Merge Unified's Statsig integration Merge Agent Handler's Statsig MCP server

Connect your AI Agents to Statsig in minutes

Merge lets you securely connect your agents to Statsig and thousands of tools instantly

Start building for free

Read docs

Statsig

Learn more about Merge Agent Handler

Available tools

list_audit_logs

List Statsig audit log entries, optionally filtered by action type, tags, date/time range, and sorted by a given field. Use for reviewing recent changes to gates, configs, experiments, and other resources.

get_company

Get information about the Statsig company/organization associated with the current API key.

get_project

Get information about the current Statsig project associated with the API key.

list_dynamic_configs

List Statsig dynamic configs with optional filtering by target app, team, or tags. Use listtargetapps/listteams/listtags to find valid filter values.

get_dynamic_config

Get full details for a Statsig dynamic config by ID, including rules and default value. Use listdynamicconfigs to find valid IDs.

create_dynamic_config

Create a Statsig dynamic config. Requires a unique name. Use listtargetapps/listtags/listteams/listunitid_types to find valid targetApps/tags/teamID/idType values to include.

update_dynamic_config

Partially update a Statsig dynamic config's name, description, rules, default value, tags, target apps, or team. Use listdynamicconfigs to find valid IDs.

delete_dynamic_config

Permanently delete a Statsig dynamic config by ID. This cannot be undone. Use listdynamicconfigs to find valid IDs.

enable_dynamic_config

Enable a Statsig dynamic config so its rules are evaluated. Use listdynamicconfigs to find valid IDs.

disable_dynamic_config

Disable a Statsig dynamic config so it always returns its default value. Use listdynamicconfigs to find valid IDs.

archive_dynamic_config

Archive a Statsig dynamic config, removing it from active use. Use listdynamicconfigs to find valid IDs.

list_environments

List the environments configured for this Statsig project (e.g. development, staging, production). Use this to find valid environment names for gate overrides and key configuration.

list_experiments

List Statsig experiments with optional filtering by status, target app, team, or tags. Returns a lean field set (id, name, status, hypothesis) by default; pass fields to widen. Use listtargetapps/listteams/listtags to find valid filter values.

get_experiment

Get full details for a Statsig experiment by ID, including groups and metrics. Use list_experiments to find valid IDs.

create_experiment

Create a Statsig experiment. Requires a unique name. Use listmetrics/listtargetapps/listtags/listteams/listunitidtypes to find valid primaryMetrics/secondaryMetrics/targetApps/tags/teamID/idType values.

update_experiment

Partially update a Statsig experiment's name, description, hypothesis, groups, metrics, tags, or team. Use list_experiments to find valid IDs.

delete_experiment

Permanently delete a Statsig experiment by ID. This cannot be undone. Use list_experiments to find valid IDs.

list_gates

List Statsig feature gates with optional filtering by unit ID type, target app, team, tags, gate type, or creator. Use listtargetapps/listteams/listtags to find valid filter values.

get_gate

Get full details for a Statsig feature gate by ID, including targeting rules and status. Use list_gates to find valid gate IDs.

create_gate

Create a Statsig feature gate. Requires a unique name. Use listtargetapps/listtags/listteams/listunitid_types to find valid targetApps/tags/teamID/idType values to include.

update_gate

Partially update a Statsig feature gate's name, description, rules, tags, target apps, or team. Use list_gates to find valid gate IDs.

delete_gate

Permanently delete a Statsig feature gate by ID. This cannot be undone. Use list_gates to find valid gate IDs.

enable_gate

Enable a Statsig feature gate so its rules are evaluated. Use list_gates to find valid gate IDs.

disable_gate

Disable a Statsig feature gate so it always evaluates to false. Use list_gates to find valid gate IDs.

archive_gate

Archive a Statsig feature gate, removing it from active use. Use list_gates to find valid gate IDs.

get_gate_overrides

Get the per-environment ID overrides configured for a Statsig feature gate. Use list_gates to find valid gate IDs.

update_gate_overrides

Add per-environment ID overrides to a Statsig feature gate (e.g. force a specific user ID to pass or fail in staging). Existing overrides on the gate are preserved; the entries supplied here are added alongside them. Use list_gates to find valid gate IDs.

list_holdouts

List Statsig holdouts (groups of users excluded from experimentation) with optional tag filtering. Use list_tags to find valid tag names.

get_holdout

Get full details for a Statsig holdout by ID. Use list_holdouts to find valid IDs.

create_holdout

Create a Statsig holdout. Requires a unique name. Use listunitidtypes/listteams to find valid idType/teamID values.

update_holdout

Partially update a Statsig holdout's description. Use list_holdouts to find valid IDs.

delete_holdout

Permanently delete a Statsig holdout by ID. This cannot be undone. Use list_holdouts to find valid IDs.

list_keys

List Statsig Console/Server/Client API keys with optional filtering by target app or environment. Use listtargetapps to find valid target app IDs. By default the secret key value is masked (e.g. console-ab12) to avoid exposing live credentials in bulk. Set reveal_secret=true only if you need the full usable secret value — treat that response as sensitive credential material.

get_key

Get details for a Statsig API key by its key value. Use listkeys with revealsecret=true to find a usable key value — the masked value list_keys returns by default (e.g. console-ab12) will not resolve here. Returns the full, usable secret value — treat the response as sensitive credential material.

create_key

Create a new Statsig API key. Requires a description and type (SERVER, CLIENT, CONSOLE, SCIM, or ORG). Use listtargetapps to find valid targetAppID values.

deactivate_key

Deactivate a Statsig API key so it can no longer authenticate requests. Use listkeys with revealsecret=true to find a usable key value — the masked value list_keys returns by default (e.g. console-ab12) will not resolve here. Response echoes back the full secret key value — treat it as sensitive credential material.

list_layers

List Statsig layers (containers that group mutually-exclusive experiments).

get_layer

Get full details for a Statsig layer by ID. Use list_layers to find valid IDs.

create_layer

Create a Statsig layer. Requires a unique name and idType. Use listunitidtypes/listtarget_apps to find valid idType/targetApps values.

update_layer

Partially update a Statsig layer's description or target apps. Use list_layers to find valid IDs.

delete_layer

Permanently delete a Statsig layer by ID. This cannot be undone. Use list_layers to find valid IDs.

list_metrics

List Statsig metrics with optional tag filtering. Use listtags to find valid tag names. Use this, not getmetric, to browse or find metric names/IDs for experiments.

get_metric

Get the full definition for a Statsig metric by ID. Use list_metrics to find valid IDs.

create_metric

Create a Statsig metric. Requires a unique name, type ('ratio', 'mean', 'eventcountcustom', 'eventuser', 'funnel', 'composite', 'compositesum', 'sum', 'userwarehouse', 'percentile', or 'latestvalue'), and unitTypes. Also requires metricEvents for event-based types. Use listunitidtypes/listtags/list_teams to find valid unitTypes/tags/teamID values.

update_metric

Update a Statsig metric's description, directionality, tags, or team. Use list_metrics to find valid IDs.

delete_metric

Permanently delete a Statsig metric by ID. This cannot be undone. Use list_metrics to find valid IDs.

list_segments

List Statsig segments (reusable named user groups referenced by gates, configs, and experiments).

get_segment

Get full details for a Statsig segment by ID. Use list_segments to find valid IDs.

create_segment

Create a Statsig segment. Requires a unique name and type ('idlist' or 'rulebased'). Use listunitidtypes/listtags/list_teams to find valid idType/tags/teamID values.

delete_segment

Permanently delete a Statsig segment by ID. This cannot be undone. Use list_segments to find valid IDs.

list_segment_ids

List the IDs currently in a static (idlist-type) Statsig segment. Use listsegments to find valid IDs.

add_segment_ids

Add IDs to a static (idlist-type) Statsig segment (max 100000 per call). Returns the segment's first page of IDs post-add (up to 100) plus the true total in count/pageinfo; use listsegmentids with a page number to see the rest for segments over 100 IDs. Use list_segments to find valid IDs.

list_tags

List Statsig tags. Use this to find valid tag names/IDs to reference when creating or filtering gates, dynamic configs, experiments, holdouts, and metrics.

get_tag

Get details for a Statsig tag by its name. Use list_tags to find valid tag names.

create_tag

Create a Statsig tag. Requires a unique name and description.

list_target_apps

List Statsig target apps. Use this to find valid target app IDs to reference when creating or filtering gates, dynamic configs, experiments, layers, and keys. The id field may be null per Statsig's schema — fall back to name (always present) if so. Target Apps is an Enterprise-only Statsig feature — this returns an empty list on Developer/Pro plans.

get_target_app

Get details for a Statsig target app by name. Use listtargetapps to find valid names. Target Apps is an Enterprise-only Statsig feature.

create_target_app

Create a Statsig target app. Requires a unique name and description. Target Apps is an Enterprise-only Statsig feature — this fails on Developer/Pro plans.

list_unit_id_types

List Statsig unit ID types (e.g. userID, stableID). Use this to find valid idType values to reference when creating gates, dynamic configs, experiments, layers, holdouts, and segments.

get_unit_id_type

Get details for a Statsig unit ID type by name. Use listunitid_types to find valid names.

create_unit_id_type

Create a Statsig unit ID type. Requires a unique name (e.g. 'userID', 'orgID').

list_users

List members of this Statsig project.

get_user

Get details for a Statsig project member by user ID. Use list_users to find valid IDs.

list_teams

List teams configured in this Statsig project. Use this to find valid team names to reference when creating or filtering gates, dynamic configs, experiments, holdouts, and segments. Teams is an Enterprise-only Statsig feature — this fails on Developer/Pro plans.

get_team

Get details for a Statsig team by name. Use list_teams to find valid team names. Teams is an Enterprise-only Statsig feature.

validate_credential

Validate Statsig Console API key by fetching company info. Returns success status and the connected company's name.

View all tools by creating a free account See more tools

How to set up Merge Agent Handler

In an mcp.json file, add the configuration below, and restart Cursor.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11

Copy Code

Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.

Make sure Claude is using the Node v20+.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "command": "npx",
5      "args": [
6        "-y",
7        "mcp-remote@latest",
8        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9        "--header",
10        "Authorization: Bearer ${AUTH_TOKEN}"
11      ],
12      "env": {
13        "AUTH_TOKEN": "yMt*****"
14      }
15    }
16  }
17}

Copy Code

Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.

Learn more in the official documentation ↗

1{
2    "mcpServers": {
3      "agent-handler": {
4        "command": "npx",
5        "args": [
6          "-y",
7          "mcp-remote@latest",
8          "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9          "--header",
10          "Authorization: Bearer ${AUTH_TOKEN}"
11        ],
12        "env": {
13          "AUTH_TOKEN": "<ah-production-access-key>"
14        }
15      }
16    }
17  }

Copy Code

In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".

You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.

Learn more in the official documentation ↗

1{
2  "inputs": [
3    {
4      "type": "promptString",
5      "id": "agent-handler-auth",
6      "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7      "password": true
8    }
9  ],
10  "servers": {
11    "agent-handler": {
12      "type": "stdio",
13      "command": "npx",
14      "args": [
15        "-y",
16        "mcp-remote@latest",
17        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18        "--header",
19        "Authorization: Bearer ${input:agent-handler-auth}"
20      ]
21    }
22  }
23}

Copy Code

FAQs on using Merge's Statsig MCP server

What is a Statsig MCP?

It's an MCP server that lets your agents access data and functionality from Statsig via tools. Your agents can invoke these tools to check a feature gate's rollout status, create or update an experiment, pull event metrics, and review a dynamic config.

Statsig offers an official MCP server, but you can also use one from a third-party platform, like Merge Agent Handler.

How can I use the Statsig MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

Feature gate rollout monitoring: an agent checks a gate's rollout percentage on a schedule and posts to Slack when it crosses a defined threshold, so the team doesn't have to babysit a gradual rollout manually

Experiment result summaries: when an experiment reaches statistical significance, an agent pulls the results and writes a summary of the winning variant and lift into a shared doc for stakeholders

Gradual rollout automation: an agent increases a feature gate's rollout percentage in fixed increments on a set schedule, pausing automatically if error rates spike

Incident-triggered rollback: when a monitoring tool fires an incident alert tied to a recent release, an agent disables the associated feature gate immediately and notifies the on-call engineer

What are popular tools for Statsig's MCP server?

Here are some of the most commonly used tools:

list_feature_gates: returns every feature gate in a project along with its current rollout status. Useful for agents that need to audit which gates are live before making rollout changes

get_feature_gate: returns the configuration and targeting rules for a single feature gate. Use this when an agent needs to check a specific gate's rollout percentage or targeting conditions before acting on it

update_feature_gate: changes a feature gate's rollout percentage, targeting rules, or enabled status. Call this when an agent is automating a gradual rollout or rolling back a flag during an incident

list_experiments: returns active and completed experiments in a project. Good for workflows that need to check which experiments are running before summarizing results

get_experiment_results: returns the metrics, variants, and statistical significance for a given experiment. Helpful when an agent needs to summarize a test's outcome for stakeholders

list_dynamic_configs: returns the dynamic configs in a project along with their current values. Useful for agents that need to check a config's current state before recommending or making a change

What makes Merge Agent Handler's Statsig MCP server better than alternative Statsig MCP servers?

A few things set it apart from a self-hosted or DIY Statsig MCP setup:

Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Statsig, this means you can prevent experiment result data, targeting rules tied to specific user segments, or API secret keys from being exposed even when the agent has broad read access

Managed authentication and credentials: Merge stores and refreshes Statsig credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or manage token rotation manually

Real-time observability and audit trail: Every tool call made against Statsig is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly what an agent read or wrote without instrumenting anything yourself

Tool Packs and controlled access: Tool Packs let you bundle specific Statsig tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's Statsig MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account.

2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.

3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.

4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Statsig and complete the auth flow. Merge stores and manages the credentials going forward.

5. Open a Claude Code session and start querying Statsig data directly. The first time you use a Statsig tool, a Magic Link may appear to complete connector authentication.

If you want to connect Merge Agent Handler's Statsig MCP with internal or customer-facing agentic products, you can follow the steps in our docs.

Can employees use Merge to connect their AI tools to Statsig?

Yes, Merge for Workforce lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, Codex, and other MCP-compatible AI tools to Statsig without bypassing IT governance.

Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Merge and gets individual credentials tied to their identity. A product manager can ask their AI to check a feature gate's rollout percentage, pull an experiment's results, or review which users are in a target audience, all within IT-defined permissions.

IT also provisions access by role or group via SCIM. A product manager, for example, might get Statsig access to check feature gate rollout status, Amplitude access to pull usage trends, and Notion access to document experiment findings, while a growth engineer gets Statsig access to create and update experiments, GitHub access to review flag implementation code, and Slack access to post rollout updates.

Every tool call an employee's AI makes to Statsig is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.