--- title: "Statsig MCP server for AI agents - actionlake" description: "Give Claude 354 Statsig actions through one MCP server: experiments, gates, autotunes. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/statsig updated: 2026-10-23 --- Connectors · Developer & infrastructure # Statsig MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Statsig and the rest of your systems. It gives your agent 354 Statsig actions (140 reads, 159 writes and 55 that wait for a confirmation) and holds the Statsig credential itself, so the agent never does. It paces Statsig's limits and records every call. [Connect Statsig 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: "statsig.dashboards.list", intent: "check which Statsig account is connected" } # List Dashboards · read · 1 upstream call ``` - 354 actions in one signed file - 140 read look, never change - 159 write create and update - 55 wait for a yes destructive, confirmed first Set up ## Connect Statsig 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 Statsig. 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_key` Statsig Console API key ``` account { op: "connections.requirements", service: "statsig" } # 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: "statsig.dashboards.list" } # list dashboards · read · 1 upstream call check { action: "statsig.dashboards.create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Statsig 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_key` **Limits we pace to** 1,800 calls per 15 minutes, per connection **API covered** Statsig Console API 20240601.0.0 (OpenAPI 3.0.0)`statsigapi.net` **Built from** Statsig's documentation, read 23 October 2026[api.statsig.com](https://api.statsig.com/openapi/20240601.json) [docs.statsig.com](https://docs.statsig.com/console-api/introduction) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 140 of 140 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 1, so ask can line Statsig up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Statsig. 354 actions in 37 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **140** read look, never change - **159** write create and update - **55** destructive wait for a confirmation 1. ### Experiments 63 22 read · 30 write · 11 destructive Create Experiment · List Experiments · Get Experiment · Partially Update Experiment 2. ### Gates 39 14 read · 20 write · 5 destructive List Gates · Create Gate · Read Gate · Partially Update Gates 3. ### Autotunes 24 5 read · 13 write · 6 destructive Create Autotune · List Autotune · Read Autotune · Start Autotune Experiment 4. ### Dynamic configs 24 8 read · 13 write · 3 destructive Create Dynamic Config · List Dynamic Configs · Archive Dynamic Config · Disable Dynamic Config 5. ### Metrics 20 10 read · 8 write · 2 destructive List all Metrics · Create Metric · Update a metric · Read Metric Definition 6. ### Prompts 16 7 read · 7 write · 2 destructive Create Prompt · List Prompts · Get Prompt · Delete Prompt 7. ### Segments 15 4 read · 7 write · 4 destructive List Segments · Create Segment · Get Segment · Delete Segment 8. ### Ingestion 13 7 read · 5 write · 1 destructive Backfill Ingestion · Create Ingestion Source · Read Ingestion · Delete Ingestion Source **29 more areas · 140 actions** - Layers **13** - Holdouts **11** - Evals **10** - Users **10** - Alerts **9** - Release pipeline triggers **8** - Settings **8** - Keys **7** - Dashboards **6** - Eval datasets **6** - Target app **6** - Eval graders **5** - Param stores **5** - Release pipelines **5** - Roles **5** - Tags **5** - Unit id types **5** - Events **3** - Change validation **2** - Environments **2** - Audit logs **1** - Company **1** - Exports **1** - Exposure count **1** - Logs **1** - Overrides **1** - Project **1** - Reports **1** - WH connections **1** Top actions ## The Statsig API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 48 of Statsig's 48 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `statsig.dashboards.list` List Dashboards | List Dashboards. | read | `analytics.dashboard.list` 22 connectors | | `statsig.dashboards.create` Create Dashboard | Create Dashboard. | write | `analytics.dashboard.create` 18 connectors | | `statsig.segments.list` List Segments | List Segments. | read | `analytics.segment.list` 17 connectors | | `statsig.experiments.list` List Experiments | List Experiments. | read | `analytics.experiment.list` 12 connectors | | `statsig.experiments.create` Create Experiment | Create Experiment. | write | `analytics.experiment.create` 12 connectors | | `statsig.roles.list` List Roles | List Roles. | read | `identity.role.list` 184 connectors | | `statsig.metrics.list` List all Metrics | List all Metrics. | read | `analytics.metric_definition.list` 11 connectors | | `statsig.metrics.create` Create Metric | Create Metric. | write | `analytics.metric_definition.create` 10 connectors | | `statsig.segments.create` Create Segment | Create Segment. | write | `analytics.segment.create` 10 connectors | | `statsig.roles.create` Create Role | Create Role. | write | `identity.role.create` 105 connectors | | `statsig.keys.create` Create Key | Create Key. | write | `identity.api_key.create` 100 connectors | | `statsig.segments.delete` Delete Segment | Delete Segment. | destructive | `analytics.segment.delete` 10 connectors | Try it ## Prompts to paste into Claude. Each one names the Statsig actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Who has access in Statsig? List every user and their role. calls `statsig.users.list` 2. Write write Create Dashboard in Statsig. Show me exactly what you will send before you save it. calls `statsig.dashboards.create` Governance for Statsig ## Destructive actions wait for a yes. 55 Statsig actions are destructive. The first 10: - Delete Segment `statsig.segments.delete` - Delete Experiment `statsig.experiments.delete` - Delete a metric `statsig.metrics.delete` - Delete Role `statsig.roles.delete` - Delete Key `statsig.keys.delete` - Delete Tag `statsig.tags.delete` - Delete Gates `statsig.gates.delete` - Delete Topline Alert `statsig.alerts.delete` - Delete Eval `statsig.evals.delete` - Delete a layer `statsig.layers.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. do statsig.segments.delete confirm_policy: **human** Delete Segment? **intent:** the user asked me to delete Segment run suspended · waiting for a named person · key _statsig-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "statsig-agent", allowed_actions: ["statsig.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "statsig.segments.delete", approver: "lead@example.com" }, { match: "statsig.experiments.delete", approver: "lead@example.com" }, { match: "statsig.metrics.delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Statsig only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Statsig costs on actionlake. Every Statsig action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Statsig 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 354 Statsig actions - 354 actions page each page of a long list is one call - 140 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 Statsig action. 354 actions by area: the id your agent calls, what it does, and its effect. **Experiments 63** - `statsig.experiments.abandon` Abandon Experiment destructive - `statsig.experiments.alerts_get` Get Experiment Guardrail Alert Statuses read - `statsig.experiments.alerts_resolve` Resolve Metric Rollout Alert write - `statsig.experiments.archive` Archive Experiment write - `statsig.experiments.assignment_source_delete` Delete Assignment Source destructive - `statsig.experiments.assignment_source_patch` Patch Assignment Source write - `statsig.experiments.assignment_source_update` Post Assignment Source write - `statsig.experiments.assignment_sources_create` Create Assignment Source write - `statsig.experiments.assignment_sources_list` List Assignment Sources read - `statsig.experiments.code_cleanup` Start Experiment Code Cleanup write - `statsig.experiments.context_get` Get Experiment Context read - `statsig.experiments.create` Create Experiment write - `statsig.experiments.cumulative_exposures_list` Retrieve cumulative exposures read - `statsig.experiments.defer_decision` Conclude Experiment & Defer Decision write - `statsig.experiments.delete` Delete Experiment destructive - `statsig.experiments.diagnostics_checks_get` Retrieve Experiment Checks Diagnostics read - `statsig.experiments.dimensional_exposures_get` Retrieve Exposures By Dimension read - `statsig.experiments.disable_groups` Disable Experiment Groups write - `statsig.experiments.eligible_reviewers_get` Get Eligible Reviewers read - `statsig.experiments.enable_groups` Enable Experiment Groups write - `statsig.experiments.entity_properties_create` Create Entity Property Source write - `statsig.experiments.entity_properties_list` List Entity Property Sources read - `statsig.experiments.entity_property_delete` Delete Entity Property Source destructive - `statsig.experiments.entity_property_get` Get Entity Property Source read - `statsig.experiments.entity_property_patch` Patch Entity Property Source write - `statsig.experiments.entity_property_update` Post Entity Property Source write - `statsig.experiments.get` Get Experiment read - `statsig.experiments.list` List Experiments read - `statsig.experiments.load_pulse` Load Pulse (Warehouse Native) write - `statsig.experiments.make_decision` Finish Experiment Early write - `statsig.experiments.overrides_conditional_delete` Delete a Single Experiment Override destructive - `statsig.experiments.overrides_create` Update Experiment Overrides write - `statsig.experiments.overrides_delete` Delete Experiment Overrides destructive - `statsig.experiments.overrides_get` Get Experiment Overrides read - `statsig.experiments.overrides_patch` Partially Update Experiment Overrides write - `statsig.experiments.overrides_user_id_delete` Delete a Single Experiment User ID Override destructive - `statsig.experiments.patch` Partially Update Experiment write - `statsig.experiments.pulse_load_history_cancel` Cancel Pulse Load (Warehouse Native) destructive - `statsig.experiments.pulse_load_history_get` Get Pulse Load History Details (Warehouse Native) read - `statsig.experiments.pulse_load_history_list` Pulse Load History (Warehouse Native) read - `statsig.experiments.pulse_metric_result_get` Retrieve Pulse Metric Result read - `statsig.experiments.pulse_results_get` Retrieve Pulse Results (Beta) read - `statsig.experiments.qualifying_events_create` Create Qualifying Event write - `statsig.experiments.qualifying_events_delete` Delete Qualifying Event destructive - `statsig.experiments.qualifying_events_get` Read Qualifying Event read - `statsig.experiments.qualifying_events_list` List qualifying event read - `statsig.experiments.qualifying_events_update` Update Qualifying Event write - `statsig.experiments.reset` Reset Experiment destructive - `statsig.experiments.restart_as_new` Restart As New Experiment write - `statsig.experiments.reviews_approve` Approve Experiment Review write - `statsig.experiments.reviews_commit` Commit Experiment Review write - `statsig.experiments.reviews_create` Create Experiment Review write - `statsig.experiments.reviews_delete` Cancel Experiment Review destructive - `statsig.experiments.reviews_get` Get Experiment Review read - `statsig.experiments.reviews_list` List Experiment Reviews read - `statsig.experiments.reviews_reject` Reject Experiment Review write - `statsig.experiments.reviews_update` Edit Experiment Review write - `statsig.experiments.schedule_start` Schedule Experiment Start write - `statsig.experiments.start` Start Experiment write - `statsig.experiments.summary_charts_get` Retrieve Experiment Summary Charts (Beta) read - `statsig.experiments.unarchive` Unarchive Experiment write - `statsig.experiments.update` Fully Update Experiment write - `statsig.experiments.versions_list` List Experiment Versions read **Gates 39** - `statsig.gates.alerts_resolve` Resolve Metric Rollout Alert write - `statsig.gates.archive` Archive Gate write - `statsig.gates.checks_get` Read Gate Checks read - `statsig.gates.code_cleanup` Start Gate Code Cleanup write - `statsig.gates.create` Create Gate write - `statsig.gates.delete` Delete Gates destructive - `statsig.gates.disable` Disable Gate write - `statsig.gates.dynamic_config_references_list` List Dynamic Config References read - `statsig.gates.eligible_reviewers_get` Get Eligible Reviewers read - `statsig.gates.enable` Enable Gate write - `statsig.gates.experiment_references_list` List Experiment References read - `statsig.gates.gate_references_list` List Gate References read - `statsig.gates.get` Read Gate read - `statsig.gates.launch` Launch Gate write - `statsig.gates.list` List Gates read - `statsig.gates.load_pulse` Load Pulse Gate write - `statsig.gates.overrides_create` Update Gate Overrides write - `statsig.gates.overrides_delete` Delete Gate Overrides destructive - `statsig.gates.overrides_get` Get Gate Override read - `statsig.gates.overrides_patch` Add Gate Overrides write - `statsig.gates.overrides_user_id_delete` Delete a Single Gate User ID Override destructive - `statsig.gates.patch` Partially Update Gates write - `statsig.gates.reviews_approve` Approve Gate Review write - `statsig.gates.reviews_commit` Commit Gate Review write - `statsig.gates.reviews_create` Create Gate Review write - `statsig.gates.reviews_delete` Cancel Gate Review destructive - `statsig.gates.reviews_get` Get Gate Review read - `statsig.gates.reviews_list` List Gate Reviews read - `statsig.gates.reviews_reject` Reject Gate Review write - `statsig.gates.reviews_update` Edit Gate Review write - `statsig.gates.rule_create` Add Gate Rule write - `statsig.gates.rules_delete` Delete Gate Rule destructive - `statsig.gates.rules_list` Read Gate Rules read - `statsig.gates.rules_patch` Update Gate Rules write - `statsig.gates.rules_pulse_load_history_list` Pulse Load History (Warehouse Native) read - `statsig.gates.rules_pulse_results_get` Retrieve Pulse Results read - `statsig.gates.unarchive` Unarchive Gate write - `statsig.gates.update` Fully Update Gates write - `statsig.gates.versions_list` List Gate Versions read **Autotunes 24** - `statsig.autotunes.create` Create Autotune write - `statsig.autotunes.delete` Delete Autotune destructive - `statsig.autotunes.get` Read Autotune read - `statsig.autotunes.list` List Autotune read - `statsig.autotunes.make_decision` Finish Experiment Early write - `statsig.autotunes.overrides_conditional_delete` Delete a Single Autotune Override destructive - `statsig.autotunes.overrides_create` Update Autotune Overrides write - `statsig.autotunes.overrides_delete` Delete Autotune Overrides destructive - `statsig.autotunes.overrides_get` Get Autotune Overrides read - `statsig.autotunes.overrides_patch` Partially Update Autotune Overrides write - `statsig.autotunes.overrides_user_id_delete` Delete a Single Autotune User ID Override destructive - `statsig.autotunes.patch` Partially Update Autotune write - `statsig.autotunes.reset` Reset Experiment destructive - `statsig.autotunes.reviews_approve` Approve Autotune Review write - `statsig.autotunes.reviews_commit` Commit Autotune Review write - `statsig.autotunes.reviews_create` Create Autotune Review write - `statsig.autotunes.reviews_delete` Cancel Autotune Review destructive - `statsig.autotunes.reviews_get` Get Autotune Review read - `statsig.autotunes.reviews_list` List Autotune Reviews read - `statsig.autotunes.reviews_reject` Reject Autotune Review write - `statsig.autotunes.reviews_update` Edit Autotune Review write - `statsig.autotunes.schedule_start` Schedule Autotune Start write - `statsig.autotunes.start` Start Autotune Experiment write - `statsig.autotunes.update` Fully Update Autotune write **Dynamic configs 24** - `statsig.dynamic_configs.archive` Archive Dynamic Config write - `statsig.dynamic_configs.create` Create Dynamic Config write - `statsig.dynamic_configs.delete` Delete Dynamic Config destructive - `statsig.dynamic_configs.disable` Disable Dynamic Config write - `statsig.dynamic_configs.eligible_reviewers_get` Get Eligible Reviewers read - `statsig.dynamic_configs.enable` Enable Dynamic Config write - `statsig.dynamic_configs.get` Get Dynamic Config read - `statsig.dynamic_configs.list` List Dynamic Configs read - `statsig.dynamic_configs.patch` Partially Update Dynamic Config write - `statsig.dynamic_configs.reviews_approve` Approve Dynamic Config Review write - `statsig.dynamic_configs.reviews_commit` Commit Dynamic Config Review write - `statsig.dynamic_configs.reviews_create` Create Dynamic Config Review write - `statsig.dynamic_configs.reviews_delete` Cancel Dynamic Config Review destructive - `statsig.dynamic_configs.reviews_get` Get Dynamic Config Review read - `statsig.dynamic_configs.reviews_list` List Dynamic Config Reviews read - `statsig.dynamic_configs.reviews_reject` Reject Dynamic Config Review write - `statsig.dynamic_configs.reviews_update` Edit Dynamic Config Review write - `statsig.dynamic_configs.rule_delete` Delete Dynamic Config Rule destructive - `statsig.dynamic_configs.rule_get` Get Specific Dynamic Config Rule read - `statsig.dynamic_configs.rule_patch` Update Dynamic Config Rule By Id write - `statsig.dynamic_configs.rules_list` Get Dynamic Config Rules read - `statsig.dynamic_configs.unarchive` Unarchive Dynamic Config write - `statsig.dynamic_configs.update` Fully Update Dynamic Config write - `statsig.dynamic_configs.versions_list` List Dynamic Config Versions read **Metrics 20** - `statsig.metrics.cancel_archive` Cancel archive a metric write - `statsig.metrics.create` Create Metric write - `statsig.metrics.delete` Delete a metric destructive - `statsig.metrics.experiments_list` Lineage: List experiments related to Metric read - `statsig.metrics.get` Read Metric Definition read - `statsig.metrics.get_by_name` Read Metric Definition by Name read - `statsig.metrics.list` List all Metrics read - `statsig.metrics.metric_source_create` Create Metric Source write - `statsig.metrics.metric_source_delete` Delete Metric Source destructive - `statsig.metrics.metric_source_get` Read Metric Source read - `statsig.metrics.metric_source_list` List metric source read - `statsig.metrics.metric_source_metrics_list` Read Metric Source Metrics read - `statsig.metrics.metric_source_update` Update Metric Source write - `statsig.metrics.reload` Reload metric data write - `statsig.metrics.schedule_archive` Schedule a metric archive write - `statsig.metrics.sql_get` Get SQL for a metric read - `statsig.metrics.unarchive` Unarchive a metric write - `statsig.metrics.update` Update a metric write - `statsig.metrics.value_get` Read Single Metric Value read - `statsig.metrics.values_list` List All Metric Values read **Prompts 16** - `statsig.prompts.create` Create Prompt write - `statsig.prompts.delete` Delete Prompt destructive - `statsig.prompts.eval_settings` Update Prompt Eval Settings write - `statsig.prompts.get` Get Prompt read - `statsig.prompts.list` List Prompts read - `statsig.prompts.patch` Update Prompt (partial) write - `statsig.prompts.versions_create` Create Prompt Version write - `statsig.prompts.versions_delete` Delete Prompt Version destructive - `statsig.prompts.versions_eval_runs_get` Get Prompt Version Eval Run read - `statsig.prompts.versions_eval_runs_list` List Prompt Version Eval Runs read - `statsig.prompts.versions_eval_runs_results_list` List Prompt Version Eval Run Results read - `statsig.prompts.versions_get` Get Prompt Version read - `statsig.prompts.versions_list` List Prompt Versions read - `statsig.prompts.versions_patch` Update Prompt Version (partial) write - `statsig.prompts.versions_start_evals` Start Prompt Version Evaluation Job write - `statsig.prompts.versions_stop_evals` Stop Prompt Version Evaluation Job write **Segments 15** - `statsig.segments.add_ids` Add IDs to User Store ID List write - `statsig.segments.archive` Archive Segment write - `statsig.segments.conditional_create` Update Segment Rules write - `statsig.segments.create` Create Segment write - `statsig.segments.delete` Delete Segment destructive - `statsig.segments.get` Get Segment read - `statsig.segments.id_list_delete` Remove IDs from Segment destructive - `statsig.segments.id_list_list` Get IDs in a Segment read - `statsig.segments.id_list_patch` Add IDs to Segment write - `statsig.segments.id_list_reset` Reset ID List Segment destructive - `statsig.segments.idlist_metadata_get` Get ID List Metadata read - `statsig.segments.list` List Segments read - `statsig.segments.remove_ids` Remove IDs from User Store ID List write - `statsig.segments.reviews_commit` Commit Segment Review write - `statsig.segments.reviews_delete` Cancel Segment Review destructive **Ingestion 13** - `statsig.ingestion.backfill` Backfill Ingestion write - `statsig.ingestion.connection_databricks` Create Ingestion Databricks write - `statsig.ingestion.create` Create Ingestion Source write - `statsig.ingestion.delete` Delete Ingestion Source destructive - `statsig.ingestion.events_count_get` Get Ingestion Event Count read - `statsig.ingestion.events_delta_get` Get Ingestion Event Delta Ledger read - `statsig.ingestion.get` Read Ingestion read - `statsig.ingestion.patch` Update Ingestion Source write - `statsig.ingestion.runs_get` Read Ingestion Run read - `statsig.ingestion.runs_list` List Ingestion Runs read - `statsig.ingestion.schedule_get` Read Ingestion Schedule read - `statsig.ingestion.schedule_update` Update Ingestion Schedule write - `statsig.ingestion.status_list` List Ingestions Status read **Layers 13** - `statsig.layers.create` Create a Layer write - `statsig.layers.delete` Delete a layer destructive - `statsig.layers.experiments_list` Lineage: List Experiment related to Layer read - `statsig.layers.get` Get one layer read - `statsig.layers.list` Get Layers read - `statsig.layers.overrides_conditional_delete` Delete a Single Layer Override destructive - `statsig.layers.overrides_create` Update Layer Overrides write - `statsig.layers.overrides_delete` Delete Layer Overrides destructive - `statsig.layers.overrides_get` Get Layer Overrides read - `statsig.layers.overrides_patch` Add Layer Overrides write - `statsig.layers.overrides_user_id_delete` Delete a Single Layer User ID Override destructive - `statsig.layers.patch` Partially update a layer write - `statsig.layers.update` Update a layer write **Holdouts 11** - `statsig.holdouts.create` Create holdout write - `statsig.holdouts.delete` Delete holdout by id destructive - `statsig.holdouts.get` Get holdout by id read - `statsig.holdouts.list` List Holdouts read - `statsig.holdouts.overrides_create` Update Holdout Overrides write - `statsig.holdouts.overrides_delete` Remove Holdout Overrides destructive - `statsig.holdouts.overrides_get` Read Holdout Overrides read - `statsig.holdouts.overrides_patch` Add Holdout Overrides write - `statsig.holdouts.patch` Partially update holdout by id write - `statsig.holdouts.pulse_results_get` Retrieve Pulse Results read - `statsig.holdouts.update` Update holdout by id write **Evals 10** - `statsig.evals.create` Create Eval write - `statsig.evals.delete` Delete Eval destructive - `statsig.evals.get` Get Eval read - `statsig.evals.list` List Evals read - `statsig.evals.runs_get` Get Eval Run read - `statsig.evals.runs_list` List Eval Runs read - `statsig.evals.runs_results_get` Get Eval Run Results read - `statsig.evals.runs_results_rows_list` List Eval Run Result Rows read - `statsig.evals.send_results` Send eval results write - `statsig.evals.update` Create Eval Run write **Users 10** - `statsig.users.get` Get user by email read - `statsig.users.id_get` Get user by ID read - `statsig.users.invite` Invite users write - `statsig.users.list` List Users read - `statsig.users.teams_create` Create Team write - `statsig.users.teams_delete` Delete Team destructive - `statsig.users.teams_get` Get Team read - `statsig.users.teams_list` List Teams read - `statsig.users.teams_patch` Update team write - `statsig.users.update` Update user write **Alerts 9** - `statsig.alerts.create` Create Topline Alert write - `statsig.alerts.delete` Delete Topline Alert destructive - `statsig.alerts.events_get` Read Topline Alert Event read - `statsig.alerts.events_list` List Topline Alert Events read - `statsig.alerts.get` Read Topline Alert read - `statsig.alerts.list` List Topline Alerts read - `statsig.alerts.mute` Mute Topline Alert write - `statsig.alerts.patch` Update Topline Alert write - `statsig.alerts.unmute` Unmute Topline Alert write **Release pipeline triggers 8** - `statsig.release_pipeline_triggers.abort` Abort Pipeline Trigger destructive - `statsig.release_pipeline_triggers.approve` Approve Pipeline Trigger Phase write - `statsig.release_pipeline_triggers.get` Get Pipeline Trigger read - `statsig.release_pipeline_triggers.list` List Pipeline Triggers read - `statsig.release_pipeline_triggers.pause` Pause Pipeline Trigger write - `statsig.release_pipeline_triggers.rollout` Fully Roll Out Pipeline Trigger write - `statsig.release_pipeline_triggers.skip` Skip to Pipeline Trigger Phase write - `statsig.release_pipeline_triggers.unpause` Unpause Pipeline Trigger write **Settings 8** - `statsig.settings.project_get` Get Project Settings read - `statsig.settings.project_update` Update Project Settings write - `statsig.settings.reviews_get` Get Reviews Settings read - `statsig.settings.reviews_update` Update Reviews Settings write - `statsig.settings.roles_get` Get Roles Settings read - `statsig.settings.roles_update` Update Roles Settings write - `statsig.settings.teams_get` Get Teams Settings read - `statsig.settings.teams_update` Update Teams Settings write **Keys 7** - `statsig.keys.create` Create Key write - `statsig.keys.deactivate` Deactivate Key destructive - `statsig.keys.delete` Delete Key destructive - `statsig.keys.get` Read Key read - `statsig.keys.list` List Keys read - `statsig.keys.patch` Update Key write - `statsig.keys.rotate` Rotate Key destructive **Dashboards 6** - `statsig.dashboards.create` Create Dashboard write - `statsig.dashboards.get` Read Dashboard read - `statsig.dashboards.list` List Dashboards read - `statsig.dashboards.widgets_create` Add Widgets to Dashboard write - `statsig.dashboards.widgets_results_get` Read Dashboard Widget Results read - `statsig.dashboards.widgets_update` Replace Widgets on Dashboard write **Eval datasets 6** - `statsig.eval_datasets.create` Create Eval Dataset write - `statsig.eval_datasets.delete` Delete Eval Dataset destructive - `statsig.eval_datasets.get` Get Eval Dataset read - `statsig.eval_datasets.list` List Eval Datasets read - `statsig.eval_datasets.patch` Update Eval Dataset (partial) write - `statsig.eval_datasets.rows_list` List Eval Dataset Rows read **Target app 6** - `statsig.target_app.bulk_assign` Bulk Assign Target Apps write - `statsig.target_app.create` Create Target App write - `statsig.target_app.delete` Delete Target App destructive - `statsig.target_app.get` Read Target App read - `statsig.target_app.list` List Target Apps read - `statsig.target_app.patch` Update Target App write **Eval graders 5** - `statsig.eval_graders.create` Create Eval Grader write - `statsig.eval_graders.delete` Delete Eval Grader destructive - `statsig.eval_graders.get` Get Eval Grader read - `statsig.eval_graders.list` List Eval Graders read - `statsig.eval_graders.patch` Update Eval Grader (partial) write **Param stores 5** - `statsig.param_stores.create` Create Param Store write - `statsig.param_stores.delete` Delete Param Store destructive - `statsig.param_stores.get` Get Param Store read - `statsig.param_stores.list` List Param Stores read - `statsig.param_stores.update` Update Param Store write **Release pipelines 5** - `statsig.release_pipelines.create` Create Pipeline write - `statsig.release_pipelines.delete` Delete Pipeline destructive - `statsig.release_pipelines.get` Get Pipeline read - `statsig.release_pipelines.list` List Pipelines read - `statsig.release_pipelines.update` Update Pipeline write **Roles 5** - `statsig.roles.create` Create Role write - `statsig.roles.delete` Delete Role destructive - `statsig.roles.get` Get Role read - `statsig.roles.list` List Roles read - `statsig.roles.patch` Update Role write **Tags 5** - `statsig.tags.create` Create Tag write - `statsig.tags.delete` Delete Tag destructive - `statsig.tags.get` Read Tag read - `statsig.tags.list` List Tags read - `statsig.tags.patch` Update Tag write **Unit id types 5** - `statsig.unit_id_types.create` Create Unit ID Type write - `statsig.unit_id_types.delete` Delete Unit ID Type destructive - `statsig.unit_id_types.get` Get Unit ID Type read - `statsig.unit_id_types.list` List Unit ID Types read - `statsig.unit_id_types.patch` Update Unit ID Type write **Events 3** - `statsig.events.get` Get specific events read - `statsig.events.list` List Events read - `statsig.events.metrics_list` Get metrics using event name read **Change validation 2** - `statsig.change_validation.create` Change Validation write - `statsig.change_validation.message` Update change validation message write **Environments 2** - `statsig.environments.create` Update Environments write - `statsig.environments.list` Get Environments read **Audit logs 1** - `statsig.audit_logs.list` List Audit Logs read **Company 1** - `statsig.company.get` Get Company Info read **Exports 1** - `statsig.exports.status_list` List warehouse export status read **Exposure count 1** - `statsig.exposure_count.get` Read Exposure Event Count read **Logs 1** - `statsig.logs.list` List recent events for the Logs Explorer read **Overrides 1** - `statsig.overrides.get` Audit Overrides read **Project 1** - `statsig.project.get` Get Project Info read **Reports 1** - `statsig.reports.get` Get Reports read **WH connections 1** - `statsig.wh_connections.patch` Update Warehouse Connection Parameters write Questions ## The Statsig MCP server, answered. **Is there a Statsig MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 354 Statsig actions across experiments, gates, autotunes and dynamic configs, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Statsig. **What do I need to connect Statsig?** Statsig Console API key. The free call account { op: "connections.requirements", service: "statsig" } lists exactly what to paste. **Can an AI agent delete or change things in Statsig?** Only if its key allows it, and only with an explicit confirmation. 55 Statsig actions are destructive, including delete Segment, delete Experiment and delete a metric. 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 Statsig API limit?** actionlake paces every call to the limits in the Statsig service file: 1,800 calls per 15 minutes per connection. Repeated reads are answered from cache (140 Statsig actions can be), which never reaches Statsig. **What does a Statsig action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (354 Statsig actions page). Cache hits, searches, dry runs and calls Statsig 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 Statsig API does it cover?** The Statsig Console API 20240601.0.0 (OpenAPI 3.0.0) at statsigapi.net. It is built from Statsig's documentation as read on 23 October 2026. 354 actions in 37 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Statsig 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 Statsig 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 Statsig Shares the most action names with - [LaunchDarkly 26](https://actionlake.com/connectors/launchdarkly) - [Splunk Platform 11](https://actionlake.com/connectors/splunk-platform) - [ClickHouse Cloud 11](https://actionlake.com/connectors/clickhouse-cloud) - [Harness Platform 11](https://actionlake.com/connectors/harness-platform) - [Pulumi Cloud 10](https://actionlake.com/connectors/pulumi-cloud) - [Optimizely Feature Experimentation 9](https://actionlake.com/connectors/optimizely-feature-experimentation) Joins with, on shared entities - [HaloPSA 1](https://actionlake.com/connectors/halopsa) - [Slack 1](https://actionlake.com/connectors/slack) - [Gusto 1](https://actionlake.com/connectors/gusto) - [Microsoft 365 Users 1](https://actionlake.com/connectors/microsoft-365-users) - [NinjaOne 1](https://actionlake.com/connectors/ninjaone) - [Salesforce Sales Cloud 1](https://actionlake.com/connectors/salesforce-sales-cloud) Browse - [All Developer & infrastructure connectors](https://actionlake.com/connectors/category/developer-and-infrastructure) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Statsig; the name is the vendor's own. Counts are from the Statsig service file, version 1.0.0. ## Give your agent Statsig today. [Connect Statsig 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/statsig More: https://actionlake.com/llms.txt