
Private AI Tools MCP server
Which MCP servers are Private AI Tools'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 2026-11-03
- Registry namecom.private-ai-tools/toolsverified in the MCP registry
The registry name sits under private-ai-tools.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-03
- Tools3
- Server calls itselfprivate-ai-tools
- Server version1.0.0
- Protocol version2025-06-18
On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 235 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
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: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer298 ms
- Space in an agent's context≈ 716 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · upscale photos and short videos with AI
- not sure · remove photo backgrounds to get transparent PNGs
- not sure · compress videos and convert files between formats
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
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 →
find_toolsSearch the 144 free tools of Private AI Tools (PDF, image, video, audio, developer, data, calculators…) by task, e.g. "compress pdf", "remove background" or "json to yaml". Returns up to 8 tools, best first, with their page URL; when no…
list_toolsList every tool of Private AI Tools, or the tools of one category, with their page URL. The tools run in the user's web browser: give the user the link. Files are never sent to this server or to the assistant.
get_toolDetails of one tool by its slug (from find_tools or list_tools): name, description, page URL in every language, and the in-page agent tools (WebMCP) that a browser agent can call once the page is open. The tools run in the user's web…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"tools": {
"type": "http",
"url": "https://private-ai-tools.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http private-ai-tools https://private-ai-tools.com/mcpclaude.ai, ChatGPT and other clients: add https://private-ai-tools.com/mcp as a custom connector in the settings.
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.
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.