Statsig MCP
for LuumenAI
Read gates, experiments, and configs in Statsig, then change them through review
Connect Statsig and Luumen can read your experiments, feature gates, dynamic configs, layers, metrics, segments, and audit logs on demand. Ask what changed on a config last week, or who can approve a pending review. When a change is needed, Luumen opens or approves the review and shows you the exact proposal first.
The Statsig MCP toolbox
93 tools: 48 read, 45 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadCluster log patternsCluster similar log lines into templates (same as `statsig-query log-patterns`).
- ReadFetchFetch the full document for a search result id.
- ReadGet audit logsList audit logs for this Statsig project.
- ReadGet autotune eligible reviewersList the users and reviewer groups eligible to approve/reject a review of this autotune experiment.
- ReadGet autotune review by idGet a single review for an autotune experiment by its review ID, including its status, proposed change type, author, and requested reviewers.
- ReadGet contextBootstrap the authenticated Statsig MCP session.
- ReadGet dynamic config details by idGet the details (including rules, return values, and more) for a Dynamic Config (static, targetable JSON) in the Statsig console.
- ReadGet dynamic config eligible reviewersList the users and reviewer groups eligible to approve/reject a review of this dynamic config.
- ReadGet dynamic config review by idGet a single review for a dynamic config by its review ID, including its status, proposed change, author, and requested reviewers.
- ReadGet dynamic config version historyList historical versions of a Dynamic Config (static, targetable JSON object) to reconstruct a timeline of how it changed — rules, return values, defaults, and metadata across edits.
- ReadGet experiment details by idGet details including parameters (return values), groups, status & more of an experiment in Statsig.
- ReadGet experiment eligible reviewersList the users and reviewer groups eligible to approve/reject a review of this experiment (A/B test).
- ReadGet experiment metric dimension resultsGet topline and dimensional breakdown results for one specific experiment metric.
- ReadGet experiment overall resultsGet overall pulse results for an experiment across all pulse metrics.
- ReadGet experiment review by idGet a single review for an experiment (A/B test) by its review ID, including its status, proposed change type, author, and requested reviewers.
- ReadGetexperimentsummarychartsGet Experiment Summary charts and underlying data.
- ReadGet experiment version historyList historical versions of an experiment (AB Test) to reconstruct a timeline of how it changed — groups, allocation, status, parameters, and metadata across edits.
- ReadGet gate details by idGet all details about a gate (feature flag) like its rules, idType, and more, from the Statsig Console.
- ReadGet gate eligible reviewersList the users and reviewer groups eligible to approve/reject a review of this gate (feature flag).
- ReadGet gate resultsGet the metric results for a given gate and rule in the gate
- ReadGet gate review by idGet a single review for a gate (feature flag) by its review ID, including its status, proposed change, author, and requested reviewers.
- ReadGet gate version historyList historical versions of a gate (feature flag) to reconstruct a timeline of how it changed — rules, IDtype, enabled state, and metadata across edits.
- ReadGet layer details by idGet all details about a layer, including its parameters and metadata, from the Statsig Console.
- ReadGet layer experimentsList the experiments in a layer, including each experiment's allocation and groups within the layer.
- ReadGet layer overridesGet the conditional and ID overrides configured for a layer in the Statsig Console.
- ReadGet list of autotune reviewsList the reviews for an autotune experiment, newest first.
- ReadGet list of dynamic config reviewsList the reviews for a dynamic config, newest first.
- ReadGet list of dynamic configsList all Dynamic Configs (static, targetable JSON objects) in this Statsig project.
- ReadGet list of experiment reviewsList the reviews for an experiment (A/B test), newest first.
- ReadGet list of experimentsList all experiments (AB Tests) in this Statsig project.
- ReadGet list of gate reviewsList the reviews for a gate (feature flag), newest first.
- ReadGet list of gatesList all gates (feature flags) in this Statsig project.
- ReadGet list of layersList all layers in this Statsig project.
- ReadGet list of metricsList all metrics in this Statsig project.
- ReadGet list of metric sourcesList all metric sources in this Statsig project.
- ReadGet list of param storesList param stores in this Statsig project.
- ReadGet list of promptsList all Prompts in this Statsig project.
- ReadGet list of segmentsList all segments in this Statsig project.
- ReadGet list of tagsList all tags in this Statsig project, returning each tag's id and name.
- ReadGet metric definition by idGet the full definition for a metric in Statsig, including its type, source, and configuration details.
- ReadGet param store details by idGet a param store by name, including its description, typed parameters, and metadata.
- ReadGet prompt details by idGet the details (name, description, target apps, team, tags, and metadata) for a single Prompt in the Statsig console.
- ReadGet segment by idGet all details about a segment in the Statsig Console.
- ReadGet tool schemaGet the full input schema, description, and annotations for any Statsig MCP tool by name — including tools not shown in the default tool list (find them with Search_Tools).
- ReadInvoke toolExecute any Statsig MCP tool by name with arguments — including tools not shown in the default tool list.
- ReadQuery logs explorerFetch log lines from Statsig Logs Explorer (MCP equivalent of `statsig-query logs`).
- ReadSearchSearch the Statsig MCP data source and return relevant results.
- ReadSearch toolsSearch the full Statsig MCP tool catalog using natural language, exact names, aliases, categories, and typo-tolerant matching.
- WriteApprove autotune reviewApprove an in-flight review of an autotune experiment. Approval by default
- WriteApprove dynamic config reviewApprove an in-flight review of a dynamic config. Approval by default
- WriteApprove experiment reviewApprove an in-flight review of an experiment (A/B test). Approval by default
- WriteApprove gate reviewApprove an in-flight review of a gate (feature flag). Approval by default
- WriteCancel autotune reviewCancel (withdraw) an in-flight review of an autotune experiment. Approval by default
- WriteCancel dynamic config reviewCancel (withdraw) an in-flight review of a dynamic config. Approval by default
- WriteCancel experiment reviewCancel (withdraw) an in-flight review of an experiment (A/B test). Approval by default
- WriteCancel gate reviewCancel (withdraw) an in-flight review of a gate (feature flag). Approval by default
- WriteCommit autotune reviewCommit a review of an autotune experiment, APPLYING its proposed change to the live autotune. Approval by default
- WriteCommit dynamic config reviewCommit a review of a dynamic config, APPLYING its proposed change to the live config. Approval by default
- WriteCommit experiment reviewCommit a review of an experiment (A/B test), APPLYING its proposed change to the live experiment. Approval by default
- WriteCommit gate reviewCommit a review of a gate (feature flag), APPLYING its proposed change to the live gate. Approval by default
- WriteCreate autotuneCreate an Autotune (multi-armed bandit) experiment that automatically shifts traffic toward the best-performing variant. Approval by default
- WriteCreate autotune reviewOpen a review proposing a change to an autotune experiment. Approval by default
- WriteCreate dynamic configCreate a new Dynamic Config (static, targetable JSON object) in the Statsig console, including targeting rules, its ID (how we'll refer to it in-code) and its IDtype, which it'll randomize users on. Approval by default
- WriteCreate dynamic config reviewOpen a review proposing a change to a dynamic config. Approval by default
- WriteCreate experimentCreate an experiment, including its ID (which is how we refer to it in-code), its groups (test/control, and return values) and the ID type it should randomize users on. Approval by default
- WriteCreate experiment reviewOpen a review proposing a change to an experiment (A/B test). Approval by default
- WriteCreate gateCreate a new gate (feature flag), including its rules (who should pass it) its ID (how we'll refer to it in-code) and its IDtype, which it'll randomize users on. Approval by default
- WriteCreate gate reviewOpen a review proposing a change to a gate (feature flag). Approval by default
- WriteCreate layerCreate a new layer, including its name, ID type, and optional target apps or team ownership. Approval by default
- WriteCreate param storeCreate a new Param Store (a reusable, named collection of typed parameters) in this Statsig project. Approval by default
- WriteCreate promptCreate a new Prompt (a specialized AI Config for managing and versioning LLM prompts) in the Statsig console. Approval by default
- WriteCreate prompt versionCreate a new version of an existing Prompt. Approval by default
- WriteCreate segmentCreate a new segment, including its name, type, optional ID, ID type, and rules for rule-based segments. Approval by default
- WriteDelete experimentDelete an experiment (A/B test) by ID. Approval by default
- WriteDelete param storeDelete a Param Store by name. Approval by default
- WriteEdit autotune reviewEdit an in-flight autotune review's metadata — description and/or requested reviewers. Approval by default
- WriteEdit dynamic config reviewEdit an in-flight dynamic config review's metadata (description, requested reviewers) and/or its proposed `change`. Approval by default
- WriteEdit experiment reviewEdit an in-flight experiment (A/B test) review's metadata — description and/or requested reviewers. Approval by default
- WriteEdit gate reviewEdit an in-flight gate (feature flag) review's metadata (description, requested reviewers) and/or its proposed `change`. Approval by default
- WriteReject autotune reviewReject an in-flight review of an autotune experiment. Approval by default
- WriteReject dynamic config reviewReject an in-flight review of a dynamic config. Approval by default
- WriteReject experiment reviewReject an in-flight review of an experiment (A/B test). Approval by default
- WriteReject gate reviewReject an in-flight review of a gate (feature flag). Approval by default
- WriteStart experiment code cleanupStart code cleanup for a stale experiment by name, which creates a PR to remove the experiment from your codebase. Approval by default
- WriteStart gate code cleanupStart code cleanup for a gate by name, which creates a PR to remove the gate from your codebase. Approval by default
- WriteStart prompt version evalsStart an offline evaluation job for a specific Prompt Version, identified by the Prompt id and the versionId. Approval by default
- WriteUpdate dynamic config entirelyFully update a dynamic config, replacing everything the dynamic config currently has on the Statsig console with the data included in this POST request. Approval by default
- WriteUpdate experiment entirelyFully update an experiment, replacing everything the experiment currently has on the Statsig console with the data included in this POST request. Approval by default
- WriteUpdate gate entirelyFully update a gate, replacing everything the gate currently has on the Statsig console with the data included in this POST request. Approval by default
- WriteUpdate layer entirelyFully update a layer, replacing everything the layer currently has on the Statsig console with the data included in this POST request. Approval by default
- WriteUpdate param storeUpdate an existing Param Store by name. Approval by default
- WriteUpdate promptPartially update a Prompt by ID. Approval by default
- WriteUpdate segmentUpdate a Statsig segment using the appropriate segment endpoint. Approval by default
One prompt, start to finish
What a governed Statsig MCP run looks like inside Luumen.
Questions
How does LuumenAI connect to Statsig MCP?
Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Can LuumenAI change things in Statsig MCP on its own?
Read actions answer immediately. Anything that writes — approve autotune review, approve dynamic config review, approve experiment review, approve gate review, and more — is shown as a plan and requires approval by default, including the 23 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
Who gets access to the integration?
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Is there an audit trail?
Every call to Statsig MCP — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut Statsig MCP to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.