--- title: "Wazuh MCP server for AI agents - actionlake" description: "Give Claude 178 Wazuh actions through one MCP server: security, agents, cluster, manager. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/wazuh updated: 2026-10-23 --- Connectors · MSP & PSA # Wazuh MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Wazuh and the rest of your systems. It gives your agent 178 Wazuh actions (115 reads, 38 writes and 25 that wait for a confirmation) and holds the Wazuh credential itself, so the agent never does. It paces Wazuh's limits and records every call. [Connect Wazuh free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) 100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you. `claude mcp add --transport http actionlake https://connect.actionlake.com/mcp` the first call ``` do { action: "wazuh.security.users_list", intent: "check which Wazuh account is connected" } # List users · read · 1 upstream call ``` - 178 actions in one signed file - 115 read look, never change - 38 write create and update - 25 wait for a yes destructive, confirmed first Set up ## Connect Wazuh in three steps. 1. 01 ### Add actionlake to Claude. Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us. `https://connect.actionlake.com/mcp` 2. 02 ### Connect Wazuh. Session login. actionlake opens the session and renews it when it expires. actionlake stores what you paste write-only, sealed under your tenant's key. - `username` Wazuh API user (a user from Server management > Security, e.g. `wazuh-wui`, or a dedicated user with the RBAC roles… - `password` Password of that Wazuh API user - `host` Where your Wazuh lives: your host ``` account { op: "connections.requirements", service: "wazuh" } # free: exactly what to paste, and what is found for you ``` 3. 03 ### Make the first call. Check before a write. Ask in plain words; Claude picks the action. Before anything changes, `check` validates the call and prices it, for free. ``` do { action: "wazuh.security.users_list" } # list users · read · 1 upstream call check { action: "wazuh.security.users_create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Wazuh at a glance **Sign-in** Session login. actionlake opens the session and renews it when it expires. **You provide** `username` `password` **Setup fields** `host` **Limits we pace to** 300 calls a minute, per connection **API covered** Wazuh server API 4.14 (OpenAPI 3.0.0, spec v4.14.9), at your Wazuh instance's API base URL, which you enter when connecting **Built from** Wazuh's documentation, read 23 October 2026[OpenAPI spec (GitHub)](https://raw.githubusercontent.com/wazuh/wazuh/v4.14.9/api/api/spec/spec.yaml) [documentation.wazuh.com](https://documentation.wazuh.com/current/user-manual/api/reference.html) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 115 of 115 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 4, so ask can line Wazuh up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Wazuh. 178 actions in 21 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **115** read look, never change - **38** write create and update - **25** destructive wait for a confirmation 1. ### Security 31 9 read · 10 write · 12 destructive List users · List roles · Add user · Update users 2. ### Agents 30 14 read · 12 write · 4 destructive List agents · Add agent · Delete agents · Restart agent 3. ### Cluster 23 20 read · 3 write · 0 destructive Get node logs · Get nodes info · Reloads the analysisd process for the nodes · Get nodes API config 4. ### Manager 18 15 read · 3 write · 0 destructive Get logs · Reloads the analysisd process for the master or local node · Get API config · Get active configuration 5. ### Syscollector 13 13 read · 0 write · 0 destructive Get agent browser extensions · Get agent groups · Get agent hotfixes · Get agent netaddr 6. ### Experimental 12 10 read · 0 write · 2 destructive Get agents CIS-CAT results · Get agents hardware · Get agents hotfixes · Get agents netaddr 7. ### Groups 8 5 read · 2 write · 1 destructive Get agents in a group · Get group configuration · Create a group · Get group files 8. ### Mitre 7 7 read · 0 write · 0 destructive Get MITRE groups · Get MITRE mitigations · Get MITRE references · Get MITRE software **13 more areas · 36 actions** - Rules **7** - Decoders **6** - Lists **5** - Rootcheck **4** - Syscheck **4** - Logtest **2** - Sca **2** - Active response **1** - API **1** - Ciscat **1** - Events **1** - Overview **1** - Tasks **1** Top actions ## The Wazuh API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 17 of Wazuh's 17 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `wazuh.security.users_list` List users | List users. | read | `identity.user.list` 474 connectors | | `wazuh.security.roles_list` List roles | List roles. | read | `identity.role.list` 184 connectors | | `wazuh.security.users_create` Add user | Add user. | write | `identity.user.create` 262 connectors | | `wazuh.security.roles_create` Add role | Add role. | write | `identity.role.create` 105 connectors | | `wazuh.agents.list` List agents | List agents. | read | `device.endpoint.list` 65 connectors | | `wazuh.security.users_delete` Delete users | Delete users. | destructive | `identity.user.delete` 253 connectors | | `wazuh.security.policies_list` List policies | List policies. | read | `security.policy.list` 36 connectors | | `wazuh.security.me` Get current user info | Get current user info. | read | `identity.current_user.get` 307 connectors | | `wazuh.agents.create` Add agent | Add agent. | write | `device.endpoint.create` 12 connectors | | `wazuh.security.policies_create` Add policy | Add policy. | write | `security.policy.create` 25 connectors | | `wazuh.rules.list` List rules | List rules. | read | this connector | | `wazuh.agents.insert` Add agent full | Add agent full. | write | this connector | Try it ## Prompts to paste into Claude. Each one names the Wazuh actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Which Wazuh devices have not checked in for a week? calls `wazuh.agents.list` 2. Write write Add user in Wazuh. Show me exactly what you will send before you save it. calls `wazuh.security.users_create` Governance for Wazuh ## Destructive actions wait for a yes. 25 Wazuh actions are destructive. These are all of them: - Delete users `wazuh.security.users_delete` - Delete roles `wazuh.security.roles_delete` - Delete agents `wazuh.agents.delete` - Delete policies `wazuh.security.policies_delete` - Delete groups `wazuh.groups.delete` - Delete rules file `wazuh.rules.file_delete` - Remove agent from group `wazuh.agents.group_remove` - Restore default security config `wazuh.security.config_reset` - Delete security rules `wazuh.security.rules_delete` - Add security rules to role `wazuh.security.role_rules_add` - Add roles to user `wazuh.security.user_roles_add` - Remove agents from group `wazuh.agents.bulk_group_remove` - Remove agent from groups `wazuh.agents.groups_remove_all` - Add policies to role `wazuh.security.role_policies_add` - Remove security rules from role `wazuh.security.role_rules_remove` - Revoke JWT tokens `wazuh.security.tokens_revoke_all` - Remove roles from user `wazuh.security.user_roles_remove` - Remove policies from role `wazuh.security.role_policies_remove` - Delete CDB list file `wazuh.lists.file_delete` - End session `wazuh.logtest.session_end` - Delete decoders file `wazuh.decoders.file_delete` - Clear results `wazuh.syscheck.results_clear` - Clear results `wazuh.rootcheck.results_clear` - Clear agents FIM results `wazuh.experimental.syscheck_clear` - Clear rootcheck results `wazuh.experimental.rootcheck_clear` A destructive action runs only with `confirm: true`. Under the `human` policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after. do wazuh.agents.delete confirm_policy: **human** Delete agents? **intent:** the user asked me to delete agents run suspended · waiting for a named person · key _wazuh-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "wazuh-agent", allowed_actions: ["wazuh.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "wazuh.security.users_delete", approver: "lead@example.com" }, { match: "wazuh.security.roles_delete", approver: "lead@example.com" }, { match: "wazuh.agents.delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Wazuh only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Wazuh costs on actionlake. Every Wazuh action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Wazuh refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. - 1 upstream call per action all 178 Wazuh actions - 178 actions page each page of a long list is one call - 115 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every Wazuh action. 178 actions by area: the id your agent calls, what it does, and its effect. **Security 31** - `wazuh.security.config_get` Get security config read - `wazuh.security.config_reset` Restore default security config destructive - `wazuh.security.config_update` Update security config write - `wazuh.security.me` Get current user info read - `wazuh.security.my_policies` Get current user processed policies read - `wazuh.security.policies_create` Add policy write - `wazuh.security.policies_delete` Delete policies destructive - `wazuh.security.policies_list` List policies read - `wazuh.security.policies_update` Update policy write - `wazuh.security.rbac_actions_list` List RBAC actions read - `wazuh.security.rbac_resources_list` List RBAC resources read - `wazuh.security.role_policies_add` Add policies to role destructive - `wazuh.security.role_policies_remove` Remove policies from role destructive - `wazuh.security.role_rules_add` Add security rules to role destructive - `wazuh.security.role_rules_remove` Remove security rules from role destructive - `wazuh.security.roles_create` Add role write - `wazuh.security.roles_delete` Delete roles destructive - `wazuh.security.roles_list` List roles read - `wazuh.security.roles_update` Update role write - `wazuh.security.rules_create` Add security rule write - `wazuh.security.rules_delete` Delete security rules destructive - `wazuh.security.rules_list` List security rules read - `wazuh.security.rules_update` Update security rule write - `wazuh.security.tokens_revoke_all` Revoke JWT tokens destructive - `wazuh.security.user_roles_add` Add roles to user destructive - `wazuh.security.user_roles_remove` Remove roles from user destructive - `wazuh.security.users_create` Add user write - `wazuh.security.users_delete` Delete users destructive - `wazuh.security.users_list` List users read - `wazuh.security.users_run_as_set` Enable/Disable run_as write - `wazuh.security.users_update` Update users write **Agents 30** - `wazuh.agents.bulk_group_assign` Assign agents to group write - `wazuh.agents.bulk_group_remove` Remove agents from group destructive - `wazuh.agents.bulk_restart` Restart agents write - `wazuh.agents.component_stats` Get agent's component stats read - `wazuh.agents.config_get` Get active configuration read - `wazuh.agents.create` Add agent write - `wazuh.agents.daemon_stats` Get Wazuh daemon stats from an agent read - `wazuh.agents.delete` Delete agents destructive - `wazuh.agents.distinct_fields` List agents distinct read - `wazuh.agents.group_assign` Assign agent to group write - `wazuh.agents.group_remove` Remove agent from group destructive - `wazuh.agents.group_sync_status` Get configuration sync status read - `wazuh.agents.groups_remove_all` Remove agent from groups destructive - `wazuh.agents.insert` Add agent full write - `wazuh.agents.key_get` Get key read - `wazuh.agents.list` List agents read - `wazuh.agents.list_outdated` List outdated agents read - `wazuh.agents.list_ungrouped` List agents without group read - `wazuh.agents.quick_create` Add agent quick write - `wazuh.agents.reconnect` Force reconnect agents write - `wazuh.agents.restart` Restart agent write - `wazuh.agents.restart_by_group` Restart agents in group write - `wazuh.agents.restart_by_node` Restart agents in node write - `wazuh.agents.summary` Summarize agents information read - `wazuh.agents.summary_os` Summarize agents OS read - `wazuh.agents.summary_status` Summarize agents status read - `wazuh.agents.uninstall_permission` Check user's permission to uninstall agents read - `wazuh.agents.upgrade` Upgrade agents write - `wazuh.agents.upgrade_custom` Upgrade agents custom write - `wazuh.agents.upgrade_results` Get upgrade results read **Cluster 23** - `wazuh.cluster.analysisd_reload` Reloads the analysisd process for the nodes write - `wazuh.cluster.api_config` Get nodes API config read - `wazuh.cluster.configuration_validate` Check nodes config read - `wazuh.cluster.healthcheck` Get nodes healthcheck read - `wazuh.cluster.local_config` Get local node config read - `wazuh.cluster.local_info` Get local node info read - `wazuh.cluster.node_component_config_get` Get node active configuration read - `wazuh.cluster.node_configuration_get` Get node config read - `wazuh.cluster.node_configuration_update` Update node configuration write - `wazuh.cluster.node_daemon_stats` Get Wazuh daemon stats from a cluster node read - `wazuh.cluster.node_info` Get node info read - `wazuh.cluster.node_logs_list` Get node logs read - `wazuh.cluster.node_logs_summary` Get node logs summary read - `wazuh.cluster.node_stats` Get node stats read - `wazuh.cluster.node_stats_analysisd` Get node stats analysisd read - `wazuh.cluster.node_stats_hourly` Get node stats hour read - `wazuh.cluster.node_stats_remoted` Get node stats remoted read - `wazuh.cluster.node_stats_weekly` Get node stats week read - `wazuh.cluster.node_status` Get node status read - `wazuh.cluster.nodes_list` Get nodes info read - `wazuh.cluster.restart` Restart nodes write - `wazuh.cluster.ruleset_sync_status` Get cluster nodes ruleset synchronization status read - `wazuh.cluster.status` Get cluster status read **Manager 18** - `wazuh.manager.analysisd_reload` Reloads the analysisd process for the master or local node write - `wazuh.manager.api_config` Get API config read - `wazuh.manager.component_config_get` Get active configuration read - `wazuh.manager.configuration_get` Get configuration read - `wazuh.manager.configuration_update` Update Wazuh configuration write - `wazuh.manager.configuration_validate` Check config read - `wazuh.manager.daemon_stats` Get Wazuh daemon stats read - `wazuh.manager.info` Get information read - `wazuh.manager.logs_list` Get logs read - `wazuh.manager.logs_summary` Get logs summary read - `wazuh.manager.restart` Restart manager write - `wazuh.manager.stats` Get stats read - `wazuh.manager.stats_analysisd` Get stats analysisd read - `wazuh.manager.stats_hourly` Get stats hour read - `wazuh.manager.stats_remoted` Get stats remoted read - `wazuh.manager.stats_weekly` Get stats week read - `wazuh.manager.status` Get status read - `wazuh.manager.version_check` Check available updates read **Syscollector 13** - `wazuh.syscollector.browser_extensions_list` Get agent browser extensions read - `wazuh.syscollector.groups_list` Get agent groups read - `wazuh.syscollector.hardware` Get agent hardware read - `wazuh.syscollector.hotfixes_list` Get agent hotfixes read - `wazuh.syscollector.netaddr_list` Get agent netaddr read - `wazuh.syscollector.netiface_list` Get agent netiface read - `wazuh.syscollector.netproto_list` Get agent netproto read - `wazuh.syscollector.os` Get agent OS read - `wazuh.syscollector.packages_list` Get agent packages read - `wazuh.syscollector.ports_list` Get agent ports read - `wazuh.syscollector.processes_list` Get agent processes read - `wazuh.syscollector.services_list` Get agent services read - `wazuh.syscollector.users_list` Get agent users read **Experimental 12** - `wazuh.experimental.ciscat_results_list` Get agents CIS-CAT results read - `wazuh.experimental.hardware_list` Get agents hardware read - `wazuh.experimental.hotfixes_list` Get agents hotfixes read - `wazuh.experimental.netaddr_list` Get agents netaddr read - `wazuh.experimental.netiface_list` Get agents netiface read - `wazuh.experimental.netproto_list` Get agents netproto read - `wazuh.experimental.os_list` Get agents OS read - `wazuh.experimental.packages_list` Get agents packages read - `wazuh.experimental.ports_list` Get agents ports read - `wazuh.experimental.processes_list` Get agents processes read - `wazuh.experimental.rootcheck_clear` Clear rootcheck results destructive - `wazuh.experimental.syscheck_clear` Clear agents FIM results destructive **Groups 8** - `wazuh.groups.agents_list` Get agents in a group read - `wazuh.groups.configuration_get` Get group configuration read - `wazuh.groups.configuration_update` Update group configuration write - `wazuh.groups.create` Create a group write - `wazuh.groups.delete` Delete groups destructive - `wazuh.groups.file_get` Get a file in group read - `wazuh.groups.files_list` Get group files read - `wazuh.groups.list` Get groups read **Mitre 7** - `wazuh.mitre.groups_list` Get MITRE groups read - `wazuh.mitre.metadata` Get MITRE metadata read - `wazuh.mitre.mitigations_list` Get MITRE mitigations read - `wazuh.mitre.references_list` Get MITRE references read - `wazuh.mitre.software_list` Get MITRE software read - `wazuh.mitre.tactics_list` Get MITRE tactics read - `wazuh.mitre.techniques_list` Get MITRE techniques read **Rules 7** - `wazuh.rules.file_delete` Delete rules file destructive - `wazuh.rules.file_get` Get rules file content read - `wazuh.rules.file_put` Update rules file write - `wazuh.rules.files_list` Get files read - `wazuh.rules.groups_list` Get groups read - `wazuh.rules.list` List rules read - `wazuh.rules.requirement_values_list` Get requirements read **Decoders 6** - `wazuh.decoders.file_delete` Delete decoders file destructive - `wazuh.decoders.file_get` Get decoders file content read - `wazuh.decoders.file_put` Update decoders file write - `wazuh.decoders.files_list` Get files read - `wazuh.decoders.list` List decoders read - `wazuh.decoders.parents_list` Get parent decoders read **Lists 5** - `wazuh.lists.file_delete` Delete CDB list file destructive - `wazuh.lists.file_get` Get CDB list file content read - `wazuh.lists.file_put` Update CDB list file write - `wazuh.lists.files_list` Get CDB lists files read - `wazuh.lists.list` Get CDB lists info read **Rootcheck 4** - `wazuh.rootcheck.last_scan` Get last scan datetime read - `wazuh.rootcheck.results_clear` Clear results destructive - `wazuh.rootcheck.results_list` Get results read - `wazuh.rootcheck.run` Run scan write **Syscheck 4** - `wazuh.syscheck.files_list` Get results read - `wazuh.syscheck.last_scan` Get last scan datetime read - `wazuh.syscheck.results_clear` Clear results destructive - `wazuh.syscheck.run` Run scan write **Logtest 2** - `wazuh.logtest.run` Run logtest write - `wazuh.logtest.session_end` End session destructive **Sca 2** - `wazuh.sca.checks_list` Get policy checks read - `wazuh.sca.policies_list` Get results read **Active response 1** - `wazuh.active_response.run` Run command write **API 1** - `wazuh.api.info` Get API info read **Ciscat 1** - `wazuh.ciscat.results_list` Get results read **Events 1** - `wazuh.events.ingest` Ingest events write **Overview 1** - `wazuh.overview.agents` Get agents overview read **Tasks 1** - `wazuh.tasks.status_list` List tasks read Questions ## The Wazuh MCP server, answered. **Is there a Wazuh MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 178 Wazuh actions across security, agents, cluster and manager, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Wazuh. **What do I need to connect Wazuh?** Wazuh API user (a user from Server management > Security, e.g. `wazuh-wui`, or a dedicated user with the RBAC roles… and Password of that Wazuh API user. Plus your host. The free call account { op: "connections.requirements", service: "wazuh" } lists exactly what to paste. **Can an AI agent delete or change things in Wazuh?** Only if its key allows it, and only with an explicit confirmation. 25 Wazuh actions are destructive, including delete users, delete roles and delete agents. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it. **Will an AI agent use up my Wazuh API limit?** actionlake paces every call to the limits in the Wazuh service file: 300 calls a minute per connection. Repeated reads are answered from cache (115 Wazuh actions can be), which never reaches Wazuh. **What does a Wazuh action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (178 Wazuh actions page). Cache hits, searches, dry runs and calls Wazuh refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. **Which Wazuh API does it cover?** The Wazuh server API 4.14 (OpenAPI 3.0.0, spec v4.14.9) at your Wazuh instance's API base URL, which you enter when connecting. It is built from Wazuh's documentation as read on 23 October 2026. 178 actions in 21 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Wazuh data, and where?** actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Wazuh credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models. **Which AI clients can use it?** Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names. ## More connectors like Wazuh Shares the most action names with - [Imperva Cloud Application Security 12](https://actionlake.com/connectors/imperva-cloud-application-security) - [Jamf Pro 11](https://actionlake.com/connectors/jamf-pro) - [Acronis Cyber Protect Cloud 11](https://actionlake.com/connectors/acronis-cyber-protect-cloud) - [Action1 10](https://actionlake.com/connectors/action1) - [TP-Link Omada Open API 9](https://actionlake.com/connectors/tp-link-omada-open-api) - [Sublime Security 8](https://actionlake.com/connectors/sublime-security) Joins with, on shared entities - [Microsoft 365 Users 3](https://actionlake.com/connectors/microsoft-365-users) - [Cloudflare 3](https://actionlake.com/connectors/cloudflare) - [Okta 3](https://actionlake.com/connectors/okta) - [JumpCloud 3](https://actionlake.com/connectors/jumpcloud) - [Veeam Backup & Replication 3](https://actionlake.com/connectors/veeam-backup-and-replication) - [Tenable Vulnerability Management 3](https://actionlake.com/connectors/tenable-vulnerability-management) Browse - [All MSP & PSA connectors](https://actionlake.com/connectors/category/msp-and-psa) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Wazuh; the name is the vendor's own. Counts are from the Wazuh service file, version 1.0.0. ## Give your agent Wazuh today. [Connect Wazuh free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/wazuh More: https://actionlake.com/llms.txt