SentinelX MCP
Installs an agent on your Linux boxes that lets Claude or ChatGPT run allowlisted shell commands, edit files, and manage systemd services over a single outbound WebSocket. No inbound ports or tunnels. The agent exposes 20+ MCP tools including sentinel_exec for commands, sentinel_edit for structured file operations, sentinel_service for systemctl actions, and read primitives like sentinel_read and sentinel_search. You configure an allowlist in /etc/sentinelx/config.yaml that gates which commands, services, and filesystem paths the LLM can touch. Reach for this when you want to operate remote servers conversationally without SSH or when you need multi-host orchestration from your chat interface. The hub at mcp.sentinelx.app handles auth and routing.
- tools
- 19
- transport
- HTTP
- last updated
- Aug 15, 2026
Tools
19 toolsPublic tool metadata for what this MCP can expose to an agent.
sentinel_execRun an allowlisted shell command
Run an allowlisted shell command
No parameter schema in public metadata yet.
sentinel_script_runRun a one-off bash or python3 script
Run a one-off bash or python3 script
No parameter schema in public metadata yet.
sentinel_editStructured file edit (replace, regex, replace-block, write, append, prepend)
Structured file edit (replace, regex, replace-block, write, append, prepend)
No parameter schema in public metadata yet.
sentinel_moveMove/rename a file or directory
Move/rename a file or directory
No parameter schema in public metadata yet.
sentinel_copyCopy a file or directory
Copy a file or directory
No parameter schema in public metadata yet.
sentinel_deleteDelete a file or directory
Delete a file or directory
No parameter schema in public metadata yet.
sentinel_chmodChange file permissions
Change file permissions
No parameter schema in public metadata yet.
sentinel_chownChange file owner/group
Change file owner/group
No parameter schema in public metadata yet.
sentinel_servicesystemctl start/stop/restart/reload/status
systemctl start/stop/restart/reload/status
No parameter schema in public metadata yet.
sentinel_restartShortcut for sentinel_service with action=restart
Shortcut for sentinel_service with action=restart
No parameter schema in public metadata yet.
sentinel_upload_fileSingle-shot file upload to the host
Single-shot file upload to the host
No parameter schema in public metadata yet.
sentinel_readRead a file's contents, with optional line-range slicing
Read a file's contents, with optional line-range slicing
No parameter schema in public metadata yet.
sentinel_listStructured directory listing (name, type, size, mtime)
Structured directory listing (name, type, size, mtime)
No parameter schema in public metadata yet.
sentinel_searchRecursive content search with regex and glob filters
Recursive content search with regex and glob filters
No parameter schema in public metadata yet.
sentinel_local_apiAllowlisted actions on host-local structured endpoints: a unix socket (HTTP or JSON-RPC) or a declared binary over stdio (JSON-RPC, MCP servers included). Only when the host declares local_apis
Allowlisted actions on host-local structured endpoints: a unix socket (HTTP or JSON-RPC) or a declared binary over stdio (JSON-RPC, MCP servers included). Only when the host declares local_apis
No parameter schema in public metadata yet.
sentinel_capabilitiesHost policy/capabilities; optional bounded summary projection
Host policy/capabilities; optional bounded summary projection
No parameter schema in public metadata yet.
sentinel_helpRich orientation/help; optional topic/path/single-playbook projections
Rich orientation/help; optional topic/path/single-playbook projections
No parameter schema in public metadata yet.
sentinel_stateInternal agent state, for debugging
Internal agent state, for debugging
No parameter schema in public metadata yet.
sentinel_pingCheap connectivity check
Cheap connectivity check
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
sentinelx-cloud-core
Operate your Linux, macOS, and Windows servers from Claude.ai or ChatGPT — safely. SentinelX gives your LLM an allowlisted, auditable shell: it can only run commands you've explicitly permitted, filesystem access is gated by a per-path allowlist, and every action is recorded. No inbound ports — just a single outbound WebSocket.
The security model is the point. Handing an LLM unrestricted shell on a server you care about is the thing SentinelX is designed to avoid: the allowlist is the real trust boundary, so the agent can't run — or invent — anything you didn't allow. This is the agent you install on the host; structured file edits and service management come with it.
SentinelX in ChatGPT — it reads the allowlist, runs only what's permitted (df -h, /proc/meminfo), and reports back.
Install
Most people start with the one-liner — it auto-detects Linux or macOS:
curl -fsSL https://get.sentinelx.app | bash
Details
- Repository
- github.com/pensados/sentinelx-cloud-core
- Category
- AI & LLM Tools
- Transport
- HTTP
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Remembra Relayremembra-ai/remembraCross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.16stars
Elefanteamenophis1er/elefanteOpen, Git-native memory protocol for MCP agents. Portable, versioned, human-editable.15stars
Figbridgerudraptpsingh/figbridgeFree, local MCP bridge for Figma — HTML, CSS, Tailwind, tokens, agent handoff bundles.15stars
Openfuse Mcpopenfused/openfusedEncrypted mail, shared memory, and persistent context for AI agents.14stars
Context Memjubakitiashvili/context-memPersistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools13stars
Synapse Layer — Trust Infrastructure for AI Agentssynapselayer/synapse-layerMCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.13stars