Search and install skills, MCP servers and CLI tools for AI agents from SkillFoxx.
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.
Read one catalog card with install instructions, a machine-readable install recipe with its status, access level (fields riskLevel and riskReasons: what the tool adds to the agent, low minimal, medium extended, high broad; not a code quality rating) and limitations. Section is skills, mcp, cli, plugins, workflows or prompts. For step-by-step install in a specific agent call plan_install.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http catalog https://skillfoxx.ru/api/mcp
Read one catalog card with install instructions, a machine-readable install recipe with its status, access level (fields riskLevel and riskReasons: what the tool adds to the agent, low minimal, medium extended, high broad; not a code quality rating) and limitations. Section is skills, mcp, cli, plugins, workflows or prompts. For step-by-step install in a specific agent call plan_install.
| Argument | Type | Description |
|---|---|---|
| lang | string | |
| slug* | string | |
| section* | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"section",
"slug"
],
"properties": {
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"default": "ru"
},
"slug": {
"type": "string"
},
"section": {
"type": "string"
}
}
}List catalog categories with card counts.
| Argument | Type | Description |
|---|---|---|
| lang | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"default": "ru"
}
}
}Get exact install steps for one catalog tool in one agent: commands, config file path and snippet, one-click links for Cursor and VS Code, variables to fill in, recipe status and access level. Secrets are never included, only placeholders with the variable name. Agent is one of: claude-code, cursor, vscode, codex, gemini-cli, devin, cline, zoo-code, opencode, zed, sourcecraft, coddy, antigravity, kiro, claude-desktop, lm-studio (site aliases like vs-code, windsurf, roo-code, github-copilot, gemini also work). Section is skills, mcp, cli, plugins, workflows or prompts. After a successful install call report_install with the returned reportToken.
| Argument | Type | Description |
|---|---|---|
| lang | string | |
| slug* | string | |
| agent* | string | |
| section* | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"section",
"slug",
"agent"
],
"properties": {
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"default": "ru"
},
"slug": {
"type": "string"
},
"agent": {
"type": "string"
},
"section": {
"type": "string"
}
}
}Recommend skills, MCP servers and CLI tools for a project from a safe summary. Send the goal, framework names, dependency names and notable file names. Never send source code or secrets.
| Argument | Type | Description |
|---|---|---|
| goal | string | |
| lang | string | |
| files | array | |
| problems | array | |
| frameworks | array | |
| dependencies | array |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"goal": {
"type": "string",
"default": "",
"maxLength": 2000
},
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"default": "ru"
},
"files": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200
},
"default": [],
"maxItems": 400
},
"problems": {
"type": "array",
"items": {
"type": "string",
"maxLength": 300
},
"default": [],
"maxItems": 20
},
"frameworks": {
"type": "array",
"items": {
"type": "string",
"maxLength": 60
},
"default": [],
"maxItems": 40
},
"dependencies": {
"type": "array",
"items": {
"type": "string",
"maxLength": 120
},
"default": [],
"maxItems": 400
}
}
}Tell SkillFoxx that you installed a catalog tool for the user, so the anonymous install counter stays honest. Call it only after the user agreed and the installation finished without errors, with the reportToken from plan_install. Do not call it when you installed through npx skillfoxx (the CLI reports by itself) or when the user asked not to send statistics. No personal data is stored.
| Argument | Type | Description |
|---|---|---|
| slug* | string | |
| agent* | string | |
| event | string | |
| section* | string | |
| reportToken* | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"section",
"slug",
"agent",
"reportToken"
],
"properties": {
"slug": {
"type": "string",
"maxLength": 150
},
"agent": {
"type": "string",
"maxLength": 20
},
"event": {
"enum": [
"add",
"remove"
],
"type": "string",
"default": "add"
},
"section": {
"type": "string",
"maxLength": 20
},
"reportToken": {
"type": "string",
"maxLength": 64
}
}
}Search the SkillFoxx catalog of skills, MCP servers and CLI tools for AI agents. Returns published, reviewed cards only.
| Argument | Type | Description |
|---|---|---|
| lang | string | |
| limit | integer | |
| query* | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"lang": {
"enum": [
"ru",
"en"
],
"type": "string",
"default": "ru"
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 20,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 120,
"minLength": 2
}
}
}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 5, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.