PluginBench
MCP Server
Maintained

io.github.Shawn5cents/agentskin MCP Server

io.github.Shawn5cents/agentskin

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.Shawn5cents/agentskin MCP server?

The Semantic Layer for AI Agents. Prunes noisy API data by 70%+ for token-efficient reasoning.

How to install io.github.Shawn5cents/agentskin

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • BRAVE_SEARCH_API_KEY
    secret

    Brave Search API Key

  • SERPER_API_KEY
    secret

    Serper.dev Search API Key

  • TAVILY_API_KEY
    secret

    Tavily Search API Key

  • APILAYER_KEY
    secret

    MediaStack API Key

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "agentskin": {
      "command": "npx",
      "args": [
        "-y",
        "agentskin"
      ],
      "env": {
        "BRAVE_SEARCH_API_KEY": "<YOUR_BRAVE_SEARCH_API_KEY>",
        "SERPER_API_KEY": "<YOUR_SERPER_API_KEY>",
        "TAVILY_API_KEY": "<YOUR_TAVILY_API_KEY>",
        "APILAYER_KEY": "<YOUR_APILAYER_KEY>"
      }
    }
  }
}

Related MCP servers

Keyless non-custodial crypto payments for AI agents: payment links and tip jars, no API key.

0
JavaScript
MIT
View repository →

StackExchange-style Q&A network where AI agents ask, answer, critique, and earn reputation.

Five trust services for agents: claim checks, citation audits, extraction, tripwires, work audits.

View repository →

Graph-backed session memory for LLMs: checkpoint, resume, and replay decisions across context windows.

26
Python
MIT
View repository →

Local-first flight recorder for AI agents: sessions, costs, loop runs, and stuck-loop flags.

3
Python
MIT
View repository →

Conversational Windows disk cleanup (whitelist-only) + device cleanup guides in 7 languages.

1
HTML
View repository →