Skip to content

Connectors · Data & integration

Jenkins MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Jenkins and the rest of your systems. It gives your agent 59 Jenkins actions (35 reads, 15 writes and 9 that wait for a confirmation) and holds the Jenkins credential itself, so the agent never does. It paces Jenkins'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/mcp
the first call
do {  action: "jenkins.users.list",  intent: "check which Jenkins account is connected"}# List users · read · 1 upstream call
  • 59actionsin one signed file
  • 35readlook, never change
  • 15writecreate and update
  • 9wait for a yesdestructive, confirmed first

Set up

Connect Jenkins 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 Jenkins.

    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.

    • usernameJenkins user id (login name) the API token belongs to
    • api_tokenAPI token: in Jenkins click your name (top right) > Security (or Configure) > API Token > Add new token
    • hostWhere your Jenkins lives: your host
    account { op: "connections.requirements", service: "jenkins" }
    # 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: "jenkins.users.list" }# list users · read · 1 upstream callcheck { action: "jenkins.jobs.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Jenkins 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
usernameapi_token
Setup fields
host
Limits we pace to
10 calls a second, per connection
API covered
Jenkins Remote Access API (2.4xx LTS) with Pipeline: Stage View, Pipeline: Input Step and Pipeline: Declarative, at your Jenkins instance's API base URL, which you enter when connecting
Built from
Jenkins's documentation, read 23 October 2026jenkins.ioGitHubGitHub
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
30 of 35 reads, for up to 1 minute; a write clears what it affects
Shared entities
2, so ask can line Jenkins up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Jenkins.

59 actions in 22 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 35readlook, never change
  • 15writecreate and update
  • 9destructivewait for a confirmation
  1. Builds

    16

    9 read · 4 write · 3 destructive

    List a job's builds · List a Pipeline build's artifacts · Get a build · Trigger a build

  2. Jobs

    6

    2 read · 3 write · 1 destructive

    List top-level jobs and folders · Create a job from config.xml · Get a job · Delete a job

  3. Views

    6

    2 read · 4 write · 0 destructive

    Create a view from config.xml · List views · Get a view · Replace a view's config.xml

  4. Nodes

    5

    2 read · 2 write · 1 destructive

    List agents (nodes) · Create an agent from config.xml · Get an agent (node) · Replace an agent's config.xml

  5. Users

    4

    2 read · 1 write · 1 destructive

    List users · Get a user · Generate an API token for a user · Revoke a user's API token

  6. Queue

    3

    2 read · 0 write · 1 destructive

    List the build queue · Get a queue item · Cancel a queued build

  7. Credentials

    2

    2 read · 0 write · 0 destructive

    List credentials in a store domain · List the domains of a credentials store

  8. Folders

    2

    1 read · 1 write · 0 destructive

    Create a job inside a folder from config.xml · List the jobs in a folder

14 more areas · 15 actions
  • Pipeline converter 2
  • Crumb 1
  • Fingerprints 1
  • Instance 1
  • Labels 1
  • Me 1
  • Overall load 1
  • Pipeline linter 1
  • Pipeline runs 1
  • Plugins 1
  • Safe shutdown 1
  • Script 1
  • Update center 1
  • Whoami 1

Top actions

The Jenkins API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 20 of Jenkins's 20 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
jenkins.users.listList usersList users.readidentity.user.list474 connectors
jenkins.me.getGet the signed-in userGet the signed-in user.readidentity.current_user.get307 connectors
jenkins.users.getGet a userGet a user.readidentity.user.get399 connectors
jenkins.builds.listList a job's buildsList a job's builds.readdevops.pipeline_run.list13 connectors
jenkins.jobs.listList top-level jobs and foldersList top-level jobs and folders.readdevops.pipeline.list9 connectors
jenkins.nodes.listList agents (nodes)List agents (nodes).readdevops.runner.list9 connectors
jenkins.builds.artifacts.listList a Pipeline build's artifactsList a Pipeline build's artifacts.readdevops.artifact.list17 connectors
jenkins.jobs.createCreate a job from config.xmlCreate a job from config.xml.writedevops.pipeline.create7 connectors
jenkins.nodes.createCreate an agent from config.xmlCreate an agent from config.xml.writedevops.runner.create7 connectors
jenkins.builds.getGet a buildGet a build.readdevops.pipeline_run.get12 connectors
jenkins.jobs.deleteDelete a jobDelete a job.destructivedevops.pipeline.delete7 connectors
jenkins.builds.createTrigger a buildTrigger a build.writedevops.pipeline.run9 connectors

Try it

Prompts to paste into Claude.

Each one names the Jenkins actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Who has access in Jenkins? List every user and their role.

    callsjenkins.users.list

  2. Writewrite

    Create a job from config.xml in Jenkins. Show me exactly what you will send before you save it.

    callsjenkins.jobs.create

Governance for Jenkins

Destructive actions wait for a yes.

9 Jenkins actions are destructive. These are all of them:

  • Delete a jobjenkins.jobs.delete
  • Abort a running Pipeline buildjenkins.builds.cancel
  • Run a Groovy script on the controllerjenkins.script.run
  • Shut Jenkins down once running builds finishjenkins.safe_shutdown.run
  • Run a Groovy script on an agentjenkins.nodes.script.run
  • Revoke a user's API tokenjenkins.users.api_tokens.delete
  • Cancel a queued buildjenkins.queue.items.cancel
  • Hard-kill a Pipeline buildjenkins.builds.force.cancel
  • Reject a pending input stepjenkins.builds.inputs.cancel

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.

dojenkins.jobs.deleteconfirm_policy: human

Delete a job?

intent: the user asked me to delete a job

run suspended · waiting for a named person · key jenkins-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "jenkins-agent",  allowed_actions: ["jenkins.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "jenkins.jobs.delete", approver: "[email protected]" },    { match: "jenkins.builds.cancel", approver: "[email protected]" },    { match: "jenkins.script.run", approver: "[email protected]" }  ]}
Illustrative. Scoped to Jenkins only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Jenkins costs on actionlake.

Every Jenkins action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Jenkins 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 59 Jenkins actions
  • 59actions pageeach page of a long list is one call
  • 30reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Jenkins action.

59 actions by area: the id your agent calls, what it does, and its effect.

Builds16
  • jenkins.builds.artifacts.listList a Pipeline build's artifactsread
  • jenkins.builds.cancelAbort a running Pipeline builddestructive
  • jenkins.builds.changesets.listList a Pipeline build's SCM change setsread
  • jenkins.builds.createTrigger a buildwrite
  • jenkins.builds.flow_nodes.getGet a Pipeline stage or stepread
  • jenkins.builds.flow_nodes.log.getGet the log of a Pipeline stepread
  • jenkins.builds.force.cancelHard-kill a Pipeline builddestructive
  • jenkins.builds.getGet a buildread
  • jenkins.builds.inputs.approveApprove a pending input stepwrite
  • jenkins.builds.inputs.cancelReject a pending input stepdestructive
  • jenkins.builds.inputs.with_parameters.approveApprove a pending input step with parameterswrite
  • jenkins.builds.listList a job's buildsread
  • jenkins.builds.pending_inputs.listList a build's pending input stepsread
  • jenkins.builds.pipeline.getGet a Pipeline build's stagesread
  • jenkins.builds.test_report.getGet a build's test reportread
  • jenkins.builds.with_parameters.createTrigger a build with parameterswrite
Jobs6
  • jenkins.jobs.config.updateReplace a job's config.xmlwrite
  • jenkins.jobs.createCreate a job from config.xmlwrite
  • jenkins.jobs.deleteDelete a jobdestructive
  • jenkins.jobs.description.updateSet a job's descriptionwrite
  • jenkins.jobs.getGet a jobread
  • jenkins.jobs.listList top-level jobs and foldersread
Views6
  • jenkins.views.config.updateReplace a view's config.xmlwrite
  • jenkins.views.createCreate a view from config.xmlwrite
  • jenkins.views.getGet a viewread
  • jenkins.views.jobs.addAdd a job to a list viewwrite
  • jenkins.views.jobs.removeRemove a job from a list viewwrite
  • jenkins.views.listList viewsread
Nodes5
  • jenkins.nodes.config.updateReplace an agent's config.xmlwrite
  • jenkins.nodes.createCreate an agent from config.xmlwrite
  • jenkins.nodes.getGet an agent (node)read
  • jenkins.nodes.listList agents (nodes)read
  • jenkins.nodes.script.runRun a Groovy script on an agentdestructive
Users4
  • jenkins.users.api_tokens.createGenerate an API token for a userwrite
  • jenkins.users.api_tokens.deleteRevoke a user's API tokendestructive
  • jenkins.users.getGet a userread
  • jenkins.users.listList usersread
Queue3
  • jenkins.queue.items.cancelCancel a queued builddestructive
  • jenkins.queue.items.getGet a queue itemread
  • jenkins.queue.listList the build queueread
Credentials2
  • jenkins.credentials.domains.listList the domains of a credentials storeread
  • jenkins.credentials.listList credentials in a store domainread
Folders2
  • jenkins.folders.jobs.createCreate a job inside a folder from config.xmlwrite
  • jenkins.folders.jobs.listList the jobs in a folderread
Pipeline converter2
  • jenkins.pipeline_converter.to_jenkinsfile.queryConvert Pipeline JSON to a Jenkinsfileread
  • jenkins.pipeline_converter.to_json.queryConvert a Jenkinsfile to Pipeline JSONread
Crumb1
  • jenkins.crumb.getGet a CSRF crumbread
Fingerprints1
  • jenkins.fingerprints.getGet an artifact fingerprintread
Instance1
  • jenkins.instance.getGet the Jenkins instance (mode, executors, top-level jobs and views)read
Labels1
  • jenkins.labels.getGet an agent labelread
Me1
  • jenkins.me.getGet the signed-in userread
Overall load1
  • jenkins.overall_load.getGet overall load statisticsread
Pipeline linter1
  • jenkins.pipeline_linter.validateValidate a declarative Jenkinsfileread
Pipeline runs1
  • jenkins.pipeline_runs.listList a Pipeline job's runs with stagesread
Plugins1
  • jenkins.plugins.listList installed pluginsread
Safe shutdown1
  • jenkins.safe_shutdown.runShut Jenkins down once running builds finishdestructive
Script1
  • jenkins.script.runRun a Groovy script on the controllerdestructive
Update center1
  • jenkins.update_center.getGet the update center stateread
Whoami1
  • jenkins.whoami.getGet the caller's authentication detailsread

Questions

The Jenkins MCP server, answered.

Is there a Jenkins MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 59 Jenkins actions across builds, jobs, views and nodes, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Jenkins.

What do I need to connect Jenkins?

Jenkins user id (login name) the API token belongs to and API token: in Jenkins click your name (top right) > Security (or Configure) > API Token > Add new token. Plus your host. The free call account { op: "connections.requirements", service: "jenkins" } lists exactly what to paste.

Can an AI agent delete or change things in Jenkins?

Only if its key allows it, and only with an explicit confirmation. 9 Jenkins actions are destructive, including delete a job, abort a running Pipeline build and run a Groovy script on the controller. 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 Jenkins API limit?

actionlake paces every call to the limits in the Jenkins service file: 10 calls a second per connection. Repeated reads are answered from cache (30 Jenkins actions can be), which never reaches Jenkins.

What does a Jenkins action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (59 Jenkins actions page). Cache hits, searches, dry runs and calls Jenkins 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 Jenkins API does it cover?

The Jenkins Remote Access API (2.4xx LTS) with Pipeline: Stage View, Pipeline: Input Step and Pipeline: Declarative at your Jenkins instance's API base URL, which you enter when connecting. It is built from Jenkins's documentation as read on 23 October 2026. 59 actions in 22 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Jenkins data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 1 minute, 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 Jenkins 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 Jenkins today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.