native-mcp

Connects to MCP servers and registers their tools as native agent tools.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/kaminocorp/hermes-alpha-hunter --skill native-mcp-kaminocorp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: native-mcp
Source: https://github.com/kaminocorp/hermes-alpha-hunter/tree/main/skills/mcp/native-mcp
Command: npx skills add https://github.com/kaminocorp/hermes-alpha-hunter --skill native-mcp-kaminocorp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mcp.

What problem does it solve? Integrating external capabilities like filesystem access, GitHub, databases, or APIs into an AI agent normally requires custom glue code or manual tool wiring. This Skill connects to MCP (Model Context Protocol) servers at startup, discovers their tools automatically, and registers them as first-class tools the agent can call directly. ## Core Features & Use Cases - Automatic Tool Discovery: Connects to configured MCP servers on startup, lists their tools, and registers them with a mcp_{server}_{tool} naming prefix across all platforms (CLI, Discord, Telegram). - Dual Transport Support: Runs local stdio-based servers (npx, uvx, or any command) and connects to remote HTTP/StreamableHTTP servers with custom headers and authentication. - Security Controls: Filters environment variables passed to subprocesses, redacts credentials from error messages, and supports per-server sampling limits for server-initiated LLM requests. - Use Case: Add a GitHub MCP server with a personal access token to your config, restart the agent, and immediately ask it to list issues or create pull requests using the auto-registered mcp_github_* tools. ## Quick Start Add an MCP server entry under the mcp_servers key in ~/.hermes/config.yaml with a command or url, then restart the agent and ask it to use the newly discovered tools.

Frequently Asked Questions about native-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I connect an MCP server to my AI agent?▼

Add an entry under the mcp_servers key in ~/.hermes/config.yaml with either a command (stdio transport) or a url (HTTP transport), then restart the agent. On startup it connects, discovers tools via list_tools(), and registers them with a mcp_{server}_{tool} prefix.

How do I configure stdio vs HTTP MCP servers?▼

Stdio servers use a command and args field to launch a subprocess like npx or uvx, while HTTP servers use a url field with optional headers for authentication. A server config must have one or the other, not both.

Does the MCP client pass my environment variables to servers?▼

No, only safe baseline variables like PATH, HOME, and XDG_* are inherited by stdio subprocesses. API keys and secrets must be explicitly declared in the server's env config block, preventing accidental credential leakage.

Why are my MCP tools not appearing after configuration?▼

Common causes include a missing mcp Python package, incorrect YAML indentation, the server key not being under mcp_servers, or the command binary not being on PATH. Check startup logs for connection messages and look for the mcp_{server}_{tool} naming pattern.

What happens when an MCP server connection drops?▼

The client automatically retries with exponential backoff up to 5 times, capped at 60 seconds between attempts. If the server remains unreachable after 5 retries, it gives up, while other configured servers continue operating normally.

When should I use mcporter instead of the native MCP client?▼

Use mcporter for ad-hoc, one-off MCP tool calls from the terminal without any configuration. The native MCP client is better for persistent integrations where tools should be auto-discovered and available in every conversation.