core-agent-mcp
Provides drop-in integration with Hermes via mcp_servers config, enabling remote execution of system tools and file management inside agentic workflows.
Click on "Deploy 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., "@core-agent-mcpwhat's my public IP address?"
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.
Core Agent MCP
Remote execution layer for agentic systems. Expose 64 stable tools via Model Context Protocol — Hermes, OpenClaw, Claude Code, atau MCP client lain bisa pakai ini remote atau lokal.
Kenapa?
Agentic systems butuh remote execution layer yang reliable — bukan cuma shell access, tapi tools terstruktur, typed, dan terdefinisi yang return hasil konsisten. core-agent-mcp solusinya:
🛠 64 production tools — file, network, system, text, git, crypto, monitoring
🔌 Dual transport — stdio (local) atau HTTP SSE (remote)
🎯 Stable output — setiap tool return
{success: bool, data: ..., error?: str}🧩 Hermes-ready — drop-in via
mcp_serversconfig
Related MCP server: SystemKernelMCP
Quick Start
# Install
pip install core-agent-mcp
# Run stdio (local agent)
core-agent-mcp
# Run HTTP (remote agent)
core-agent-mcp --transport sse --host 0.0.0.0 --port 8931Integrasi Hermes
Tambah ke ~/.hermes/config.yaml:
mcp_servers:
core-agent:
command: "core-agent-mcp"
timeout: 120Remote:
mcp_servers:
core-agent:
url: "http://your-server:8931/mcp"
timeout: 120
connect_timeout: 30/reset sesi Hermes — semua tool muncul sebagai mcp_core_agent_*.
Integrasi OpenClaw / Claude Code
Claude Code (claude_code.json)
{
"mcpServers": {
"core-agent": { "command": "core-agent-mcp" }
}
}OpenClaw
mcp_servers:
core-agent:
command: "core-agent-mcp"Tools (64 tools)
System (11)
Tool | Description |
| OS, kernel, hostname, CPU, Python |
| Execute shell command (timeout, cwd, env) |
| Get env var value |
| List env vars (keys atau key=value) |
| Locate binary in PATH |
| Disk space per partition |
| RAM + swap usage |
| Load avg + per-core usage |
| System uptime |
| User accounts (UID>=1000 + root) |
| System hostname |
Filesystem (16)
Tool | Description |
| Read file (line range, max 1MB) |
| Write/overwrite file (auto mkdir) |
| Append to file |
| Dir listing with metadata |
| File/dir metadata detail |
| Find by glob pattern |
| Search content via regex |
| Copy file/dir (recursive) |
| Move/rename file/dir |
| Delete file/dir (safe: need recursive flag) |
| mkdir -p |
| Download URL to file |
| MD5/SHA1/SHA256/SHA512 |
| Directory tree (depth-limited) |
| Last N lines |
| First N lines |
Network (7)
Tool | Description |
| Full HTTP (GET/POST/PUT/DELETE/PATCH) |
| DNS A/AAAA/MX/NS/TXT/CNAME |
| TCP port open check |
| Domain WHOIS lookup |
| SSL certificate details |
| Detect public IP |
| ICMP ping (count-based) |
Text & Data (20)
Tool | Description |
| Regex search in text |
| Words/lines/chars/bytes |
| Unified diff text A vs B |
| Validate & parse JSON |
| Pretty-print JSON |
| Base64 encode |
| Base64 decode |
| URL percent-encode |
| URL percent-decode |
| MD5/SHA1/SHA256/SHA512 |
| Random UUID v4 |
| Time-ordered UUID v7 |
| ISO/Unix/RFC2822 now |
| Text to hex |
| Hex to text |
| Unix sec → ISO 8601 |
| ISO 8601 → Unix sec |
| CSV text → JSON array |
| JSON → YAML |
| YAML → JSON |
Development (7)
Tool | Description |
| Working tree status |
| Commit log (N entries, filter author) |
| Diff unstaged/staged/refs |
| List local branches |
| Count commits (branch/all) |
| Commit detail + diffstat |
| Pretty-print JSON |
Meta (2)
Tool | Description |
| Health check → pong + version |
| List all tools with descriptions |
CLI
core-agent-mcp [OPTIONS]
Options:
--transport TEXT stdio (default) atau sse
--host TEXT HTTP host (default: 0.0.0.0)
--port INTEGER HTTP port (default: 8931)
--timeout INTEGER Tool timeout (default: 120s)
--max-output INTEGER Max output bytes (default: 51200)
--workdir TEXT Working directory
--helpEnv Variables
Variable | Default | Description |
| 120 | Default tool timeout |
| 51200 | Max output bytes |
| $PWD | Working directory |
| - | Comma-separated allowed paths |
Dev
git clone https://github.com/jefripunza/core-agent-mcp
cd core-agent-mcp
uv venv && source .venv/bin/activate
uv pip install -e .
core-agent-mcp
# Test via MCP inspector
npx @modelcontextprotocol/inspector core-agent-mcpLicense
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Related MCP Servers
- AlicenseDqualityDmaintenanceAI-native orchestration layer with 80+ tools for task management, code editing, browser automation, terminal control, and persistent memory across CLI, local MCP, and cloud deployments.694 npm31ISC
- FlicenseNot gradedqualityDmaintenanceProvides 180+ tools for full system control including terminal, Git, Docker, Kubernetes, VMs, BIOS, kernel, cybersecurity, AI, and cloud, designed to work with MCP clients like Cursor and Claude Desktop.-
- AlicenseNot gradedqualityDmaintenanceExposes a Linux host with shell, Python, and filesystem tools as MCP tools over HTTPS, enabling AI agents to execute commands and manage files remotely.9 npmMIT
- AlicenseNot gradedqualityAmaintenanceA typed, policy-controlled OS capability layer for AI agents via MCP, exposing safe filesystem, git, and text-processing tools governed by a strict policy engine.MIT