Connectors · Developer & infrastructure
Graylog MCP server for AI agents.
actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Graylog and the rest of your systems. It gives your agent 662 Graylog actions (397 reads, 186 writes and 79 that wait for a confirmation) and holds the Graylog credential itself, so the agent never does. It paces Graylog's limits and records every call.
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/mcpdo { action: "graylog.users.get_page", intent: "check which Graylog account is connected"}# Get paginated list of users · read · 1 upstream call- 662actionsin one signed file
- 397readlook, never change
- 186writecreate and update
- 79wait for a yesdestructive, confirmed first
Set up
Connect Graylog in three steps.
- 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 - 02
Connect Graylog.
Username and secret. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.
access_tokenGraylog access tokenhostWhere your Graylog lives: your host
account { op: "connections.requirements", service: "graylog" } # free: exactly what to paste, and what is found for you - 03
Make the first call. Check before a write.
Ask in plain words; Claude picks the action. Before anything changes,
checkvalidates the call and prices it, for free.do { action: "graylog.users.get_page" }# get paginated list of users · read · 1 upstream callcheck { action: "graylog.users.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent
Graylog at a glance
- Sign-in
- Username and secret. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
- You provide
access_token- Setup fields
host- Limits we pace to
- 10 calls a second, per connection
- API covered
- Graylog 7.2.1+25725f2 REST API (OpenAPI 3.1, served at /api/openapi), at your Graylog instance's API base URL, which you enter when connecting
- Built from
- Graylog's documentation, read 23 October 2026GitHubgo2docs.graylog.org
- Service file
- Version 1.0.0, signed (Ed25519)
- Cached reads
- 317 of 397 reads, for up to 5 minutes; a write clears what it affects
- Shared entities
- 2, so ask can line Graylog up with your other systems
- Data
- Processed and stored in Sydney, Australia. No US region yet
Capabilities
What an AI agent can do in Graylog.
662 actions in 162 areas. Every one carries its effect, so a key can allow the reads and hold the rest.
- 397readlook, never change
- 186writecreate and update
- 79destructivewait for a confirmation
System lookup
2515 read · 6 write · 4 destructive
List available data adapters · List available caches · Create a new data adapter · Create a new cache
Streams
2010 read · 8 write · 2 destructive
Get a paginated list of streams · Create a stream · Get a single stream · Update a stream
Events definitions
198 read · 9 write · 2 destructive
Get a paginated list of event definitions · Create new event definition · Get an event definition · Update existing event definition
Tools
1818 read · 0 write · 0 destructive
Split and index test (tools) · Test contains string (tools) · Test grok (tools) · Test json (tools)
Users
187 read · 6 write · 5 destructive
Get paginated list of users · Create a new user account · Get user details by userId · Modify user details
Pipelines rules
1410 read · 3 write · 1 destructive
Create a processing rule from source · Get function descriptors · Get all processing rules · Retrieve the named processing rules in bulk
Indexer indices
1310 read · 1 write · 2 destructive
Get information of all specified indices and their shards · Reopen a closed index. This will also trigger an index ranges rebuild job · List all open, closed and reopened indices · Get a list of closed indices that can be reopened
System content packs
127 read · 2 write · 3 destructive
Upload a content pack · Install a revision of a content pack · Download a revision of a content pack · Get a revision of a content pack
154 more areas · 523 actions
- System inputs 12
- Pipelines pipelines 10
- Sidecar configurations 10
- Datanode 9
- Events notifications 9
- Search 9
- System index sets 9
- Roles 8
- Sidecar collectors 8
- System grok 8
- Views 8
- Authorization roles 7
- Collectors fleets 7
- Stream rules 7
- System 7
- System authentication services backends 7
- System index sets templates 7
- System notifications 7
- Aws 6
- Cluster 6
- Collectors 6
- Events 6
- Extractors 6
- Pipelines rulebuilder 6
- Sidecar 6
- Sidecar configuration variables 6
- Stream destinations filters 6
- System index sets field type profiles 6
- System indexer indices 6
- System input states 6
- System outputs 6
- System stats 6
- Collectors sources 5
- Data node rolling restart 5
- Search decorators 5
- System deflector 5
- System field types 5
- System index ranges 5
- System jobs 5
- System metrics 5
- Authorization shares 4
- Cluster debug support bundle 4
- Cluster input state 4
- Cluster system loggers 4
- Collectors config 4
- Data nodes API 4
- Data nodes rest API 4
- Datanode upgrade 4
- Entity lists 4
- Indexer indices templates 4
- Migration 4
- Op amp enrollment 4
- Pipelines connections 4
- Search simple 4
- Stream outputs 4
- System cluster 4
- System cluster config 4
- System debug events 4
- System debug support bundle 4
- System index sets types 4
- System loggers 4
- System notification message 4
- System URL allowlist 4
- Authorization capabilities 3
- Aws cloud trail 3
- Aws kinesis auto 3
- Cluster deflector 3
- Cluster jobs 3
- Cluster node metrics 3
- Content stream 3
- Favorite fields 3
- Favorites 3
- Field types 3
- Indexer cluster 3
- Messages 3
- Onboarding 3
- Search export 3
- Stream destinations filters builder 3
- System catalog 3
- System cluster stats 3
- System inputs types 3
- System mongodb 3
- System processing 3
- System sessions 3
- Telemetry 3
- Ca 2
- Client certificates 2
- Cluster processing 2
- Cluster processing status 2
- Indexer failures 2
- Indexer overview 2
- Search jobs 2
- Search metadata 2
- Search suggestions 2
- Sidecar administration 2
- Sidecar collector actions 2
- Start page 2
- Static fields 2
- System authentication HTTP header auth config 2
- System authentication services configuration 2
- System authentication services test 2
- System configuration 2
- System getting started guides 2
- System indices retention 2
- System indices rotation 2
- System message processors 2
- System permissions 2
- System processing status 2
- Authorization grants overview 1
- Aws config 1
- Certificate renewal 1
- Certificates 1
- Cluster journal 1
- Cluster load balancers 1
- Cluster lookup table 1
- Cluster metrics 1
- Cluster plugins 1
- Collectors activity 1
- Dashboards 1
- Enterprise 1
- Entity scope 1
- Entity suggestions 1
- Events entity types 1
- Hello world 1
- Legacy search absolute 1
- Legacy search keyword 1
- Legacy search relative 1
- Pipelines processing load 1
- Pipelines simulator 1
- Quick jump 1
- Search functions 1
- Search pivot export 1
- Search query strings 1
- Search saved 1
- Search validation 1
- Stream routing rules 1
- Stream rules inputs 1
- Streams metrics 1
- System authentication services 1
- System cluster traffic 1
- System codecs types 1
- System datanodes 1
- System fields 1
- System index set defaults 1
- System journal 1
- System load balancers 1
- System messages 1
- System opensearch 1
- System plugins 1
- System search version 1
- System service manager 1
- System throughput 1
- Token usage 1
- Views qualifying views 1
Top actions
The Graylog API, shaped for agents.
The ids your agent types, what each does, and the one name it shares with other systems. 27 of Graylog's 27 action names are shared with at least one other connector, so an agent learns them once.
| Action | What it does | Effect | Same name in |
|---|---|---|---|
graylog.users.get_pageGet paginated list of users | Get paginated list of users. | read | identity.user.list474 connectors |
graylog.authorization_roles.get_listGet a paginated list of all roles | Get a paginated list of all roles. | read | identity.role.list184 connectors |
graylog.users.createCreate a new user account | Create a new user account. | write | identity.user.create262 connectors |
graylog.users.deleteRemoves a user account | Removes a user account. | destructive | identity.user.delete253 connectors |
graylog.authorization_roles.getGet a single role | Get a single role. | read | identity.role.get127 connectors |
graylog.events_definitions.get_pageGet a paginated list of event definitions | Get a paginated list of event definitions. | read | monitoring.monitor.list32 connectors |
graylog.events_definitions.createCreate new event definition | Create new event definition. | write | monitoring.monitor.create27 connectors |
graylog.events_notifications.get_pageGet a paginated list of event notifications | Get a paginated list of event notifications. | read | monitoring.notification_channel.list18 connectors |
graylog.events_notifications.createCreate new notification definition | Create new notification definition. | write | monitoring.notification_channel.create16 connectors |
graylog.dashboards.viewsGet a list of all dashboards | Get a list of all dashboards. | read | monitoring.dashboard.list15 connectors |
graylog.streams.get_pageGet a paginated list of streams | Get a paginated list of streams. | read | monitoring.log_stream.list12 connectors |
graylog.streams.createCreate a stream | Create a stream. | write | monitoring.log_stream.create8 connectors |
Try it
Prompts to paste into Claude.
Each one names the Graylog actions it will call, so you know what it reads and what it changes before you send it.
- Readread
Who has access in Graylog? List every user and their role.
calls
graylog.users.get_page - Writewrite
Create a new user account in Graylog. Show me exactly what you will send before you save it.
calls
graylog.users.create
Governance for Graylog
Destructive actions wait for a yes.
79 Graylog actions are destructive. The first 10:
- Removes a user account
graylog.users.delete - Delete a role
graylog.authorization_roles.delete - Delete event definition
graylog.events_definitions.delete - Delete a notification
graylog.events_notifications.delete - Delete a stream
graylog.streams.delete - Remove the named role and dissociate any users from it
graylog.roles.delete - Delete view
graylog.views.delete - Shutdown (system)
graylog.system.shutdown - Shutdown (cluster)
graylog.cluster.shutdown - Add a user to a role
graylog.roles.add_member
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.
Removes a user account?
intent: the user asked me to removes a user account
account { op: "keys.create", name: "graylog-agent", allowed_actions: ["graylog.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "graylog.users.delete", approver: "[email protected]" }, { match: "graylog.authorization_roles.delete", approver: "[email protected]" }, { match: "graylog.events_definitions.delete", approver: "[email protected]" } ]}Cost
What Graylog costs on actionlake.
Every Graylog action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Graylog 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.
- 1upstream call per actionall 662 Graylog actions
- 662actions pageeach page of a long list is one call
- 317reads can be cacheda cache hit costs nothing
- 100,000calls a month, freepaid plans from US$49 a month for 250,000
Action index
Every Graylog action.
662 actions by area: the id your agent calls, what it does, and its effect.
System lookup25
graylog.system_lookup.adaptersList available data adaptersreadgraylog.system_lookup.cachesList available cachesread- and 23 more in this area
Streams20
graylog.streams.createCreate a streamwritegraylog.streams.get_pageGet a paginated list of streamsread- and 18 more in this area
Events definitions19
graylog.events_definitions.createCreate new event definitionwritegraylog.events_definitions.getGet an event definitionread- and 17 more in this area
Tools18
graylog.tools.split_and_index_testSplit and index test (tools)readgraylog.tools.test_contains_stringTest contains string (tools)read- and 16 more in this area
Users18
graylog.users.change_userModify user detailswritegraylog.users.createCreate a new user accountwrite- and 16 more in this area
Pipelines rules14
graylog.pipelines_rules.create_from_parserCreate a processing rule from sourcewritegraylog.pipelines_rules.function_descriptorsGet function descriptorsread- and 12 more in this area
Indexer indices13
graylog.indexer_indices.allList all open, closed and reopened indicesreadgraylog.indexer_indices.closedGet a list of closed indices that can be reopenedread- and 11 more in this area
System content packs12
graylog.system_content_packs.create_content_packUpload a content packwritegraylog.system_content_packs.download_content_pack_revisionsDownload a revision of a content packread- and 10 more in this area
System inputs12
graylog.system_inputs.createLaunch input on this nodewritegraylog.system_inputs.get_pageGet a paginated list of inputsread- and 10 more in this area
Pipelines pipelines10
graylog.pipelines_pipelines.create_from_parserCreate a processing pipeline from sourcewritegraylog.pipelines_pipelines.get_allGet all processing pipelinesread- and 8 more in this area
Sidecar configurations10
graylog.sidecar_configurations.copy_configurationCopy a configurationwritegraylog.sidecar_configurations.create_configurationCreate new configurationwrite- and 8 more in this area
Datanode9
graylog.datanode.bulk_startStart multiple nodes in the clusterwritegraylog.datanode.bulk_stopStop multiple nodes in the clusterwrite- and 7 more in this area
Events notifications9
graylog.events_notifications.createCreate new notification definitionwritegraylog.events_notifications.getGet a notificationread- and 7 more in this area
Search9
graylog.search.create_search_v2Create a search querywritegraylog.search.execute_queryExecute the referenced search query asynchronouslywrite- and 7 more in this area
System index sets9
graylog.system_index_sets.getGet index setreadgraylog.system_index_sets.global_statsGet stats of all index setsread- and 7 more in this area
Roles8
graylog.roles.createCreate a new rolewritegraylog.roles.get_membersRetrieve the role's membersread- and 6 more in this area
Sidecar collectors8
graylog.sidecar_collectors.copy_collectorCopy a collectorwritegraylog.sidecar_collectors.create_collectorCreate a new collectorwrite- and 6 more in this area
System grok8
graylog.system_grok.bulk_update_patternsAdd a list of new patternswritegraylog.system_grok.create_patternAdd a new named patternwrite- and 6 more in this area
Views8
graylog.views.createCreate a new viewwritegraylog.views.duplicateDuplicate an existing viewwrite- and 6 more in this area
Authorization roles7
graylog.authorization_roles.deleteDelete a roledestructivegraylog.authorization_roles.getGet a single roleread- and 5 more in this area
Collectors fleets7
graylog.collectors_fleets.bulk_statsGet statistics for all fleetsreadgraylog.collectors_fleets.createCreate a new fleetwrite- and 5 more in this area
Stream rules7
graylog.stream_rules.createCreate a stream rulewritegraylog.stream_rules.getGet a single stream rulesread- and 5 more in this area
System7
graylog.system.get_metricsGet metrics for multiple inputsreadgraylog.system.jvmGet JVM informationread- and 5 more in this area
System authentication services backends7
graylog.system_authentication_services_backends.createCreates a new authentication service backendwritegraylog.system_authentication_services_backends.getReturns the authentication service backend for the given IDread- and 5 more in this area
System index sets templates7
graylog.system_index_sets_templates.built_insGets built-in templatesreadgraylog.system_index_sets_templates.createCreates a new editable templatewrite- and 5 more in this area
System notifications7
graylog.system_notifications.bulk_deleteBulk delete notifications by their IDsdestructivegraylog.system_notifications.get_countGet the count of active system notificationsread- and 5 more in this area
Aws6
graylog.aws.createCreate a new AWS inputwritegraylog.aws.get_kinesis_streamsGet all available Kinesis streams for the specified regionread- and 4 more in this area
Cluster6
graylog.cluster.cluster_process_buffer_dumpGet a process buffer dump of all cluster nodesreadgraylog.cluster.getGet system overview of all Graylog nodesread- and 4 more in this area
Collectors6
graylog.collectors.find_instancesGet a paginated list of collector instancesreadgraylog.collectors.get_instanceGet a collector instanceread- and 4 more in this area
Events6
graylog.events.filter_optionsGet the available values for the given event fieldsreadgraylog.events.getGet event by IDread- and 4 more in this area
Extractors 6Pipelines rulebuilder 6Sidecar 6Sidecar configuration variables 6Stream destinations filters 6System index sets field type profiles 6System indexer indices 6System input states 6System outputs 6System stats 6Collectors sources 5Data node rolling restart 5Search decorators 5System deflector 5System field types 5System index ranges 5System jobs 5System metrics 5Authorization shares 4Cluster debug support bundle 4Cluster input state 4Cluster system loggers 4Collectors config 4Data nodes API 4Data nodes rest API 4Datanode upgrade 4Entity lists 4Indexer indices templates 4Migration 4Op amp enrollment 4Pipelines connections 4Search simple 4Stream outputs 4System cluster 4System cluster config 4System debug events 4System debug support bundle 4System index sets types 4System loggers 4System notification message 4System URL allowlist 4Authorization capabilities 3Aws cloud trail 3Aws kinesis auto 3Cluster deflector 3Cluster jobs 3Cluster node metrics 3Content stream 3Favorite fields 3Favorites 3Field types 3Indexer cluster 3Messages 3Onboarding 3Search export 3Stream destinations filters builder 3System catalog 3System cluster stats 3System inputs types 3System mongodb 3System processing 3System sessions 3Telemetry 3Ca 2Client certificates 2Cluster processing 2Cluster processing status 2Indexer failures 2Indexer overview 2Search jobs 2Search metadata 2Search suggestions 2Sidecar administration 2Sidecar collector actions 2Start page 2Static fields 2System authentication HTTP header auth config 2System authentication services configuration 2System authentication services test 2System configuration 2System getting started guides 2System indices retention 2System indices rotation 2System message processors 2System permissions 2System processing status 2Authorization grants overview 1Aws config 1Certificate renewal 1Certificates 1Cluster journal 1Cluster load balancers 1Cluster lookup table 1Cluster metrics 1Cluster plugins 1Collectors activity 1Dashboards 1Enterprise 1Entity scope 1Entity suggestions 1Events entity types 1Hello world 1Legacy search absolute 1Legacy search keyword 1Legacy search relative 1Pipelines processing load 1Pipelines simulator 1Quick jump 1Search functions 1Search pivot export 1Search query strings 1Search saved 1Search validation 1Stream routing rules 1Stream rules inputs 1Streams metrics 1System authentication services 1System cluster traffic 1System codecs types 1System datanodes 1System fields 1System index set defaults 1System journal 1System load balancers 1System messages 1System opensearch 1System plugins 1System search version 1System service manager 1System throughput 1Token usage 1Views qualifying views 1
This index shows a sample of each area. All 662 actions, with their inputs and prices, are in the catalogue, which a free sandbox key can search.
Questions
The Graylog MCP server, answered.
Is there a Graylog MCP server for Claude?
Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 662 Graylog actions across system lookup, streams, events definitions and tools, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Graylog.
What do I need to connect Graylog?
Graylog access token. Plus your host. The free call account { op: "connections.requirements", service: "graylog" } lists exactly what to paste.
Can an AI agent delete or change things in Graylog?
Only if its key allows it, and only with an explicit confirmation. 79 Graylog actions are destructive, including removes a user account, delete a role and delete event definition. 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 Graylog API limit?
actionlake paces every call to the limits in the Graylog service file: 10 calls a second per connection. Repeated reads are answered from cache (317 Graylog actions can be), which never reaches Graylog.
What does a Graylog action cost?
One upstream call, the only unit actionlake bills. A list that pages bills one call per page (662 Graylog actions page). Cache hits, searches, dry runs and calls Graylog 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 Graylog API does it cover?
The Graylog 7.2.1+25725f2 REST API (OpenAPI 3.1, served at /api/openapi) at your Graylog instance's API base URL, which you enter when connecting. It is built from Graylog's documentation as read on 23 October 2026. 662 actions in 162 areas, each one in the signed service file (version 1.0.0).
Does actionlake keep my Graylog 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 Graylog 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.
Give your agent Graylog today.
Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.