Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AI Tools MCP What AI tool should I use to create product demo videos?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that gives your AI assistant access to a database of ~400 AI tool cards extracted from The AI Search YouTube channel, each with pricing, platform, use cases, and source links. Updated automatically as new videos are published.
Built so you can ask your AI "what tool should I use for X?" and get an answer grounded in hands-on testing from a channel that's reviewed 2-3 AI tools a week for years.
Add to your MCP config (Claude Code, Cursor, Windsurf, or any MCP-compatible client):
{
"mcpServers": {
"ai-tools": {
"command": "npx",
"args": ["-y", "@caseybuilds/ai-tools-mcp"]
}
}
}No API keys, no setup.
Related MCP server: HyperStore MCP
The server exposes one tool: search_tools. When called, it returns every card in the database. Your AI reads them all and picks what's relevant to your question.
Why return everything instead of filtering? The AI matches intent to tool better than keyword search — a query about "making 3D product mockups" should surface a card that says "generate photorealistic scene compositions."
The full set fits comfortably in any modern LLM's context. If you want to keep your main conversation's context clean, have your AI call this tool from a sub-agent.
Tool name and one-line description
URL, pricing (free / freemium / paid / open-source), platform (web / local / API / mobile / etc.)
Local-friendly: whether it runs on consumer hardware
What it does: 2-3 sentence summary
When to use it: the job this tool is best at
Sources: links to the original YouTube reviews with dates and depth (deep-dive vs. mention)
All cards are extracted from video transcripts on The AI Search, a YouTube channel that reviews AI tools 2-3 times per week. Each card links back to its source video(s).
git clone https://github.com/Minecraft9101010/ai-tools-mcp.git
cd ai-tools-mcp
npm install
npm run devThe server fetches cards from GitHub first (so users always get the latest). If that fails (offline, rate-limited), it falls back to the local cards/ directory. Cards are cached in memory for one hour.
Returns all AI tool cards from the database. Each card includes the tool name, description, pricing, platform, what it does, and when to use it. Sourced from The AI Search YouTube channel. Tip: call this from a sub-agent to keep the main thread's context clean.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden, and it discloses the read-only nature ('Returns'), the full scope ('all'), the exact card fields, the data source (The AI Search YouTube channel), and a context-management tip. It does not mention freshness, auth, or rate limits, but for a zero-parameter retrieval tool this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences: function, result contents, and practical tip. Every sentence adds value and the core action is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, no-output-schema retrieval tool, the description is complete: it states the resource, return fields, provenance, and a usage tip. Nothing essential for a correct first call is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and an empty schema, so there is no parameter meaning for the description to add. The baseline of 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific action and resource: 'Returns all AI tool cards from the database.' The second sentence enumerates the card contents, making the tool's function concrete. There are no sibling tools, so differentiation is not needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use it: when a complete list of AI tool cards is needed. The tip about calling from a sub-agent adds useful invocation guidance, though it does not contrast with alternatives because none are defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.1.0search_toolsWith only one tool exposed, there is no possibility of confusion or overlap. The tool's purpose is singular and unambiguous.
The single tool name follows a clear verb_noun snake_case convention. With only one tool, there is no inconsistent pattern to penalize.
A one-tool server feels too thin for the broad 'AI Tools MCP' scope. Even if the single function is useful, agents have no complementary operations or filtering capabilities.
The tool only returns all AI tool cards at once, with no filtering, searching, retrieval by ID, or management operations. Significant gaps exist for a server ostensibly about AI tools.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Live data gateway for AI — 3,300+ tools across 750+ sources, with citations
AI-powered SaaS tool discovery API. Search 150+ curated business tools and get recommendations.
Search, inspect, recommend, and explain rated AI tools through Agent Radar.
Find best-fit tools for any problem, vetted for prompt-injection risk before your agent trusts them
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Minecraft9101010/ai-tools-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server