Search a plain-English guide to open-source AI projects: what each does, cost and privacy.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Full details of one project: what it does, who it's for, whether it needs coding, rating, numbers, license and source links.
The project's slug, from search_projects or list_categories.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http plain-ayi https://plain-ayi.com/mcp
Full details of one project: what it does, who it's for, whether it needs coding, rating, numbers, license and source links.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The project's slug, from search_projects or list_categories. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]*$",
"maxLength": 100,
"description": "The project's slug, from search_projects or list_categories."
}
}
}All categories on both shelves ('ai' and 'ai-integrated') with a short description, how many projects each has, and the slugs of its projects.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Find open-source AI projects by what they do, e.g. 'run chat models offline' or 'transcribe audio'. Searches both shelves unless 'shelf' is given: 'ai' (AI tools) or 'ai-integrated' (everyday software that AI assistants can use, e.g. a notes app with an MCP server). Optionally narrow by category or by whether it can be used without writing code. Returns short summaries, best matches first.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many results to return (default 10, max 25). |
| query* | string | Words describing what you're looking for. |
| shelf | string | 'ai' = AI tools, 'ai-integrated' = software that works with AI. Leave out to search both. |
| category | string | Category slug from list_categories. |
| useWithoutCoding | string | 'yes' = no coding needed, 'some-setup' = usable with some setup, 'developers' = needs a developer. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 25,
"minimum": 1,
"description": "How many results to return (default 10, max 25)."
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Words describing what you're looking for."
},
"shelf": {
"enum": [
"ai",
"ai-integrated"
],
"type": "string",
"description": "'ai' = AI tools, 'ai-integrated' = software that works with AI. Leave out to search both."
},
"category": {
"enum": [
"run-locally",
"chat",
"agents",
"coding",
"coding-addons",
"app-builders",
"documents",
"memory",
"images-video",
"speech-audio",
"3d-design",
"models",
"training",
"data-science",
"testing-safety",
"cybersecurity",
"finance",
"robotics",
"smart-home",
"infrastructure",
"building-blocks",
"everyday",
"learning",
"messages",
"notes",
"planning",
"design-media",
"money",
"data",
"web-dev",
"security",
"health",
"files",
"home"
],
"type": "string",
"description": "Category slug from list_categories."
},
"useWithoutCoding": {
"enum": [
"yes",
"some-setup",
"developers"
],
"type": "string",
"description": "'yes' = no coding needed, 'some-setup' = usable with some setup, 'developers' = needs a developer."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 4, 2026.