The MCP Registry Server allows you to retrieve MCP servers using semantic search. You can perform retrieval operations against the MCP registry by providing a search query. This server can be integrated with Claude Desktop for seamless usage.
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., "@mcp-registry-server find MCP servers for weather data"
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.
MCP Retriever: Retrieve MCP Servers using semantic search
Related MCP server: MCP Registry Server
retrieve_mcps
Perform retrieval operations against the MCP registry.
Inputs:
query (string): The search query for retrieval.
To install MCP Registry Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @KBB99/mcp-registry-server --client claudeFirst build the server:
git clone https://github.com/KBB99/mcp-registry-server.git
cd mcp-registry-server
npm install
npm run buildYou can confirm the server is working by running:
node ./dist/index.jsAdd this to your claude_desktop_config.json:
{
"mcpServers": {
"mcp-registry-server": {
"command": "node",
"args": [
"./path/to/build/mcp-registry-server/dist/index.js"
]
}
}
}This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
This README assumes that your server package is named mcp-server-retriever. Adjust the package name and installation details if they differ in your setup. Also, ensure that your server script is correctly built and that all dependencies are properly managed in your package.json.
Performs retrieval from our registry of MCPs.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The query to perform retrieval on |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states 'Performs retrieval' but doesn't disclose behavioral traits like whether it's read-only, if it requires authentication, rate limits, or what the output format might be. This leaves significant gaps for an agent to understand how to use it effectively.
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?
The description is a single, efficient sentence with no wasted words. It's appropriately sized and front-loaded, clearly stating the tool's purpose without unnecessary details.
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?
Given the tool has no annotations, no output schema, and a simple input schema, the description is incomplete. It doesn't explain what 'MCPs' are, what the retrieval returns, or any behavioral context, making it insufficient for an agent to fully understand the tool's use.
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 input schema has 100% description coverage, with the 'query' parameter documented as 'The query to perform retrieval on'. The description doesn't add any meaning beyond this, such as query syntax or examples. With high schema coverage, the baseline is 3, as the schema handles the parameter documentation adequately.
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?
The description states the action ('Performs retrieval') and resource ('from our registry of MCPs'), which is clear but vague. It doesn't specify what type of retrieval (e.g., search, lookup, fetch) or what 'MCPs' refers to, and with no siblings, differentiation isn't needed but specificity is lacking.
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 provides no guidance on when to use this tool, such as context, prerequisites, or alternatives. With no sibling tools, it's implied this is the only retrieval option, but no explicit usage scenarios are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of confusion or overlap between tools. The single tool has a distinct and clear purpose, making disambiguation trivial.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'retrieve_mcps' follows a clear verb_noun pattern, but with no other tools to compare, it sets a consistent baseline.
A single tool for a registry server feels thin and likely insufficient for the domain. Typical registry operations might include search, list, get details, or update, but this server only offers retrieval, which is too limited for the apparent scope.
The tool surface is severely incomplete for a registry domain. Only retrieval is provided, with no capabilities for searching, listing, creating, updating, or deleting MCP entries, which are common operations for a registry, leading to significant gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.
Search the official MCP registry: 17,000+ servers with trust grades, stars, tools, install config.
Search and discover 25,000+ MCP servers across all major registries. Connect and pay autonomously.
Search a nightly-refreshed directory of MCP servers by keyword, category or topic.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/KBB99/mcp-registry-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server