Actuent vs Jevcore MCP
A side-by-side look at the Actuent and Jevcore MCP 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 Jevcore MCP 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 Jevcore MCP when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- You want tools like
jev_ask, jev_rank, jev_check.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Developer Tools | Developer Tools |
| Quality signal | 75/100 · Great | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | other | Not declared |
| Pricing | Freemium | Free |
| Required env vars | None listed | None listed |
| Verified owner | Verified | Community listing |
| GitHub stars | — | 102 |
| Directory activity | 5 views 0 installs 1 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 13 | 3 |
| Full listing | View Actuent | View Jevcore MCP |
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
Jevcore MCP tools 3
jev_askAsk TypeSafe Jev one or more typed questions about a single piece of state. Jev does not generate text: it returns a selected option and calibrated probabilities. Use it for judgments the rest of the work branches on — routing, classifying, scoring, triaging. Do NOT use it to write prose, explain, summarize, or generate code. Question types: "noul" is yes/no and returns the probability of true; "choice" picks one of the criteria keys you declare; "score" places the state on an ordered scale whose levels you declare in ascending order. A noul may also declare "boundary" — what true means and what false means — which is worth supplying whenever the line between them is not obvious. Batch related questions into one call: they are answered against the same state in one round-trip. A score question answers with a numeric "score" that may fall between levels, a "legend" mapping each level index to its description, and probabilities per level. This tool returns probabilities, not decisions — apply your own confidence threshold before acting, and treat a low-confidence answer as unknown rather than picking for it.jev_rankRank a list of candidates by how well each satisfies one stated criterion. Returns every candidate with an independent relevance probability, sorted. Use it to order search hits, triage a backlog, or find the one item that answers a question. The probabilities are independent per-candidate judgments, NOT a distribution that sums to 1. A flat set of scores means "none of these stands out", not a fine-grained ordering. What you send is capped, and the two caps behave differently. The candidate list is truncated at 16,000 characters, and the reply carries `truncated: true` when that happens — check for it, because a cut list is still ranked and the scores then describe what Jev actually read rather than what you sent. The generated questions are refused at 4,000 characters instead: exceeding that gives you an error asking for fewer or smaller items, never a silent best-N, so retrying the same call cannot help. Because the criterion is repeated into every candidate's question, that second cap is what bounds the candidate count — measured, an ordinary criterion fits 20 candidates and a 400-character criterion fits 7, while candidate length does not change the count at all and only starts truncating the list past roughly 1,600 characters per candidate.jev_checkCheck whether a piece of evidence supports a specific claim. Returns "supported", "contradicted", "conflicted", "insufficient", or "unknown", with the underlying probabilities. The distinction between "not supported" and "contradicted" is the reason to use this rather than reading the evidence yourself. It judges one claim against the evidence you give it. It does not search for evidence, and it cannot detect that you omitted the decisive passage.
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"
]
}
}
}
Jevcore MCP
{
"mcpServers": {
"jevcore-mcp": {
"command": "npx",
"args": [
"-y",
"jevcore-mcp"
]
}
}
}
Frequently asked questions
Actuent is categorized under Developer Tools and uses a remote HTTP/SSE transport. Jevcore MCP belongs to Developer Tools and uses a local stdio subprocess. Pick Actuent for developer tools work and Jevcore MCP 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. Jevcore MCP is listed as free. 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 jevcore-mcp 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. Jevcore MCP has 67/100 (Great) with 0 views, 0 installs and 102 GitHub stars.