Skip to main content

Statsig

MCP server for Statsig - manage experiments, feature gates, and dynamic configs

Tools

93 available tools

Search the tool definitions captured from the MCP server. The live list can vary with version, deployment, and credentials.

93 tools found.

  • Approve autotune review

    Tool name: Approve_Autotune_Review

    Approve an in-flight review of an autotune experiment.

  • Approve dynamic config review

    Tool name: Approve_Dynamic_Config_Review

    Approve an in-flight review of a dynamic config.

  • Approve experiment review

    Tool name: Approve_Experiment_Review

    Approve an in-flight review of an experiment (A/B test).

  • Approve gate review

    Tool name: Approve_Gate_Review

    Approve an in-flight review of a gate (feature flag).

  • Cancel autotune review

    Tool name: Cancel_Autotune_Review

    Cancel (withdraw) an in-flight review of an autotune experiment.

  • Cancel dynamic config review

    Tool name: Cancel_Dynamic_Config_Review

    Cancel (withdraw) an in-flight review of a dynamic config.

  • Cancel experiment review

    Tool name: Cancel_Experiment_Review

    Cancel (withdraw) an in-flight review of an experiment (A/B test).

  • Cancel gate review

    Tool name: Cancel_Gate_Review

    Cancel (withdraw) an in-flight review of a gate (feature flag).

  • Cluster log patterns

    Tool name: Cluster_Log_Patterns

    Cluster similar log lines into templates (same as statsig-query log-patterns).

  • Commit autotune review

    Tool name: Commit_Autotune_Review

    Commit a review of an autotune experiment, APPLYING its proposed change to the live autotune.

  • Commit dynamic config review

    Tool name: Commit_Dynamic_Config_Review

    Commit a review of a dynamic config, APPLYING its proposed change to the live config.

  • Commit experiment review

    Tool name: Commit_Experiment_Review

    Commit a review of an experiment (A/B test), APPLYING its proposed change to the live experiment.

  • Commit gate review

    Tool name: Commit_Gate_Review

    Commit a review of a gate (feature flag), APPLYING its proposed change to the live gate.

  • Create autotune

    Tool name: Create_Autotune

    Create an Autotune (multi-armed bandit) experiment that automatically shifts traffic toward the best-performing variant.

  • Create autotune review

    Tool name: Create_Autotune_Review

    Open a review proposing a change to an autotune experiment.

  • Create dynamic config

    Tool name: Create_Dynamic_Config

    Create 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.

  • Create dynamic config review

    Tool name: Create_Dynamic_Config_Review

    Open a review proposing a change to a dynamic config.

  • Create experiment

    Tool name: Create_Experiment

    Create 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.

  • Create experiment review

    Tool name: Create_Experiment_Review

    Open a review proposing a change to an experiment (A/B test).

  • Create gate

    Tool name: Create_Gate

    Create 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.

  • Create gate review

    Tool name: Create_Gate_Review

    Open a review proposing a change to a gate (feature flag).

  • Create layer

    Tool name: Create_Layer

    Create a new layer, including its name, ID type, and optional target apps or team ownership.

  • Create param store

    Tool name: Create_Param_Store

    Create a new Param Store (a reusable, named collection of typed parameters) in this Statsig project.

  • Create prompt

    Tool name: Create_Prompt

    Create a new Prompt (a specialized AI Config for managing and versioning LLM prompts) in the Statsig console.

  • Create prompt version

    Tool name: Create_Prompt_Version

    Create a new version of an existing Prompt.

  • Create segment

    Tool name: Create_Segment

    Create a new segment, including its name, type, optional ID, ID type, and rules for rule-based segments.

  • Delete experiment

    Tool name: Delete_Experiment

    Delete an experiment (A/B test) by ID.

  • Delete param store

    Tool name: Delete_Param_Store

    Delete a Param Store by name.

  • Edit autotune review

    Tool name: Edit_Autotune_Review

    Edit an in-flight autotune review's metadata — description and/or requested reviewers.

  • Edit dynamic config review

    Tool name: Edit_Dynamic_Config_Review

    Edit an in-flight dynamic config review's metadata (description, requested reviewers) and/or its proposed change.

  • Edit experiment review

    Tool name: Edit_Experiment_Review

    Edit an in-flight experiment (A/B test) review's metadata — description and/or requested reviewers.

  • Edit gate review

    Tool name: Edit_Gate_Review

    Edit an in-flight gate (feature flag) review's metadata (description, requested reviewers) and/or its proposed change.

  • Get experiment summary charts

    Tool name: GetExperimentSummaryCharts

    Get Experiment Summary charts and underlying data.

  • Get audit logs

    Tool name: Get_Audit_Logs

    List audit logs for this Statsig project.

  • Get autotune eligible reviewers

    Tool name: Get_Autotune_Eligible_Reviewers

    List the users and reviewer groups eligible to approve/reject a review of this autotune experiment.

  • Get autotune review by ID

    Tool name: Get_Autotune_Review_by_ID

    Get a single review for an autotune experiment by its review ID, including its status, proposed change type, author, and requested reviewers.

  • Get context

    Tool name: Get_Context

    Bootstrap the authenticated Statsig MCP session.

  • Get dynamic config details by ID

    Tool name: Get_Dynamic_Config_Details_by_ID

    Get the details (including rules, return values, and more) for a Dynamic Config (static, targetable JSON) in the Statsig console.

  • Get dynamic config eligible reviewers

    Tool name: Get_Dynamic_Config_Eligible_Reviewers

    List the users and reviewer groups eligible to approve/reject a review of this dynamic config.

  • Get dynamic config review by ID

    Tool name: Get_Dynamic_Config_Review_by_ID

    Get a single review for a dynamic config by its review ID, including its status, proposed change, author, and requested reviewers.

  • Get dynamic config version history

    Tool name: Get_Dynamic_Config_Version_History

    List 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.

  • Get experiment details by ID

    Tool name: Get_Experiment_Details_by_ID

    Get details including parameters (return values), groups, status & more of an experiment in Statsig.

  • Get experiment eligible reviewers

    Tool name: Get_Experiment_Eligible_Reviewers

    List the users and reviewer groups eligible to approve/reject a review of this experiment (A/B test).

  • Get experiment metric dimension results

    Tool name: Get_Experiment_Metric_Dimension_Results

    Get topline and dimensional breakdown results for one specific experiment metric.

  • Get experiment overall results

    Tool name: Get_Experiment_Overall_Results

    Get overall pulse results for an experiment across all pulse metrics.

  • Get experiment review by ID

    Tool name: Get_Experiment_Review_by_ID

    Get a single review for an experiment (A/B test) by its review ID, including its status, proposed change type, author, and requested reviewers.

  • Get experiment version history

    Tool name: Get_Experiment_Version_History

    List historical versions of an experiment (AB Test) to reconstruct a timeline of how it changed — groups, allocation, status, parameters, and metadata across edits.

  • Get gate details by ID

    Tool name: Get_Gate_Details_by_ID

    Get all details about a gate (feature flag) like its rules, idType, and more, from the Statsig Console.

  • Get gate eligible reviewers

    Tool name: Get_Gate_Eligible_Reviewers

    List the users and reviewer groups eligible to approve/reject a review of this gate (feature flag).

  • Get gate results

    Tool name: Get_Gate_Results

    Get the metric results for a given gate and rule in the gate

  • Get gate review by ID

    Tool name: Get_Gate_Review_by_ID

    Get a single review for a gate (feature flag) by its review ID, including its status, proposed change, author, and requested reviewers.

  • Get gate version history

    Tool name: Get_Gate_Version_History

    List historical versions of a gate (feature flag) to reconstruct a timeline of how it changed — rules, IDtype, enabled state, and metadata across edits.

  • Get layer details by ID

    Tool name: Get_Layer_Details_by_ID

    Get all details about a layer, including its parameters and metadata, from the Statsig Console.

  • Get layer experiments

    Tool name: Get_Layer_Experiments

    List the experiments in a layer, including each experiment's allocation and groups within the layer.

  • Get layer overrides

    Tool name: Get_Layer_Overrides

    Get the conditional and ID overrides configured for a layer in the Statsig Console.

  • Get list of autotune reviews

    Tool name: Get_List_of_Autotune_Reviews

    List the reviews for an autotune experiment, newest first.

  • Get list of dynamic config reviews

    Tool name: Get_List_of_Dynamic_Config_Reviews

    List the reviews for a dynamic config, newest first.

  • Get list of dynamic configs

    Tool name: Get_List_of_Dynamic_Configs

    List all Dynamic Configs (static, targetable JSON objects) in this Statsig project.

  • Get list of experiment reviews

    Tool name: Get_List_of_Experiment_Reviews

    List the reviews for an experiment (A/B test), newest first.

  • Get list of experiments

    Tool name: Get_List_of_Experiments

    List all experiments (AB Tests) in this Statsig project.

  • Get list of gate reviews

    Tool name: Get_List_of_Gate_Reviews

    List the reviews for a gate (feature flag), newest first.

  • Get list of gates

    Tool name: Get_List_of_Gates

    List all gates (feature flags) in this Statsig project.

  • Get list of layers

    Tool name: Get_List_of_Layers

    List all layers in this Statsig project.

  • Get list of metric sources

    Tool name: Get_List_of_Metric_Sources

    List all metric sources in this Statsig project.

  • Get list of metrics

    Tool name: Get_List_of_Metrics

    List all metrics in this Statsig project.

  • Get list of param stores

    Tool name: Get_List_of_Param_Stores

    List param stores in this Statsig project.

  • Get list of prompts

    Tool name: Get_List_of_Prompts

    List all Prompts in this Statsig project.

  • Get list of segments

    Tool name: Get_List_of_Segments

    List all segments in this Statsig project.

  • Get list of tags

    Tool name: Get_List_of_Tags

    List all tags in this Statsig project, returning each tag's id and name.

  • Get metric definition by ID

    Tool name: Get_Metric_Definition_by_ID

    Get the full definition for a metric in Statsig, including its type, source, and configuration details.

  • Get param store details by ID

    Tool name: Get_Param_Store_Details_by_Id

    Get a param store by name, including its description, typed parameters, and metadata.

  • Get prompt details by ID

    Tool name: Get_Prompt_Details_by_ID

    Get the details (name, description, target apps, team, tags, and metadata) for a single Prompt in the Statsig console.

  • Get segment by ID

    Tool name: Get_Segment_by_ID

    Get all details about a segment in the Statsig Console.

  • Get tool schema

    Tool name: Get_Tool_Schema

    Get 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).

  • Invoke tool

    Tool name: Invoke_Tool

    Execute any Statsig MCP tool by name with arguments — including tools not shown in the default tool list.

  • Query logs explorer

    Tool name: Query_Logs_Explorer

    Fetch log lines from Statsig Logs Explorer (MCP equivalent of statsig-query logs).

  • Reject autotune review

    Tool name: Reject_Autotune_Review

    Reject an in-flight review of an autotune experiment.

  • Reject dynamic config review

    Tool name: Reject_Dynamic_Config_Review

    Reject an in-flight review of a dynamic config.

  • Reject experiment review

    Tool name: Reject_Experiment_Review

    Reject an in-flight review of an experiment (A/B test).

  • Reject gate review

    Tool name: Reject_Gate_Review

    Reject an in-flight review of a gate (feature flag).

  • Search tools

    Tool name: Search_Tools

    Search the full Statsig MCP tool catalog using natural language, exact names, aliases, categories, and typo-tolerant matching.

  • Start experiment code cleanup

    Tool name: Start_Experiment_Code_Cleanup

    Start code cleanup for a stale experiment by name, which creates a PR to remove the experiment from your codebase.

  • Start gate code cleanup

    Tool name: Start_Gate_Code_Cleanup

    Start code cleanup for a gate by name, which creates a PR to remove the gate from your codebase.

  • Start prompt version evals

    Tool name: Start_Prompt_Version_Evals

    Start an offline evaluation job for a specific Prompt Version, identified by the Prompt id and the versionId.

  • Update dynamic config entirely

    Tool name: Update_Dynamic_Config_Entirely

    Fully update a dynamic config, replacing everything the dynamic config currently has on the Statsig console with the data included in this POST request.

  • Update experiment entirely

    Tool name: Update_Experiment_Entirely

    Fully update an experiment, replacing everything the experiment currently has on the Statsig console with the data included in this POST request.

  • Update gate entirely

    Tool name: Update_Gate_Entirely

    Fully update a gate, replacing everything the gate currently has on the Statsig console with the data included in this POST request.

  • Update layer entirely

    Tool name: Update_Layer_Entirely

    Fully update a layer, replacing everything the layer currently has on the Statsig console with the data included in this POST request.

  • Update param store

    Tool name: Update_Param_Store

    Update an existing Param Store by name.

  • Update prompt

    Tool name: Update_Prompt

    Partially update a Prompt by ID.

  • Update segment

    Tool name: Update_Segment

    Update a Statsig segment using the appropriate segment endpoint.

  • Fetch

    Tool name: fetch

    Fetch the full document for a search result id.

  • Search

    Tool name: search

    Search the Statsig MCP data source and return relevant results.

Compatibility

Connect Statsig to the clients your teams already use

27 AI clients can connect to Statsig through Runlayer. Pick one for its setup steps and controls.

Why Runlayer

Why connect Statsig through Runlayer?

One approved path

Approve Statsig once and everyone gets it in the AI clients they already use. Runlayer holds the credentials, so nothing sits in client configuration.

Fine-grained policy

Control who can use each server, tool, and resource, and under which runtime conditions.

Runtime security

Scan tool inputs and outputs for prompt injection, credential exposure, PII, and data exfiltration, then alert, mask, or block.

Audit and observability

Trace every request across users, clients, tools, policies, scanner decisions, and downstream systems.

Frequently asked questions