SentinelMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_system_logsB | Fetch and parse system/service logs locally. Summarizes errors and warning patterns to prevent token usage bloat. |
| get_service_statesA | Fetch the active status, configuration, and state of system services. Supports Windows and Linux services. |
| get_system_metricsA | Monitor system performance indicators: CPU, RAM, disk space, and hardware S.M.A.R.T health indicators. Supports Windows and Linux. |
| check_network_status | Diagnose network stack: IP interfaces, active listening ports, gateway connectivity, and DNS lookup. Supports Windows and Linux. |
| analyze_root_causeA | Perform root cause analysis on system evidence. Outputs confidence scores, severity, and ranked repair hypotheses. Handles hardware faults by recommending replacements and estimating costs. Integrates with OSV.dev CVE database for vulnerability lookup. |
| execute_service_repair | Perform operational corrections on system services (restart, start, enable, disable). Requires acquiring the global State Lock. Supports Windows and Linux. |
| execute_config_patch | Apply patches or edits to config files. Automatically performs backups prior to editing to support automated rollbacks on validation failures. |
| execute_package_repair | Repair broken package dependencies or install missing libraries safely (apt-get on Linux, winget on Windows, npm globally). Requires acquiring the global State Lock. |
| verify_repair_state | Verify if the system has been restored to a healthy state. If verification succeeds, commits updates and releases state-lock. If verification fails, AUTOMATICALLY triggers system rollback of all modified configurations and flags the attempt failed. Supports Windows and Linux. |
| retrieve_similar_incidents | Query the local knowledge database for past incidents matching the given fingerprint. Returns prior repair strategies and their success rates. |
| get_incident_history | Retrieve a complete log of all past diagnostic and repair incidents. |
| check_repair_strategy_limitA | Ensure that the same repair strategy is not retried endlessly. If it has failed multiple times for this failure fingerprint, it will be marked as BLOCKED. |
| register_prevention_rule | Register a system hardening or monitoring recommendation rule to prevent identical future failures. |
| get_prevention_rules | Fetch all registered hardening/prevention rules in the system. |
| get_platform_capabilitiesA | Query the operational capabilities and supported monitoring features on this host platform (Windows or Linux). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| diagnose-and-repair | Guides the agent through detecting, diagnosing, repairing, and verifying a system or service failure. |
| incident-postmortem | Generates a post-mortem summary for a resolved incident. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Incident History Log | A complete browsable log of all past system diagnostic and self-healing incidents. |
| Registered Hardening Rules | A list of registered system hardening and failure prevention rules. |
| Health Checks | Current health status of all registered health checks |
| Widget Examples | Provides metadata and examples for all registered UI widgets |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AnanthanarayanKV/SentinalMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server