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-installer install the mcp-server-fetch package for me"
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.
This server is a server that installs other MCP servers for you. Install it, and you can ask Claude to install MCP servers hosted in npm or PyPi for you. Requires npx and uv to be installed for node and Python servers respectively.
Put this into your claude_desktop_config.json (either at ~/Library/Application Support/Claude on macOS or C:\Users\NAME\AppData\Roaming\Claude on Windows):
"mcpServers": {
"mcp-installer": {
"command": "npx",
"args": [
"@anaisbetts/mcp-installer"
]
}
}Hey Claude, install the MCP server named mcp-server-fetch
Hey Claude, install the @modelcontextprotocol/server-filesystem package as an MCP server. Use ['/Users/anibetts/Desktop'] for the arguments
Hi Claude, please install the MCP server at /Users/anibetts/code/mcp-youtube, I'm too lazy to do it myself.
Install the server @modelcontextprotocol/server-github. Set the environment variable GITHUB_PERSONAL_ACCESS_TOKEN to '1234567890'
Install an MCP server whose code is cloned locally on your computer
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | The path to the MCP server code cloned on your computer | |
| args | No | The arguments to pass along | |
| env | No | The environment variables to set, delimited by = |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool installs an MCP server, implying a mutation or setup operation, but doesn't cover critical aspects like whether it requires specific permissions, if it's idempotent, potential side effects (e.g., overwriting existing installations), or error handling. This leaves significant gaps in understanding the tool's behavior.
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 that directly states the tool's purpose without unnecessary words. It is front-loaded and wastes no space, making it easy to parse quickly.
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 complexity of an installation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what 'install' entails (e.g., setup steps, success criteria), return values, or error conditions. For a mutation tool with 3 parameters, more context is needed to guide the agent effectively.
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, clearly documenting all three parameters (path, args, env). The description adds no additional meaning beyond what the schema provides, such as examples or constraints. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description doesn't enhance parameter understanding.
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 clearly states the action ('Install') and the resource ('an MCP server whose code is cloned locally on your computer'), making the purpose understandable. However, it doesn't explicitly differentiate from its sibling 'install_repo_mcp_server', which likely installs from a repository rather than local code, leaving some ambiguity about when to choose one over the other.
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 versus its sibling 'install_repo_mcp_server' or any alternatives. It lacks context about prerequisites (e.g., needing cloned code), exclusions, or typical scenarios, leaving the agent to infer usage based on the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Install an MCP server via npx or uvx
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The package name of the MCP server | |
| args | No | The arguments to pass along | |
| env | No | The environment variables to set, delimited by = |
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 the action ('Install') but does not disclose behavioral traits such as whether this requires network access, admin permissions, what happens on failure, or if it modifies system state. For a tool that likely performs system-level changes, this is a significant gap in transparency.
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 that directly states the tool's purpose without unnecessary words. It is appropriately sized and front-loaded, making it easy for an agent to parse quickly.
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 complexity of installing software (likely involving system changes) and the absence of annotations and output schema, the description is insufficient. It does not cover critical aspects like success/failure outcomes, error handling, or dependencies, leaving the agent with incomplete context for safe and effective 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?
Schema description coverage is 100%, so the schema already documents all parameters (name, args, env) with descriptions. The description adds no additional meaning beyond what the schema provides, such as examples or constraints. Baseline 3 is appropriate as the schema handles 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 clearly states the action ('Install') and the resource ('an MCP server'), specifying the method ('via npx or uvx'). It distinguishes from the sibling tool 'install_local_mcp_server' by implying this is for remote repositories, though not explicitly. However, it lacks full specificity about what exactly is being installed (e.g., from a package registry).
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 versus its sibling 'install_local_mcp_server' or other alternatives. It mentions the installation method but does not specify contexts, prerequisites, or exclusions, leaving the agent to infer usage based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have clearly distinct purposes: one installs from local code, the other installs via package managers (npx/uvx). There is no overlap or ambiguity between them.
Both tools follow a consistent verb_noun pattern with 'install' as the verb and descriptive suffixes ('local_mcp_server', 'repo_mcp_server'). The naming is perfectly uniform and predictable.
With only 2 tools, the server feels thin for an 'installer' domain. It covers basic installation methods but lacks tools for managing installed servers (e.g., list, update, remove), which limits its utility.
The toolset is severely incomplete for an installer. It provides installation but no lifecycle management (e.g., uninstall, list, update, configure). This will cause agent failures when trying to manage servers beyond initial installation.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Search and install 4,000+ security-scanned MCP servers from inside any MCP-aware AI client.
The official e18e MCP server keeping your agent in check from installing bloated dependencies.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/anaisbetts/mcp-installer'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
