Koskamo

should-i-use MCP

An MCP server that provides honest library recommendations for coding agents, helping them decide which dependencies to install or avoid based on a curated index of 992 rubric-written guides. It offers tools to pick libraries, audit dependencies, and find alternatives.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

should-i-use MCP logo, by mrkeyoorCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by mrkeyoor
MCP endpoint (Streamable HTTP)
https://mrkeyoor.com/mcp
Vendor documentation

What its tools do

6 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (6)

6 of 6 have a description · 6 of 6 declare behavior hints · 6 of 6 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Warning Advertises resources/templates/list but does not implement it
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Pick top library recommendations for specific tasks
  • Audit dependencies for unmaintained or unstable packages
  • Find curated alternatives for existing libraries
  • Get documentation links and repo information

Source and maintenance

Community listingRegistry 0.3.2
mcp-registry: io.github.mrkeyoor/should-i-use@0.3.2Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
should-i-use 0.3.3
MCP protocol negotiated in check
2025-11-25
Tools
6 advertised
Resources
0 advertised
Resource templates
Not advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {},
  "prompts": {},
  "resources": {}
}

Tools

6 advertised

pick_library — Pick a library
Advertised by the server during the last successful anonymous check.
Advertised read-only

Given a coding task, recommend 1-3 libraries from the should-i-use index with one-line reasoning and an honest warning about the top pick. Use before installing anything.

pick_library input schema
{
  "type": "object",
  "required": [
    "task"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "What you are trying to do, e.g. \"parse CSV files in node\""
    },
    "ecosystem": {
      "enum": [
        "npm",
        "pypi"
      ],
      "type": "string",
      "description": "Optional registry filter"
    }
  }
}
pick_library output schema
{
  "type": "object",
  "required": [
    "answer"
  ],
  "properties": {
    "answer": {
      "type": "string",
      "description": "The clamped text answer (hard limit ~500 tokens)"
    }
  }
}
pick_library annotations
{
  "title": "Pick a library",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
should_i_use — Should I use this library?
Advertised by the server during the last successful anonymous check.
Advertised read-only

Honest verdict on a specific library: 4-axis scores with reasons, when to skip it, and maintenance signals (last push, weekly downloads).

should_i_use input schema
{
  "type": "object",
  "required": [
    "library"
  ],
  "properties": {
    "library": {
      "type": "string",
      "description": "Library name as published on npm or PyPI"
    }
  }
}
should_i_use output schema
{
  "type": "object",
  "required": [
    "answer"
  ],
  "properties": {
    "answer": {
      "type": "string",
      "description": "The clamped text answer (hard limit ~500 tokens)"
    }
  }
}
should_i_use annotations
{
  "title": "Should I use this library?",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
alternatives — Library alternatives
Advertised by the server during the last successful anonymous check.
Advertised read-only

Curated alternatives to a library, each with a one-line "prefer it when" and a verdict if the alternative is also indexed.

alternatives input schema
{
  "type": "object",
  "required": [
    "library"
  ],
  "properties": {
    "library": {
      "type": "string",
      "description": "Library name as published on npm or PyPI"
    }
  }
}
alternatives output schema
{
  "type": "object",
  "required": [
    "answer"
  ],
  "properties": {
    "answer": {
      "type": "string",
      "description": "The clamped text answer (hard limit ~500 tokens)"
    }
  }
}
alternatives annotations
{
  "title": "Library alternatives",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
how_do_i — How do I do this?
Advertised by the server during the last successful anonymous check.
Advertised read-only

Return the 1-2 best code snippets for a task with a library, plus the gotcha for each. Snippets are correct for the indexed version. Far cheaper in tokens than a docs dump.

how_do_i input schema
{
  "type": "object",
  "required": [
    "library",
    "task"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "What you want to do, e.g. \"retry a failed request\""
    },
    "library": {
      "type": "string",
      "description": "Library name as published on npm or PyPI"
    }
  }
}
how_do_i output schema
{
  "type": "object",
  "required": [
    "answer"
  ],
  "properties": {
    "answer": {
      "type": "string",
      "description": "The clamped text answer (hard limit ~500 tokens)"
    }
  }
}
how_do_i annotations
{
  "title": "How do I do this?",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
audit_dependencies — Audit dependencies
Advertised by the server during the last successful anonymous check.
Advertised read-only

Audit a project's dependencies for unmaintained packages, unstable APIs, and documented reasons to switch. Pass the contents of package.json, requirements.txt, or pyproject.toml. Returns only the dependencies worth a decision, not a report on every line. Run this before working in an unfamiliar codebase.

audit_dependencies input schema
{
  "type": "object",
  "required": [
    "manifest"
  ],
  "properties": {
    "manifest": {
      "type": "string",
      "description": "Contents of package.json, requirements.txt, pyproject.toml, or a newline-separated list of package names"
    },
    "ecosystem": {
      "enum": [
        "npm",
        "pypi"
      ],
      "type": "string",
      "description": "Optional hint when the manifest format is ambiguous"
    }
  }
}
audit_dependencies output schema
{
  "type": "object",
  "required": [
    "answer"
  ],
  "properties": {
    "answer": {
      "type": "string",
      "description": "The clamped text answer (hard limit ~500 tokens)"
    }
  }
}
audit_dependencies annotations
{
  "title": "Audit dependencies",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
docs_link — Docs link
Advertised by the server during the last successful anonymous check.
Advertised read-only

Official docs URL and GitHub repo for a library, one line each. Use when the clamped answers are not enough.

docs_link input schema
{
  "type": "object",
  "required": [
    "library"
  ],
  "properties": {
    "topic": {
      "type": "string",
      "description": "Optional topic to look up in the docs"
    },
    "library": {
      "type": "string",
      "description": "Library name as published on npm or PyPI"
    }
  }
}
docs_link output schema
{
  "type": "object",
  "required": [
    "answer"
  ],
  "properties": {
    "answer": {
      "type": "string",
      "description": "The clamped text answer (hard limit ~500 tokens)"
    }
  }
}
docs_link annotations
{
  "title": "Docs link",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1512 ms
95th percentile latency
1512 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1512 ms · metadata changed · 6 tool(s), 0 resource(s), 0 prompt(s); warnings: Advertises resources/templates/list but does not implement it

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http should-i-use-mcp-mrkeyoor https://mrkeyoor.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add should-i-use-mcp-mrkeyoor --url https://mrkeyoor.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable should-i-use-mcp-mrkeyoor in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "should-i-use-mcp-mrkeyoor": {
      "url": "https://mrkeyoor.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "should-i-use-mcp-mrkeyoor": {
      "type": "streamableHttp",
      "url": "https://mrkeyoor.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start should-i-use-mcp-mrkeyoor and inspect its tools.
VS Code configuration
{
  "servers": {
    "should-i-use-mcp-mrkeyoor": {
      "type": "http",
      "url": "https://mrkeyoor.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http should-i-use-mcp-mrkeyoor https://mrkeyoor.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://mrkeyoor.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "should-i-use-mcp-mrkeyoor": {
      "serverUrl": "https://mrkeyoor.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like should-i-use MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 8,316