PrecisionBook a discovery call
Menu

Statsig MCP for AI agents

Agents read Statsig MCP at once. Changes and sends are held for a person's approval by default.

Book a discovery callBrowse all connectors

About Statsig MCP

Statsig MCP exposes experiments, feature gates, dynamic configs, layers, metrics, segments, reviews, audit logs, and observability workflows.

What an agent can do in Statsig MCP

Every Statsig MCP action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.

Runs at once (reads)

Looks things up in Statsig MCP without asking first. 47 actions.

  • Cluster log patternsCluster similar log lines into templates (same as `statsig-query log-patterns`). Use after `Query_Logs_Explorer` when raw lines are too noisy. Pass a Logs Explorer filter (e.g. `service:scrapi AND tie
  • FetchFetch the full document for a search result id. Use the id returned by search.
  • Get audit logsList audit logs for this Statsig project. Supports filtering by id, sorting, tags, date range, and pagination.
  • Get autotune eligible reviewersList the users and reviewer groups eligible to approve/reject a review of this autotune experiment. Use this to pick valid reviewer_ids / reviewer_group_ids when creating or editing an autotune review
  • Get 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. A review is a proposed change that goes through an approve
  • Get contextBootstrap the authenticated Statsig MCP session. Returns bounded organization, selected project, environment, effective API-key permissions, review settings, accessible product areas, project environm
  • Get dynamic config details by idGet the details (including rules, return values, and more) for a Dynamic Config (static, targetable JSON) in the Statsig console.
  • Get dynamic config eligible reviewersList the users and reviewer groups eligible to approve/reject a review of this dynamic config. Use this to pick valid reviewer_ids / reviewer_group_ids when creating or editing a dynamic config review
  • Get 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. A review is a proposed change to the dynamic config that goes through
  • Get 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. Useful for debugg
  • Get experiment details by idGet details including parameters (return values), groups, status & more of an experiment in Statsig. Use query_fields to return only specific top-level fields and keep the response small.
  • Get experiment eligible reviewersList the users and reviewer groups eligible to approve/reject a review of this experiment (A/B test). Use this to pick valid reviewer_ids / reviewer_group_ids when creating or editing an experiment re
Show all 47
  • Get experiment metric dimension resultsGet topline and dimensional breakdown results for one specific experiment metric. Use this when you already know the metric ID and need that metric broken down by dimensions. Do not use this tool for
  • Get experiment overall resultsGet overall pulse results for an experiment across all pulse metrics. Use this when you need the experiment-wide topline view or a cross-metric summary. Do not use this tool when you need the dimensio
  • Get 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. A review is a proposed change that goes through an appro
  • GetexperimentsummarychartsGet Experiment Summary charts and underlying data.
  • Get 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. Useful for debugging when experimen
  • Get gate details by idGet all details about a gate (feature flag) like its rules, idType, and more, from the Statsig Console. To judge whether a feature is actually live for a user, check status and isEnabled BEFORE reason
  • Get gate eligible reviewersList the users and reviewer groups eligible to approve/reject a review of this gate (feature flag). Use this to pick valid reviewer_ids / reviewer_group_ids when creating or editing a gate review. The
  • Get gate resultsGet the metric results for a given gate and rule in the gate
  • Get 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. A review is a proposed change to the gate that goes through an a
  • Get 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. Useful for debugging when gate behavior changed
  • Get layer details by idGet all details about a layer, including its parameters and metadata, from the Statsig Console.
  • Get layer experimentsList the experiments in a layer, including each experiment's allocation and groups within the layer. The API enforces a maximum query_limit of 100. If query_limit is not provided, default to 100 (or f
  • Get layer overridesGet the conditional and ID overrides configured for a layer in the Statsig Console.
  • Get list of autotune reviewsList the reviews for an autotune experiment, newest first. A review is a proposed change to the autotune (start / reallocate / make_decision / delete, etc.) that goes through an approve → commit lifec
  • Get list of dynamic config reviewsList the reviews for a dynamic config, newest first. A review is a proposed change to the dynamic config (rules, default_value, enabled state, archive, delete, etc.) that goes through an approve → com
  • Get list of dynamic configsList all Dynamic Configs (static, targetable JSON objects) in this Statsig project. The API enforces a maximum query_limit of 100. If query_limit is not provided, default to 100 (or fewer) and never e
  • Get list of experiment reviewsList the reviews for an experiment (A/B test), newest first. A review is a proposed change to the experiment (start / stop / make_decision / rollout / settings, etc.) that goes through an approve → co
  • Get list of experimentsList all experiments (AB Tests) in this Statsig project. Supports filtering by status, tags, creator, team (query_teamID), and created date range (query_createdStartDate / query_createdEndDate as YYYY
  • Get list of gate reviewsList the reviews for a gate (feature flag), newest first. A review is a proposed change to the gate (rules, enabled state, archive, delete, etc.) that goes through an approve → commit lifecycle before
  • Get list of gatesList all gates (feature flags) in this Statsig project. Live state for each gate is determined by status and isEnabled, not just rules: when isEnabled is false the rules are NOT evaluated — status "La
  • Get list of layersList all layers in this Statsig project. The API enforces a maximum query_limit of 100. If query_limit is not provided, default to 100 (or fewer) and never exceed 100.
  • Get list of metricsList all metrics in this Statsig project. The API enforces a maximum query_limit of 100. If query_limit is not provided, default to 100 (or fewer) and never exceed 100.
  • Get list of metric sourcesList all metric sources in this Statsig project. The API enforces a maximum query_limit of 100. If query_limit is not provided, default to 100 (or fewer) and never exceed 100.
  • Get list of param storesList param stores in this Statsig project. The API enforces a maximum query_limit of 100. If query_limit is not provided, default to 100 (or fewer) and never exceed 100.
  • Get list of promptsList all Prompts in this Statsig project. A Prompt is a specialized AI Config for managing and versioning LLM prompts. Supports pagination via limit and page.
  • Get list of segmentsList all segments in this Statsig project.
  • Get list of tagsList all tags in this Statsig project, returning each tag's id and name. Use this to resolve a tag name/text (e.g. "oslo-tier-0", "checkout") to its tag id, then pass those ids to the query_tags filte
  • Get metric definition by idGet the full definition for a metric in Statsig, including its type, source, and configuration details.
  • Get param store details by idGet a param store by name, including its description, typed parameters, and metadata.
  • Get prompt details by idGet the details (name, description, target apps, team, tags, and metadata) for a single Prompt in the Statsig console.
  • Get segment by idGet all details about a segment in the Statsig Console.
  • Get 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). After fetching the schema,
  • Query logs explorerFetch log lines from Statsig Logs Explorer (MCP equivalent of `statsig-query logs`). Uses the same filter syntax as the console filter bar and CLI `--filter` (e.g. `service:scrapi AND tier:latest AND
  • SearchSearch the Statsig MCP data source and return relevant results. Use the fetch tool to retrieve full documents.
  • Search toolsSearch the full Statsig MCP tool catalog using natural language, exact names, aliases, categories, and typo-tolerant matching. Results are permission-aware and ranked by relevance, operation intent, r

Held for approval by default (changes and sends)

Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 46 actions.

  • Approve autotune reviewApprove an in-flight review of an autotune experiment. Approval does NOT apply the change to the live autotune — call Commit_Autotune_Review afterward to apply it. The acting user must be an eligible
  • Approve dynamic config reviewApprove an in-flight review of a dynamic config. Approval does NOT apply the change to the live config — call Commit_Dynamic_Config_Review afterward to apply it. The acting user must be an eligible re
  • Approve experiment reviewApprove an in-flight review of an experiment (A/B test). Approval does NOT apply the change to the live experiment — call Commit_Experiment_Review afterward to apply it. The acting user must be an eli
  • Approve gate reviewApprove an in-flight review of a gate (feature flag). Approval does NOT apply the change to the live gate — call Commit_Gate_Review afterward to apply it. The acting user must be an eligible reviewer
  • Cancel autotune reviewCancel (withdraw) an in-flight review of an autotune experiment. This permanently withdraws the proposed change; it does NOT modify the live autotune. Only mutable reviews (pending or accepted) can be
  • Cancel dynamic config reviewCancel (withdraw) an in-flight review of a dynamic config. This permanently withdraws the proposed change; it does NOT modify the live config. Only mutable reviews (pending or accepted) can be cancell
  • Cancel experiment reviewCancel (withdraw) an in-flight review of an experiment (A/B test). This permanently withdraws the proposed change; it does NOT modify the live experiment. Only mutable reviews (pending or accepted) ca
  • Cancel gate reviewCancel (withdraw) an in-flight review of a gate (feature flag). This permanently withdraws the proposed change; it does NOT modify the live gate. Only mutable reviews (pending or accepted) can be canc
  • Commit autotune reviewCommit a review of an autotune experiment, APPLYING its proposed change to the live autotune. This is the step that actually mutates the autotune (e.g. starting it, resetting/reallocating, making a de
  • Commit dynamic config reviewCommit a review of a dynamic config, APPLYING its proposed change to the live config. This is the step that actually mutates the config (e.g. updating rules/default_value, enabling/disabling, archivin
  • Commit experiment reviewCommit a review of an experiment (A/B test), APPLYING its proposed change to the live experiment. This is the step that actually mutates the experiment (e.g. starting / stopping it, shipping a decisio
  • Commit gate reviewCommit a review of a gate (feature flag), APPLYING its proposed change to the live gate. This is the step that actually mutates the gate (e.g. updating rules, enabling/disabling, archiving, or deletin
Show all 46
  • Create autotuneCreate an Autotune (multi-armed bandit) experiment that automatically shifts traffic toward the best-performing variant. Specify the variants (arms), the successEvent to optimize for, and the explorat
  • Create autotune reviewOpen a review proposing a change to an autotune experiment. The change is NOT applied to the live autotune yet — it must be approved (Approve_Autotune_Review) and then committed (Commit_Autotune_Revie
  • Create 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. C
  • Create dynamic config reviewOpen a review proposing a change to a dynamic config. The change is NOT applied to the live config yet — it must be approved (Approve_Dynamic_Config_Review) and then committed (Commit_Dynamic_Config_R
  • Create 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. For metrics, omit direction and
  • Create experiment reviewOpen a review proposing a change to an experiment (A/B test). The change is NOT applied to the live experiment yet — it must be approved (Approve_Experiment_Review) and then committed (Commit_Experime
  • Create 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.
  • Create gate reviewOpen a review proposing a change to a gate (feature flag). The change is NOT applied to the live gate yet — it must be approved (Approve_Gate_Review) and then committed (Commit_Gate_Review). Provide a
  • Create layerCreate a new layer, including its name, ID type, and optional target apps or team ownership.
  • Create param storeCreate a new Param Store (a reusable, named collection of typed parameters) in this Statsig project. Provide a name (the in-code identifier), a displayName, and a description. The store is created emp
  • Create promptCreate a new Prompt (a specialized AI Config for managing and versioning LLM prompts) in the Statsig console. A Prompt is created by name (the in-code identifier); optionally set a displayName, descri
  • Create prompt versionCreate a new version of an existing Prompt. Provide the prompts array (each entry has a role of system, user, or assistant and its content), and optionally the model, provider, temperature, top_p, max
  • Create segmentCreate a new segment, including its name, type, optional ID, ID type, and rules for rule-based segments.
  • Delete experimentDelete an experiment (A/B test) by ID. Destructive and irreversible — confirm the ID before calling. On a team that requires reviews, prefer proposing the deletion through review (Create_Experiment_Re
  • Delete param storeDelete a Param Store by name. Destructive and irreversible — it removes a store that SDKs may be reading. Confirm the name before calling.
  • Edit autotune reviewEdit an in-flight autotune review's metadata — description and/or requested reviewers. Supply any subset; an omitted field keeps the review's current value, and an empty body is rejected. Autotune rev
  • Edit dynamic config reviewEdit an in-flight dynamic config review's metadata (description, requested reviewers) and/or its proposed `change`. Supply any subset; an empty body is rejected. The review must still be mutable (pend
  • Edit experiment reviewEdit an in-flight experiment (A/B test) review's metadata — description and/or requested reviewers. Supply any subset; an omitted field keeps the review's current value, and an empty body is rejected.
  • Edit gate reviewEdit an in-flight gate (feature flag) review's metadata (description, requested reviewers) and/or its proposed `change`. Supply any subset; an empty body is rejected. The review must still be mutable
  • Invoke toolExecute any Statsig MCP tool by name with arguments — including tools not shown in the default tool list. Find tools with Search_Tools, get their exact input schema with Get_Tool_Schema, then execute
  • Reject autotune reviewReject an in-flight review of an autotune experiment. Rejection is terminal — the proposed change is not applied and the review cannot be reopened (create a new review to retry). A `reason` is require
  • Reject dynamic config reviewReject an in-flight review of a dynamic config. Rejection is terminal — the proposed change is not applied and the review cannot be reopened (create a new review to retry). A `reason` is required. The
  • Reject experiment reviewReject an in-flight review of an experiment (A/B test). Rejection is terminal — the proposed change is not applied and the review cannot be reopened (create a new review to retry). A `reason` is requi
  • Reject gate reviewReject an in-flight review of a gate (feature flag). Rejection is terminal — the proposed change is not applied and the review cannot be reopened (create a new review to retry). A `reason` is required
  • Start experiment code cleanupStart code cleanup for a stale experiment by name, which creates a PR to remove the experiment from your codebase.
  • Start gate code cleanupStart code cleanup for a gate by name, which creates a PR to remove the gate from your codebase.
  • Start prompt version evalsStart an offline evaluation job for a specific Prompt Version, identified by the Prompt id and the versionId.
  • Update 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. Use the GET option to gather the attributes of
  • Update experiment entirelyFully update an experiment, replacing everything the experiment currently has on the Statsig console with the data included in this POST request. Use the GET option to gather the attributes of the exp
  • Update gate entirelyFully update a gate, replacing everything the gate currently has on the Statsig console with the data included in this POST request. Use the GET option to gather the attributes of the gate, edit them,
  • Update layer entirelyFully update a layer, replacing everything the layer currently has on the Statsig console with the data included in this POST request. Use the GET option to gather the attributes of the layer, edit th
  • Update param storeUpdate an existing Param Store by name. Set its description and/or its parameters. Each parameter is typed (string/boolean/number/object/array) and is either a static value or a reference to a gate, l
  • Update promptPartially update a Prompt by ID. Only the fields you include are changed. Supports updating description, targetApps, team, and teamID.
  • Update segmentUpdate a Statsig segment using the appropriate segment endpoint. Supports rule-based rule updates and add operations for ID list / user store ID list segments via params.query_operation.

Changes wait in Needs you

Changes and sends in Statsig MCP are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

How approvals work

Statsig MCP questions

Can an agent change data in Statsig MCP on its own?

Not by default. Changes and sends in Statsig MCP are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

What can an agent read in Statsig MCP?

This connector lists 47 read actions. Reads run at once, without waiting for approval.

How does Statsig MCP connect?

It connects with dcr oauth. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.

Bring Statsig MCP to your agents.

Book a discovery call