
OneLessTool MCP server
Which MCP servers are OneLessTool's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-27
- Registry namecom.onelesstool/onelesstoolverified in the MCP registry
The registry name sits under onelesstool.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools9
- Server calls itselfonelesstool
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 277 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 5 of 9 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer679 ms
- Space in an agent's context≈ 1,701 tokensthe definitions of all its tools (9), which an agent carries on every turn
- Tool definitionsA · 91 of 100
- Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 5 of 9
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_catalogNatural-language search across software products, capabilities (what software does) and replacement workflows. Understands synonyms, e.g. 'make thumbnails' finds YouTube thumbnail workflows. Returns ranked hits with URLs, plus the tool…
get_toolFull structured profile of a software product: plans and prices (with evidence status and verification date), capabilities with fit and limitations, honest reasons it's hard to replace, risks, related replacement workflows and sources.
find_alternativesFor a specific product (e.g. Canva), list each capability it provides and the best alternatives — ranking tools the user ALREADY owns first at $0 extra. Pass the capabilities the user actually uses (from get_tool) for a precise answer…
compare_solutionsFor one capability (e.g. 'youtube-thumbnails', 'crm-contacts', 'workflow-automation'), compare all known tools: fit, quality scores on the dimensions that matter, required skill, cheapest qualifying plan and limitations.
find_workflowsFind practical, step-by-step workflows that replace a paid tool or accomplish an outcome with tools the user already owns. Filter by tool being replaced, capability, or free-text query.
get_workflowFull replacement guide: before/after, required tools and extra cost, setup steps, copyable prompts, templates/scripts, limitations, risks, a verification checklist to run BEFORE cancelling, and the savings methodology.
recommend_stackGiven the outcomes the user needs (free text or capability slugs) and what they already own, recommend per-capability options (owned tools at $0 first) and a minimal stack covering everything, with incremental monthly cost and warnings…
estimate_savingsAudit the user's subscriptions. For each: keep, downgrade, redundant, test_replacement, review_unused or keep_critical — with the arithmetic. Savings are split into 'likely' and 'possible' and never double-counted. Costs are what the user…
get_pricingList plan prices for one tool or all tools, each with evidence status, verification date and source URL.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"onelesstool": {
"type": "http",
"url": "https://onelesstool.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http onelesstool https://onelesstool.com/api/mcpclaude.ai, ChatGPT and other clients: add https://onelesstool.com/api/mcp as a custom connector in the settings.
OpenAPI spec
11 paths, read 2026-10-27. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.