INTELLIGENCE
Naturallanguagecontrolforyourfleet

Type what you want to do. TucDesk translates it to a verified, auditable command.

tuc — natural language control
nlc ›
TRANSLATED
$tuc fleet run --tag prod --command "systemctl restart nginx"
RISK: MEDIUM → approvalwaiting for operator confirmation…
PIPELINE

How NLC works

Every natural language request moves through three deterministic stages before anything reaches an agent.

Parse

The intent parser extracts the action, target set, and arguments from your request — “restart nginx on all prod servers” becomes a structured plan with a confidence score. Low-confidence parses are rejected, never guessed.

Classify

The plan is scored against the risk model: LOW, MEDIUM, HIGH, or CRITICAL. Risk decides whether the command auto-executes, waits for confirmation, or requires a signed approval token.

Execute

Approved plans dispatch through the fleet executor with per-agent output, exit codes, and duration captured. Every run is bound to an access decision in the immutable audit log.

RISK ASSESSMENT

Four tiers, zero surprises

Risk classification is rule-based and auditable. The same tiers apply whether the request comes from an operator, the mobile app, or an AI client.

LOW

Auto-executes

Read-only and reversible commands run immediately after ACL evaluation. Results are still written to the audit log.

e.g. df -h, uptime, systemctl status

MEDIUM

Needs confirm

Service-affecting commands pause for a one-tap confirmation from the requesting operator before dispatch.

e.g. systemctl restart, docker restart

HIGH

Approval gate

Destructive commands require an explicit approval token bound to the exact command, target set, and expiry.

e.g. rm -rf, kill -9, database writes

CRITICAL

Blocked by default

Fleet-endangering commands are refused unless an admin explicitly allowlists the pattern in policy.

e.g. mkfs, dd to block devices, shutdown of all agents

HIGH and CRITICAL actions always require explicit human confirmation. LOW and MEDIUM actions still pass ACL, consent state, target validation, and immutable audit logging before results are returned.
LOCAL-FIRST PRIVACY

Your commands stay yours

Natural language parsing is designed to run on hardware you control, with cloud inference as an explicit, optional fallback.

Ollama runs locally first

TucDesk routes NLC requests to a local Ollama model by default. Intent parsing for common operations never leaves your network — no tokens, no per-request pricing, no external dependency.

Cloud LLM is fallback

If the local model is unavailable or the request is too ambiguous, TucDesk can fall back to a configured cloud LLM. The fallback is opt-in, logged, and can be disabled entirely by policy.

History never trains models

Your command history is stored for audit and replay only. It is never used to train external models, and cloud fallback requests are sent with retention disabled.

MCP INTEGRATION

12 native MCP tools for AI agents

Connect Claude, GPT, or any MCP client to the same governed fleet API. AI agents get bounded tools, not shell access.

  • list_agents — enumerate online machines with metadata
  • get_agent — fetch full agent record and security posture
  • connect_session — initiate an authenticated terminal session
  • run_command — execute a command with approval gate
  • list_sessions — recent session history with recordings
  • get_audit_log — tamper-evident action history
  • list_fleet_runs — parallel execution history
  • get_recording — retrieve session recording metadata
  • list_address_book — access controlled endpoint registry
  • get_security_posture — per-agent compliance snapshot
  • manage_acl — read/write access control policies
  • pair_agent — complete agent onboarding from MCP
{
  "mcpServers": {
    "tucdesk": {
      "command": "npx",
      "args": ["-y", "tucdesk-mcp"],
      "env": {
        "TUCDESK_API_URL": "https://api.tucdesk.app",
        "TUCDESK_API_KEY": "tdk_..."
      }
    }
  }
}
MCP TOOL REFERENCE

Available tools, scopes, and shapes

ToolInput parametersOutput shapeScope
list_agentsteam_id, filtersagents[], online_countagents:read
get_agentagent_idagent, posture, tagsagents:read
connect_sessionagent_id, modesession_id, consent_statesessions:write
run_commandagent_id/tag, commandrun_id, risk, approvalfleet:execute
list_sessionscursor, limitsessions[], next_cursorsessions:read
get_audit_logactor, action, cursoraudit_entries[]audit:read
list_fleet_runstag, statusruns[]fleet:read
get_recordingrecording_idmetadata, signed_urlrecordings:read
list_address_bookqueryendpoints[]address_book:read
get_security_postureagent_idchecks[], scoresecurity:read
manage_aclpolicy_id, rulepolicy, decisionacl:write
pair_agentpairing_keyagent_id, statusagents:write
SAFETY MODEL

AI agents cannot bypass the consent gate

Every AI action is evaluated like a human operator action: identity → ACL → risk → approval → execution → audit. The model favors bounded tools, explicit target scope, and auditable decisions over autonomous shell access.

{
  "mcpServers": {
    "tucdesk": {
      "command": "npx",
      "args": ["-y", "tucdesk-mcp"],
      "env": {
        "TUCDESK_API_URL": "https://api.yourdomain.com",
        "TUCDESK_API_KEY": "tdk_self_hosted_..."
      }
    }
  }
}
Self-hosted deployments use the same MCP server and the same approval pipeline. The only difference is the API URL and API key stored in the MCP client configuration.
MCP MARKETPLACE

Extend with the MCP tool catalog

The MCP Marketplace lets teams browse, enable, and configure integrations from a curated tool catalog. Custom tools can be published to an organization-private catalog with the same permission model as built-in tools.

Built-in tools

12 first-party tools covering agents, fleet, sessions, audit, ACL, and pairing.

Community catalog

Curated third-party integrations for monitoring platforms, ticketing systems, and CI/CD pipelines.

Private tools

Enterprise teams publish internal tools to their organization catalog — scoped, audited, and discoverable only within the workspace.

CONNECT YOUR AI AGENT

Give Claude control of your fleet — safely.

The TucDesk MCP server connects in minutes. Every AI action goes through the same ACL, approval gates, and audit chain as a human operator.

Works with Claude Desktop · GPT-4 · Any MCP client