", "new_xml": "<mxCell id=\"rect-1\" value=\"Hello\" style=\"rounded=1;\" x=\"100\" y=\"100\" w=\"120\" h=\"60\"/>"}]} Example - Delete a cell on the default page: {"operations": [{"operation": "delete", "cell_id": "rect-1"}]}get_diagramGet the current diagram XML (fetches latest from browser, including user's manual edits). Call this when you don't know the current diagram content (cell IDs, pages, structure) — e.g. before editing a diagram you didn't create in this conversation, or after edit_diagram was rejected because the user changed the diagram in the browser. Returns the full <mxfile> by default. If a page selector is provided, returns just that page's <mxGraphModel> embedded in a one-page <mxfile> wrapper.get_selectionReturn the cells the user has selected in the preview: their ids and labels, for edges the source and target ids, for shapes the position and size, and the page they are on. Call this when the user refers to what they selected ("this box", "these arrows", "the selected shapes"), then act on the ids with edit_diagram. Says when nothing is selected. Needs the preview tab to be open.screenshot_diagramRender the diagram in the preview and return it as a PNG image, so you can see your own result. Call this once after drawing or heavily editing a complex diagram, then fix overlaps and edges that cross shapes. Without a page selector it shows the page on screen; with one it renders that page without changing what the user sees. Needs the preview tab to be open.export_diagramExport the current diagram to a file. Supports .drawio (XML), .png, .svg, and .drawio.svg (an SVG with the diagram embedded, which draw.io and load_diagram can open again). The format is auto-detected from the file extension, or can be specified explicitly. Images get a 20 px margin; a PNG has a white background (or the page's own background color) unless transparent is true. Multi-page behaviour: - .drawio with NO page selector: writes the full <mxfile> (all pages). - .drawio with a page selector: writes a single-page <mxfile> containing only that page. - .png / .svg with NO page selector: exports the currently active page in the browser. - .png with a page selector: renders that page without changing what the user sees. - .svg / .drawio.svg with a page selector: temporarily loads that page into the browser, captures it, then restores the full document (the user sees a brief flicker).list_pagesList every page (tab) in the current diagram. Returns each page's id, name, 0-based index, and cell count. Use this to discover what pages exist before targeting one with edit_diagram, get_diagram, export_diagram, rename_page, or delete_page.- +4 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Actuent
{
"mcpServers": {
"actuent": {
"command": "npx",
"args": [
"-y",
"actuent"
]
}
}
}
Next AI Draw IO
{
"mcpServers": {
"next-ai-draw-io": {
"command": "npx",
"args": [
"-y",
"@next-ai-drawio/mcp-server@latest"
]
}
}
}
Frequently asked questions
Actuent is categorized under Developer Tools and uses a remote HTTP/SSE transport. Next AI Draw IO belongs to Developer Tools and uses a local stdio subprocess. Pick Actuent for developer tools work and Next AI Draw IO for developer tools.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Actuent is listed as freemium — a free tier with paid plans. Auth: other. Next AI Draw IO is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add actuent and next-ai-draw-io as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Actuent has a quality signal of 75/100 (Great) with 5 views, 0 installs and 0 GitHub stars. Next AI Draw IO has 73/100 (Great) with 6 views, 0 installs and 36,391 GitHub stars.