AI & Machine Learning

traktirinkopi.com

Manages a catalog of AI agent skills, allowing users to browse, install, uninstall, list, and inspect skills.

2 endpoints16 known toolsFirst detected August 2, 2026Last detected August 2, 2026

ENDPOINT 1

https://hub.traktirinkopi.com/mcp

No auth detected

MCP server metadata

Name: agentCamp Skill Hub
Version: 3.4.2

Capabilities

experimentalloggingprompts.listChangedresources.listChangedtools.listChangedextensions.io.modelcontextprotocol/ui

Server instructions

agentCamp gives your AI assistant ready-made skills for real, everyday work — pick one, give it what you have, get something useful back. It's still early: a small but growing set of skills, and you can try each one and judge it yourself before you rely on it. For anyone who wants an assistant that actually helps. Built for the Indonesian agent ecosystem. How skills work: call browse_skills() to see the catalog, then install_skill(slug) to add a skill to this key. You can only run_skill(slug, ...) on skills you've installed. list_skills() shows just your installed skills. uninstall_skill(slug) removes ones you no longer need so your skill list stays small and focused. Installing is free; running a skill uses quota.

Known tools 8

browse_skills

Browse the FULL agentCamp skill catalog.

Inferred read-only

install_skill

Install a skill onto the caller's key so it can be run.

Inferred read-only

uninstall_skill

Uninstall a skill from the caller's key (soft — reinstall any time).

Inferred read-only

list_skills

List skills INSTALLED on the caller's key.

Inferred read-only

skill_detail

Inspect one skill: version, quota_cost, and the `actions` list — each action has `desc`, `quota_cost`, `params`, `read_only`, and `usage` = a ready-to-use run_skill(...) call example.

Inferred read-only

run_skill

Run a skill by slug.

Inferred read-only

my_quota

Caller's quota in quota units: sisa_kuota, kuota_terpakai, and total_runs since the last reset.

Inferred read-only

about

What is agentCamp?

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentcamp-skill-hub]
url = "https://hub.traktirinkopi.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentcamp-skill-hub": {
      "type": "http",
      "url": "https://hub.traktirinkopi.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentcamp-skill-hub
Remote MCP URL: https://hub.traktirinkopi.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentcamp-skill-hub": {
      "url": "https://hub.traktirinkopi.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentcamp-skill-hub": {
      "type": "http",
      "url": "https://hub.traktirinkopi.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentcamp-skill-hub",
  "transport": "streamable-http",
  "url": "https://hub.traktirinkopi.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://hub.traktirinkopi.com/mcp?key=

No auth detected

MCP server metadata

Name: agentCamp Skill Hub
Version: 3.4.2

Capabilities

experimentalloggingprompts.listChangedresources.listChangedtools.listChangedextensions.io.modelcontextprotocol/ui

Server instructions

Known tools 8

browse_skills

Browse the FULL agentCamp skill catalog.

Inferred read-only

install_skill

Install a skill onto the caller's key so it can be run.

Inferred read-only

uninstall_skill

Uninstall a skill from the caller's key (soft — reinstall any time).

Inferred read-only

list_skills

List skills INSTALLED on the caller's key.

Inferred read-only

skill_detail

Inspect one skill: version, quota_cost, and the `actions` list — each action has `desc`, `quota_cost`, `params`, `read_only`, and `usage` = a ready-to-use run_skill(...) call example.

Inferred read-only

run_skill

Run a skill by slug.

Inferred read-only

my_quota

Caller's quota in quota units: sisa_kuota, kuota_terpakai, and total_runs since the last reset.

Inferred read-only

about

What is agentCamp?

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentcamp-skill-hub]
url = "https://hub.traktirinkopi.com/mcp?key="
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentcamp-skill-hub": {
      "type": "http",
      "url": "https://hub.traktirinkopi.com/mcp?key="
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentcamp-skill-hub
Remote MCP URL: https://hub.traktirinkopi.com/mcp?key=

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentcamp-skill-hub": {
      "url": "https://hub.traktirinkopi.com/mcp?key="
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentcamp-skill-hub": {
      "type": "http",
      "url": "https://hub.traktirinkopi.com/mcp?key="
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentcamp-skill-hub",
  "transport": "streamable-http",
  "url": "https://hub.traktirinkopi.com/mcp?key="
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for traktirinkopi.com was fetched 2026-08-08T14:51:34.878Z.

Trust status Neutral

traktirinkopi.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.