// SCAN REPORT

Kestra Python MCP Server

39 tools. 26 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

26 can modify or destroy data

13 read-only

39 tools total

Community server · catalogue entry verified 11/06/2026

How to control Kestra Python MCP Server ↓

TOOL MAP

What Kestra Python MCP Server exposes to your agents

Read (13) Write / Execute (16) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Kestra Python MCP Server tools

Destructive · High delete_execution_logs This tool performs a destructive operation by deleting execution logs. Destructive · High delete_flow_logs The 'delete' operation in the tool name indicates this is a destructive action that irreversibly removes log data. Execute · High force_run_execution This tool forcibly triggers/resumes a workflow execution, which is an Execute-category action. Execute · High execute_flow This tool triggers the execution of a Kestra workflow, which runs external operations whose effects depend on the workflow definition and arguments.

26 of Kestra Python MCP Server's 39 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Kestra Python MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Kestra Python MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_execution_logs": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_execution_labels": {
    "limits": [
      {
        "counter": "add_execution_labels_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "download_execution_logs": {
    "limits": [
      {
        "counter": "download_execution_logs_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Kestra Python MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON KESTRA PYTHON →

Free to start. No card required.

FULL CATALOGUE

All 39 Kestra Python MCP Server tools

DESTRUCTIVE 2 tools

Destructive delete_execution_logs delete_execution_logs Destructive delete_flow_logs delete_flow_logs

EXECUTE 8 tools

Execute force_run_execution Force run an execution only if it is in CREATED, PAUSED, or QUEUED state. Execute execute_flow execute_flow Execute restart_execution restart_execution Execute backfill_executions backfill_executions Execute change_taskrun_state change_taskrun_state Execute manage_executions manage_executions Execute replay_execution replay_execution Execute resume_execution resume_execution

WRITE 8 tools

Write add_execution_labels add_execution_labels Write create_flow_from_yaml Create or update a Kestra flow from a raw YAML definition. Returns the created or updated flow's JSON metadata Write generate_flow generate_flow Write invite_user invite_user Write manage_announcements manage_announcements Write manage_flow manage_flow Write manage_invitations manage_invitations Write manage_kv_store manage_kv_store

READ 13 tools

Read download_execution_logs download_execution_logs Read find_flow find_flow Read get_execution_logs get_execution_logs Read get_instance_info Get instance metadata: configuration (default) or license info. Read list_executions list_executions Read list_flows_in_namespace Retrieve all flows in a given namespace. Read list_flows_with_triggers list_flows_with_triggers Read list_namespace_dependencies Retrieve all flow-to-flow dependencies within a given namespace and render them as an ASCII dependency graph u Read list_namespaces list_namespaces Read search_apps search_apps Read search_flows search_flows Read search_logs search_logs Read follow_execution_logs follow_execution_logs

OTHER 8 tools

Other generate_app generate_app Other generate_dashboard generate_dashboard Other generate_test generate_test Other manage_apps manage_apps Other manage_group manage_group Other manage_tests manage_tests Other namespace_directory_action namespace_directory_action Other namespace_file_action namespace_file_action

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Kestra Python MCP Server

Can an AI agent delete data through the Kestra Python MCP Server MCP server? +

Yes. The Kestra Python MCP Server server exposes 2 destructive tools including delete_execution_logs, delete_flow_logs. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Kestra Python MCP Server? +

The Kestra Python MCP Server server has 8 write tools including add_execution_labels, create_flow_from_yaml, generate_flow. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Kestra Python MCP Server.

How many tools does the Kestra Python MCP Server MCP server expose? +

39 tools across 4 categories: Destructive, Execute, Read, Write. 13 are read-only. 26 can modify, create, or delete data.

How do I enforce a policy on Kestra Python MCP Server? +

Register the Kestra Python MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Kestra Python MCP Server tool call.

Deterministic rules across all 39 Kestra Python MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON KESTRA PYTHON →

Free to start. No card required.

39 Kestra Python MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.