Skip to content

Connectors · Developer & infrastructure

CircleCI MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to CircleCI and the rest of your systems. It gives your agent 114 CircleCI actions (64 reads, 29 writes and 21 that wait for a confirmation) and holds the CircleCI credential itself, so the agent never does. It paces CircleCI'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: "circleci.pipelines.list",  intent: "check which CircleCI account is connected"}# Get a list of pipelines · read · 1 upstream call
  • 114actionsin one signed file
  • 64readlook, never change
  • 29writecreate and update
  • 21wait for a yesdestructive, confirmed first

Set up

Connect CircleCI 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 CircleCI.

    API key. 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.

    • api_tokenCircleCI personal API token
    account { op: "connections.requirements", service: "circleci" }
    # 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: "circleci.pipelines.list" }# get a list of pipelines · read · 1 upstream callcheck { action: "circleci.groups.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

CircleCI at a glance

Sign-in
API key. 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
api_token
Limits we pace to
10 calls a second, per connection
API covered
CircleCI API v2 (OpenAPI 3.0.3, info.version v2)circleci.com/api/v2
Built from
CircleCI's documentation, read 22 October 2026circleci.comcircleci.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
62 of 64 reads, for up to 5 minutes; a write clears what it affects
Shared entities
4, so ask can line CircleCI up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in CircleCI.

114 actions in 36 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 64readlook, never change
  • 29writecreate and update
  • 21destructivewait for a confirmation
  1. Insights

    10

    10 read · 0 write · 0 destructive

    Job timeseries data · Get summary metrics for a project workflow's jobs. · Get recent runs of a workflow · Get summary metrics for a project's workflows

  2. Pipeline definitions

    5

    2 read · 2 write · 1 destructive

    Create pipeline definition · List pipeline definitions · Get pipeline definition · Update pipeline definition

  3. Pipelines

    5

    4 read · 1 write · 0 destructive

    Get a list of pipelines · Get a pipeline by ID · Continue a pipeline · Get a pipeline's configuration

  4. Project pipelines

    5

    3 read · 0 write · 2 destructive

    Get all pipelines · [Recommended] Trigger a new pipeline · Trigger a new pipeline · Get your pipelines

  5. Schedules

    5

    2 read · 2 write · 1 destructive

    List schedule triggers · Create a schedule · Update a schedule · Get a schedule by ID. Available only on schedules associated with GitHub OAuth or Bitbucket Cloud pipeline definitions.

  6. Triggers

    5

    2 read · 2 write · 1 destructive

    List pipeline definition triggers · Create trigger · Get trigger · Update trigger

  7. Webhooks

    5

    2 read · 2 write · 1 destructive

    Create an outbound webhook · List webhooks · Update an outbound webhook · Get a webhook

  8. Checkout keys

    4

    2 read · 1 write · 1 destructive

    Create a new checkout key · Get all checkout keys · Get a checkout key · Delete a checkout key

28 more areas · 70 actions
  • Contexts 4
  • Groups 4
  • Policy decisions 4
  • Project env vars 4
  • Projects 4
  • Workflows 4
  • Context env vars 3
  • Context restrictions 3
  • Oidc org claims 3
  • Oidc project claims 3
  • Organizations 3
  • Otel exporters 3
  • Policy bundles 3
  • URL orb allow list 3
  • Deploy components 2
  • Deploy environments 2
  • Jobs 2
  • Me 2
  • Policy decision settings 2
  • Project jobs 2
  • Project settings 2
  • Usage exports 2
  • Deploy component versions 1
  • Job artifacts 1
  • Job tests 1
  • Pipeline workflows 1
  • Users 1
  • Workflow jobs 1

Top actions

The CircleCI API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 39 of CircleCI's 39 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
circleci.job_artifacts.listGet a job's artifactsGet a job's artifacts.readdevops.artifact.list17 connectors
circleci.groups.listGroups in an organizationGroups in an organization.readidentity.group.list262 connectors
circleci.me.getUser InformationUser Information.readidentity.current_user.get307 connectors
circleci.groups.createCreate GroupsCreate Groups.writeidentity.group.create205 connectors
circleci.schedules.listList schedule triggersList schedule triggers.readautomation.schedule.list18 connectors
circleci.groups.deleteDelete a groupDelete a group.destructiveidentity.group.delete181 connectors
circleci.deploy_environments.listList EnvironmentsList Environments.readdevops.environment.list24 connectors
circleci.pipelines.listGet a list of pipelinesGet a list of pipelines.readdevops.pipeline_run.list13 connectors
circleci.project_pipelines.listGet all pipelinesGet all pipelines.readdevops.pipeline_run.list13 connectors
circleci.workflow_jobs.listGet a workflow's jobsGet a workflow's jobs.readdevops.pipeline_job.list9 connectors
circleci.webhooks.createCreate an outbound webhookCreate an outbound webhook.writeautomation.webhook.create209 connectors
circleci.schedules.createCreate a scheduleCreate a schedule.writeautomation.schedule.create16 connectors

Try it

Prompts to paste into Claude.

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

  1. Readread

    List the CircleCI groups and how many members each one has.

    callscircleci.groups.list

  2. Writewrite

    Create Groups in CircleCI. Show me exactly what you will send before you save it.

    callscircleci.groups.create

Governance for CircleCI

Destructive actions wait for a yes.

21 CircleCI actions are destructive. These are all of them:

  • Delete a groupcircleci.groups.delete
  • Delete an outbound webhookcircleci.webhooks.delete
  • [Recommended] Trigger a new pipelinecircleci.project_pipelines.run
  • Trigger a new pipelinecircleci.project_pipelines.trigger
  • Cancel a workflowcircleci.workflows.cancel
  • Delete a schedulecircleci.schedules.delete
  • Cancel job by job IDcircleci.jobs.cancel
  • Cancel job by job numbercircleci.project_jobs.cancel
  • Delete triggercircleci.triggers.delete
  • Delete an environment variablecircleci.project_env_vars.delete
  • Delete a contextcircleci.contexts.delete
  • Delete a projectcircleci.projects.delete
  • Delete a checkout keycircleci.checkout_keys.delete
  • Delete an organizationcircleci.organizations.delete
  • 🧪 Delete an OTLP exportercircleci.otel_exporters.delete
  • Delete org-level claimscircleci.oidc_org_claims.delete
  • Remove an environment variablecircleci.context_env_vars.delete
  • Remove an entry from the org's URL orb allow-listcircleci.url_orb_allow_list.delete
  • Delete project-level claimscircleci.oidc_project_claims.delete
  • Delete context restrictioncircleci.context_restrictions.delete
  • Delete pipeline definitioncircleci.pipeline_definitions.delete

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.

docircleci.groups.deleteconfirm_policy: human

Delete a group?

intent: the user asked me to delete a group

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

Cost

What CircleCI costs on actionlake.

Every CircleCI action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call CircleCI 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 114 CircleCI actions
  • 114actions pageeach page of a long list is one call
  • 62reads 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 CircleCI action.

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

Insights10
  • circleci.insights.branches_getGet all branches for a projectread
  • circleci.insights.flaky_tests_getGet flaky tests for a projectread
  • circleci.insights.job_timeseries_listJob timeseries dataread
  • circleci.insights.org_summary_getGet summary metrics with trends for the entire org, and for each project.read
  • circleci.insights.project_summary_getGet summary metrics and trends for a project across it's workflows and branchesread
  • circleci.insights.workflow_jobs_listGet summary metrics for a project workflow's jobs.read
  • circleci.insights.workflow_runs_listGet recent runs of a workflowread
  • circleci.insights.workflow_summary_getGet metrics and trends for workflowsread
  • circleci.insights.workflow_test_metrics_getGet test metrics for a project's workflowsread
  • circleci.insights.workflows_listGet summary metrics for a project's workflowsread
Pipeline definitions5
  • circleci.pipeline_definitions.createCreate pipeline definitionwrite
  • circleci.pipeline_definitions.deleteDelete pipeline definitiondestructive
  • circleci.pipeline_definitions.getGet pipeline definitionread
  • circleci.pipeline_definitions.listList pipeline definitionsread
  • circleci.pipeline_definitions.updateUpdate pipeline definitionwrite
Pipelines5
  • circleci.pipelines.config_getGet a pipeline's configurationread
  • circleci.pipelines.continueContinue a pipelinewrite
  • circleci.pipelines.getGet a pipeline by IDread
  • circleci.pipelines.listGet a list of pipelinesread
  • circleci.pipelines.values_getGet pipeline values for a pipelineread
Project pipelines5
  • circleci.project_pipelines.get_by_numberGet a pipeline by pipeline numberread
  • circleci.project_pipelines.listGet all pipelinesread
  • circleci.project_pipelines.list_mineGet your pipelinesread
  • circleci.project_pipelines.run[Recommended] Trigger a new pipelinedestructive
  • circleci.project_pipelines.triggerTrigger a new pipelinedestructive
Schedules5
  • circleci.schedules.createCreate a schedulewrite
  • circleci.schedules.deleteDelete a scheduledestructive
  • circleci.schedules.getGet a schedule by ID. Available only on schedules associated with GitHub OAuth or Bitbucket Cloud pipeline definitions.read
  • circleci.schedules.listList schedule triggersread
  • circleci.schedules.updateUpdate a schedulewrite
Triggers5
  • circleci.triggers.createCreate triggerwrite
  • circleci.triggers.deleteDelete triggerdestructive
  • circleci.triggers.getGet triggerread
  • circleci.triggers.listList pipeline definition triggersread
  • circleci.triggers.updateUpdate triggerwrite
Webhooks5
  • circleci.webhooks.createCreate an outbound webhookwrite
  • circleci.webhooks.deleteDelete an outbound webhookdestructive
  • circleci.webhooks.getGet a webhookread
  • circleci.webhooks.listList webhooksread
  • circleci.webhooks.updateUpdate an outbound webhookwrite
Checkout keys4
  • circleci.checkout_keys.createCreate a new checkout keywrite
  • circleci.checkout_keys.deleteDelete a checkout keydestructive
  • circleci.checkout_keys.getGet a checkout keyread
  • circleci.checkout_keys.listGet all checkout keysread
Contexts4
  • circleci.contexts.createCreate a new contextwrite
  • circleci.contexts.deleteDelete a contextdestructive
  • circleci.contexts.getGet a contextread
  • circleci.contexts.listList contextsread
Groups4
  • circleci.groups.createCreate Groupswrite
  • circleci.groups.deleteDelete a groupdestructive
  • circleci.groups.getA group in an organizationread
  • circleci.groups.listGroups in an organizationread
Policy decisions4
  • circleci.policy_decisions.createMakes a decisionwrite
  • circleci.policy_decisions.getRetrieves the owner's decision audit log by given decisionIDread
  • circleci.policy_decisions.listRetrieves the owner's decision audit logs.read
  • circleci.policy_decisions.policy_bundle_getRetrieves Policy Bundle for a given decision log IDread
Project env vars4
  • circleci.project_env_vars.createCreate an environment variablewrite
  • circleci.project_env_vars.deleteDelete an environment variabledestructive
  • circleci.project_env_vars.getGet a masked environment variableread
  • circleci.project_env_vars.listList all environment variablesread
Projects4
  • circleci.projects.createCreate a new projectwrite
  • circleci.projects.deleteDelete a projectdestructive
  • circleci.projects.getGet a projectread
  • circleci.projects.rollbackRollback a projectwrite
Workflows4
  • circleci.workflows.approveApprove a jobwrite
  • circleci.workflows.cancelCancel a workflowdestructive
  • circleci.workflows.getGet a workflowread
  • circleci.workflows.rerunRerun a workflowwrite
Context env vars3
  • circleci.context_env_vars.deleteRemove an environment variabledestructive
  • circleci.context_env_vars.listList environment variablesread
  • circleci.context_env_vars.upsertAdd or update an environment variablewrite
Context restrictions3
  • circleci.context_restrictions.createCreate context restrictionwrite
  • circleci.context_restrictions.deleteDelete context restrictiondestructive
  • circleci.context_restrictions.listGet context restrictionsread
Oidc org claims3
  • circleci.oidc_org_claims.deleteDelete org-level claimsdestructive
  • circleci.oidc_org_claims.getGet org-level claimsread
  • circleci.oidc_org_claims.updatePatch org-level claimswrite
Oidc project claims3
  • circleci.oidc_project_claims.deleteDelete project-level claimsdestructive
  • circleci.oidc_project_claims.getGet project-level claimsread
  • circleci.oidc_project_claims.updatePatch project-level claimswrite
Organizations3
  • circleci.organizations.createCreate a new organizationwrite
  • circleci.organizations.deleteDelete an organizationdestructive
  • circleci.organizations.getGet an organizationread
Otel exporters3
  • circleci.otel_exporters.create🧪 Create an OTLP exporterwrite
  • circleci.otel_exporters.delete🧪 Delete an OTLP exporterdestructive
  • circleci.otel_exporters.list🧪 List OTLP exportersread
Policy bundles3
  • circleci.policy_bundles.getRetrieves Policy Bundleread
  • circleci.policy_bundles.policy_getRetrieves a policy documentread
  • circleci.policy_bundles.upsertCreates policy bundle for the contextwrite
URL orb allow list3
  • circleci.url_orb_allow_list.createCreate a new URL Orb allow-list entrywrite
  • circleci.url_orb_allow_list.deleteRemove an entry from the org's URL orb allow-listdestructive
  • circleci.url_orb_allow_list.listList the entries in the org's URL Orb allow-listread
Deploy components2
  • circleci.deploy_components.getGet Componentread
  • circleci.deploy_components.listList Componentsread
Deploy environments2
  • circleci.deploy_environments.getGet Environmentread
  • circleci.deploy_environments.listList Environmentsread
Jobs2
  • circleci.jobs.cancelCancel job by job IDdestructive
  • circleci.jobs.getGet a jobread
Me2
  • circleci.me.collaborations_listCollaborationsread
  • circleci.me.getUser Informationread
Policy decision settings2
  • circleci.policy_decision_settings.getGet the decision settingsread
  • circleci.policy_decision_settings.updateSet the decision settingswrite
Project jobs2
  • circleci.project_jobs.cancelCancel job by job numberdestructive
  • circleci.project_jobs.getGet job detailsread
Project settings2
  • circleci.project_settings.getGet project settingsread
  • circleci.project_settings.updateUpdate project settingswrite
Usage exports2
  • circleci.usage_exports.createCreate a usage exportwrite
  • circleci.usage_exports.getGet a usage exportread
Deploy component versions1
  • circleci.deploy_component_versions.listList Component Versionsread
Job artifacts1
  • circleci.job_artifacts.listGet a job's artifactsread
Job tests1
  • circleci.job_tests.listGet a job's test metadataread
Pipeline workflows1
  • circleci.pipeline_workflows.listGet a pipeline's workflowsread
Users1
  • circleci.users.getUser Informationread
Workflow jobs1
  • circleci.workflow_jobs.listGet a workflow's jobsread

Questions

The CircleCI MCP server, answered.

Is there a CircleCI MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 114 CircleCI actions across insights, pipeline definitions, pipelines and project pipelines, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by CircleCI.

What do I need to connect CircleCI?

CircleCI personal API token. The free call account { op: "connections.requirements", service: "circleci" } lists exactly what to paste.

Can an AI agent delete or change things in CircleCI?

Only if its key allows it, and only with an explicit confirmation. 21 CircleCI actions are destructive, including delete a group, delete an outbound webhook and [Recommended] Trigger a new pipeline. 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 CircleCI API limit?

actionlake paces every call to the limits in the CircleCI service file: 10 calls a second per connection. Repeated reads are answered from cache (62 CircleCI actions can be), which never reaches CircleCI.

What does a CircleCI action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (114 CircleCI actions page). Cache hits, searches, dry runs and calls CircleCI 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 CircleCI API does it cover?

The CircleCI API v2 (OpenAPI 3.0.3, info.version v2) at circleci.com/api/v2. It is built from CircleCI's documentation as read on 22 October 2026. 114 actions in 36 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my CircleCI 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 CircleCI 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 CircleCI today.

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