ABsmartly MCP Server
A Model Context Protocol server that provides full access to the ABsmartly experimentation platform through the CLI core library — 230+ commands across 33 groups including experiment lifecycle, metrics, goals, teams, and more.
Potencia tu agente
El comando propio del publicador. No es un endpoint de PlugMCP.
Host a copy with our keys and logs.
npx -y @absmartly/[email protected]Claude Code no tiene enlace de instalación para un comando local. Copia el comando de abajo y ejecútalo en una terminal.
claude mcp add absmartly-mcp -- npx -y @absmartly/mcp@2.1.0Ejecútalo en una terminal.
{ "mcpServers": { "absmartly-mcp": { "command": "npx", "args": [ "-y", "@absmartly/[email protected]" ] } }}claude_desktop_config.json
¿URL remota o un comando en tu máquina? En qué se diferencian las dos instalaciones
Ejecutar en PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirDel publicador
A Model Context Protocol server that provides full access to the ABsmartly experimentation platform through the CLI core library — 230+ commands across 33 groups including experiment lifecycle, metrics, goals, teams, and more.
MCP server for ABsmartly — experimentation platform API access for AI assistants
Download and double-click the file to install. For other clients (Cursor, VS Code, Windsurf, ChatGPT, Claude Code), see Setup below.
The server exposes 4 tools that give AI assistants access to the full ABsmartly CLI:
"What experiments are running?"
→ discover_commands(group: "experiments")
→ execute_command(group: "experiments", command: "listExperiments", params: {state: "running"})
The MCP server supports two authentication methods:
Open Settings → Connectors, scroll to the bottom, and click Add custom connector:

In the dialog, give the connector a Name (e.g. "ABsmartly") and paste the URL into Remote MCP server URL:

URL:
https://mcp.absmartly.com/sse?absmartly-endpoint=https://your-instance.absmartly.com
Click Add, then Connect. Claude Desktop will open your browser for ABsmartly login (SAML/credentials). After authentication, the MCP connection is established automatically.
The
absmartly-endpointquery parameter is optional. If omitted, the OAuth flow will prompt you to enter the URL of your ABsmartly instance in the browser before login:
Pass the API key directly in the URL — no mcp-remote bridge needed:
URL:
https://mcp.absmartly.com/sse?api_key=YOUR_API_KEY&absmartly-endpoint=https://your-instance.absmartly.com
If you'd rather pass the key via headers instead of the URL, use the mcp-remote bridge — Claude Desktop doesn't support custom headers natively for remote servers:
~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"absmartly": {
"command": "npx",
"args": [
"mcp-remote@latest",
"https://mcp.absmartly.com/sse",
"--header", "Authorization:YOUR_API_KEY",
"--header", "x-absmartly-endpoint:https://your-instance.absmartly.com"
]
}
}
}
Uses your ABsmartly CLI config and macOS Keychain credentials:
{
"mcpServers": {
"absmartly": {
"command": "npx",
"args": ["@absmartly/mcp", "--profile=production"]
}
}
}
claude mcp add --transport sse --scope user absmartly \
https://mcp.absmartly.com/sse \
-H "Authorization:YOUR_API_KEY" \
-H "x-absmartly-endpoint:https://your-instance.absmartly.com"
Subdomain shorthand — auto-constructs https://<subdomain>.absmartly.com/v1:
claude mcp add --transport sse --scope user absmartly \
https://mcp.absmartly.com/sse \
-H "Authorization:my-subdomain YOUR_API_KEY"
claude mcp add --transport http --scope user absmartly \
https://mcp.absmartly.com/mcp \
-H "Authorization:YOUR_API_KEY" \
-H "x-absmartly-endpoint:https://your-instance.absmartly.com"
Streamable HTTP is the modern MCP transport (the MCP spec deprecated SSE in March 2025). The
/sseURL still works for older clients.
claude mcp add --transport sse --scope user absmartly \
"https://mcp.absmartly.com/sse?absmartly-endpoint=https://your-instance.absmartly.com"
Then run /mcp in Claude Code to authenticate when prompted. The absmartly-endpoint query parameter is optional — omit it and the OAuth flow will prompt you for the instance URL in the browser.
claude mcp add --scope user absmartly -- npx @absmartly/mcp --profile=production
.mcp.json){
"mcpServers": {
"absmartly": {
"type": "sse",
"url": "https://mcp.absmartly.com/sse",
"headers": {
"Authorization": "YOUR_API_KEY",
"x-absmartly-endpoint": "https://your-instance.absmartly.com"
}
}
}
}
Use --scope project instead of --scope user to write to .mcp.json (shared via VCS).
Click the badge above to install with one click (OAuth). After Cursor prompts you for the ABsmartly instance URL in the browser, the flow completes automatically. Or configure manually:
.cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"absmartly": {
"url": "https://mcp.absmartly.com/sse",
"headers": {
"Authorization": "YOUR_API_KEY",
"x-absmartly-endpoint": "https://your-instance.absmartly.com"
}
}
}
}
Or with Streamable HTTP transport (modern, recommended):
{
"mcpServers": {
"absmartly": {
"type": "http",
"url": "https://mcp.absmartly.com/mcp",
"headers": {
"Authorization": "YOUR_API_KEY",
"x-absmartly-endpoint": "https://your-instance.absmartly.com"
}
}
}
}
{
"mcpServers": {
"absmartly": {
"url": "https://mcp.absmartly.com/sse?absmartly-endpoint=https://your-instance.absmartly.com"
}
}
}
Cursor will detect the OAuth requirement and open your browser for login. The absmartly-endpoint query parameter is optional — omit it and the OAuth flow will prompt for the instance URL.
{
"mcpServers": {
"absmartly": {
"command": "npx",
"args": ["@absmartly/mcp", "--profile=production"]
}
}
}
~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"absmartly": {
"serverUrl": "https://mcp.absmartly.com/sse",
"headers": {
"Authorization": "YOUR_API_KEY",
"x-absmartly-endpoint": "https://your-instance.absmartly.com"
}
}
}
}
Note: Windsurf uses
"serverUrl"instead of"url".
Or with Streamable HTTP transport:
{
"mcpServers": {
"absmartly": {
"serverUrl": "https://mcp.absmartly.com/mcp",
"headers": {
"Authorization": "YOUR_API_KEY",
"x-absmartly-endpoint": "https://your-instance.absmartly.com"
}
}
}
}
{
"mcpServers": {
"absmartly": {
"serverUrl": "https://mcp.absmartly.com/sse?absmartly-endpoint=https://your-instance.absmartly.com"
}
}
}
{
"mcpServers": {
"absmartly": {
"command": "npx",
"args": ["@absmartly/mcp", "--profile=production"]
}
}
}
Click a badge above for one-click install (OAuth). You'll be prompted for your ABsmartly instance URL in the browser. Or configure manually:
.vscode/mcp.json (workspace) or via Command Palette → MCP: Open User Configuration:
Note: VS Code uses
"servers"as root key, not"mcpServers".
{
"servers": {
"absmartly": {
"type": "sse",
"url": "https://mcp.absmartly.com/sse",
"headers": {
"Authorization": "${input:absmartly-api-key}",
"x-absmartly-endpoint": "https://your-instance.absmartly.com"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "absmartly-api-key",
"description": "ABsmartly API Key",
"password": true
}
]
}
Or with Streamable HTTP transport (recommended):
{
"servers": {
"absmartly": {
"type": "http",
"url": "https://mcp.absmartly.com/mcp",
"headers": {
"Authorization": "${input:absmartly-api-key}",
"x-absmartly-endpoint": "https://your-instance.absmartly.com"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "absmartly-api-key",
"description": "ABsmartly API Key",
"password": true
}
]
}
{
"servers": {
"absmartly": {
"type": "sse",
"url": "https://mcp.absmartly.com/sse?absmartly-endpoint=https://your-instance.absmartly.com"
}
}
}
VS Code will detect the OAuth requirement and show an Auth CodeLens to trigger the flow. The absmartly-endpoint query parameter is optional — omit it and the OAuth flow will prompt for the instance URL.
{
"servers": {
"absmartly": {
"command": "npx",
"args": ["@absmartly/mcp", "--profile=production"]
}
}
}
MCP tools only appear in Agent mode in VS Code, not in Ask or Edit mode.
Works for Gemini CLI (terminal) and Gemini Code Assist (VS Code / JetBrains / Android Studio agent mode). Both read ~/.gemini/settings.json (user-wide) or .gemini/settings.json (per-project). JetBrains IDEs use mcp.json instead.
{
"mcpServers": {
"absmartly": {
"url": "https://mcp.absmartly.com/sse?absmartly-endpoint=https://your-instance.absmartly.com"
}
}
}
Gemini auto-discovers the OAuth requirement. In Gemini CLI, run /mcp auth absmartly when prompted; in Code Assist agent mode the browser opens automatically.
{
"mcpServers": {
"absmartly": {
"url": "https://mcp.absmartly.com/sse",
"headers": {
"Authorization": "YOUR_API_KEY",
"x-absmartly-endpoint": "https://your-instance.absmartly.com"
}
}
}
}
gemini mcp add --transport sse --scope user absmartly \
https://mcp.absmartly.com/sse \
-H "Authorization: YOUR_API_KEY" \
-H "x-absmartly-endpoint: https://your-instance.absmartly.com"
Gemini Enterprise's Custom MCP Server connector (Preview) requires Streamable HTTP transport — use the /mcp endpoint:
https://mcp.absmartly.com/mcpclient_id / client_secret. Grant the mcp:access scope.SSE transport (
/sse) is not supported by this connector. The legacy Gemini CLI / Code Assist sections above continue to use/sseuntil those clients add Streamable HTTP support.Reload the IDE window after editing settings (VS Code: Command Palette → Developer: Reload Window). MCP support in Code Assist requires agent preview mode — set
"geminicodeassist.updateChannel": "Insiders"in VS Code settings if not already enabled.
ChatGPT does not support one-click install deeplinks — you connect remote MCP servers via the Custom Connectors UI. Requires a Pro, Team, Enterprise, or Edu plan, and Developer Mode enabled (Settings → Connectors → Advanced → Developer mode).
ABsmartlyhttps://mcp.absmartly.com/sse?absmartly-endpoint=https://your-instance.absmartly.comWorkspace admins must first enable Custom MCP connectors in Workspace Settings → Permissions & Roles → Connected Data.
When using API key authentication, these header formats are all supported:
The subdomain shorthand auto-constructs the endpoint as https://<subdomain>.absmartly.com/v1.
Discover what's available:
What ABsmartly operations can you help me with?
List running experiments:
Show me all running experiments
Create an experiment from a template:
Create a new A/B test called "checkout_cta_test" with Control and Blue Button variants
Full lifecycle:
Create an experiment, move it to ready, start it, then show me its details
Feature flags:
Create a feature flag called "dark_mode" and start it
Clone and modify:
Clone experiment 42 as "checkout_v2" and update the traffic split to 70/30
Compare experiments:
Show me the differences between experiments 42 and 43
Browse available command groups or search by keyword. Call without parameters to see all groups.
{ "group": "experiments" }
{ "search": "archive" }
Get detailed documentation for a specific command including parameters, types, and examples.
{ "group": "experiments", "command": "createExperimentFromTemplate" }
Execute any ABsmartly command. Common commands are listed in the tool description; use discover_commands for the full list.
{
"group": "experiments",
"command": "listExperiments",
"params": { "state": "running", "items": 10 }
}
Parameters:
group (required) — command group (e.g. experiments, metrics, goals)command (required) — command name (e.g. listExperiments, createExperimentFromTemplate)params (optional) — command parameters as JSON objectconfirmed (optional) — set to true only after the user has explicitly confirmed the action; never set it on your own initiativeraw (optional) — return full CommandResult with rows/detail/warnings/paginationlimit (optional) — max items for list operations (default: 20)Parameter shape. Each command documents its params with get_command_docs. IDs are named after the entity (experimentId, goalId, keyId, ...), and create/update fields go in a data object using the API's field names (e.g. { "data": { "first_name": "Ada" } }). The server translates these to what each @absmartly/cli core function reads. Some notable shapes:
grant/revoke…AccessUser/Team on experiments, goals and metrics) take a role: an asset role ID or name (e.g. "Editor"). Metrics use assetRoleId.testDatasource / introspectDatasource / validateDatasourceQuery and storageconfigs.testStorageConfig take the saved config's ID. The backend uses the stored secrets, so they never pass through MCP. testDatasource also accepts unsaved edits in config.activity.listActivity and events.listEvents* take their filters as top-level params. A params object holding the same fields is still accepted but deprecated.platformconfig.get/updatePlatformConfig take configKey: the config's ID or name.Deprecated params (still accepted, not shown in docs) are kept for callers written against 2.0.x.
Destructive actions (start, stop, archive, delete) require confirmation. The server returns a confirmation prompt; only after the user has explicitly confirmed should you call again with confirmed: true to proceed.
Experiment creation from templates also requires confirmation. The first call to createExperimentFromTemplate returns a preview — the resolved API payload (with names mapped to IDs) plus any warnings — without creating the experiment. Show the preview to the user, and only after they have explicitly confirmed should you call again with confirmed: true to actually create.
The recommended way to create experiments is with markdown templates:
{
"group": "experiments",
"command": "createExperimentFromTemplate",
"params": {
"templateContent": "---\nname: my_experiment\ntype: test\npercentages: \"50/50\"\nunit_type: user_id\napplication: www\n---\n\n## Variants\n\n### variant_0\n\nname: control\nconfig: {}\n\n---\n\n### variant_1\n\nname: treatment\nconfig: {}\n"
}
}
Templates use YAML frontmatter for configuration and markdown for variants, audience, and description. Names for applications, unit types, metrics, teams, tags, and owners are automatically resolved to IDs.
Read the absmartly://docs/templates resource for complete examples including:
Plus: goaltags, metrictags, metriccategories, apikeys, permissions, assetroles, notifications, favorites, cors, updateschedules, customsections, platformconfig, activity, statistics, events, storageconfigs, actiondialogfields.
@absmartly/mcp package)The package has separate entry points, so a Node host does not install or load the Cloudflare Worker stack:
import { APIClient } from "@absmartly/cli/api-client";
import { createStreamableHttpHandler, FetchHttpClient } from "@absmartly/mcp";
const mcp = createStreamableHttpHandler(async (req) => ({
apiClient: new APIClient(new FetchHttpClient(endpoint, { authToken, authType: "jwt" })),
endpoint,
authType: "JWT",
}));
app.post("/mcp", (req, res, next) => mcp.post(req, res, req.body).catch(next));
FetchHttpClient supports authType "jwt", "api-key", and "service-key" (with impersonatedUserId). It rejects absolute URLs to other origins and does not let request headers override the credential.
Dependencies.
@absmartly/cli is a peer dependency (>=1.7.0 <2). The host's own copy is used, and NodeMcpRequestContext.apiClient is typed structurally (ApiClientLike), so an APIClient from any version in that range type-checks without a cast.hono, @cloudflare/workers-oauth-provider and agents are optional peers that only @absmartly/mcp/worker needs.hono is still installed as a dependency of @modelcontextprotocol/sdk.Migrating from 1.x. 2.0.0 is a major release because the dependency and export surface changed:
@absmartly/cli moved from dependencies to peerDependencies, so the host must install it.hono, @cloudflare/workers-oauth-provider, agents) are no longer installed with the package.main and types now point at the core entry.workers-mcp and dotenv were removed.Existing @absmartly/mcp, @absmartly/mcp/node-http and @absmartly/mcp/oauth imports keep working. They now also resolve under require.
Contract testing. endpoint-manifest.json is generated from the tool definitions and the @absmartly/cli build (npm run manifest). Its endpoints array lists { method, path } pairs, such as GET /v1/experiments/{id} and GET /auth/current-user. Parameter names are not significant. A host can assert that each pair exists in its OpenAPI spec. tools, resources and commands break the list down per tool, per resource and per execute_command command.
require() the ESM-only @absmartly/cli, which needs unflagged require(esm))git clone https://github.com/absmartly/mcp.git
cd mcp
npm install
npx wrangler dev --port 8787 # Run Worker locally
npx @absmartly/mcp # Run stdio server
npm run test:unit # Unit tests
npm run typecheck # TypeScript type checking
npm run smoke:worker # Worker starts under wrangler dev and serves /health
npm run test:e2e # Gated e2e suite: fresh Worker + test-1 API, no skips allowed
npm run verify:release # Everything above; runs automatically on npm publish
npx tsx scripts/audit-catalog-params.ts # Compare every catalog command's params with its CLI core function
tests/unit/cli-catalog-core-params.test.ts runs catalog commands through the real @absmartly/cli core over a fake HTTP client, and fails if the audit finds any catalog/core param mismatch.
test:e2e needs ABSMARTLY_API_KEY and ABSMARTLY_API_ENDPOINT (test-1)
and fails without them. See tests/README.md.
The e2e suites call the Worker through the official MCP SDK client, with no model in the loop. To run one against a Worker you started yourself:
MCP_WORKER_URL=http://127.0.0.1:8787 npx tsx tests/integration/sdk-tools.test.ts --profile test-1
GitHub Actions runs automatically:
npm publish (which runs verify:release again)npm run deploy # Deploy to Cloudflare Workers
npm run build:dxt # Build DXT extension
src/
├── core.ts # Node/core package entry (@absmartly/mcp)
├── worker.ts # Worker package entry (@absmartly/mcp/worker)
├── index.ts # Cloudflare Worker (OAuth, auth, resources, prompts)
├── node-http-server.ts # Node Streamable HTTP handler
├── local-server.ts # Standalone stdio server
├── cli-catalog.ts # 230+ commands mapped to CLI core functions
├── tools.ts # Shared MCP tool setup (4 tools)
├── fetch-adapter.ts # HTTP client bridging APIClient to fetch
├── resources.ts # MCP resources (docs + entity data)
├── absmartly-oauth-handler.ts # OAuth flow handler
├── shared.ts # Shared utilities
└── types.ts # TypeScript types
FetchHttpClient only sends requests under the configured base's /v1 (plus the root /auth/current-user paths), to the configured origin. It rejects dot segments (including %2e/%2E and multiply-encoded forms), backslashes, encoded separators (%2f, %5c) and control characters before the URL is built, so fetch never normalises a path like /v1/../auth out of the prefix. Redirects are not followed.MIT License - see LICENSE file for details.
MCP server for ABsmartly — experimentation platform API access for AI assistants
{ "mcpServers": { "absmartly-mcp": { "command": "npx", "args": [ "-y", "@absmartly/[email protected]" ] } }}Herramientas
Aún no hay lista de herramientas. Los servidores remotos la reciben tras la primera comprobación de estado.
Preguntas frecuentes
Copia en esta página la configuración stdio para Cursor, Claude Desktop, Claude Code o VS Code. Usa la instalación del publicador, no un proxy de PlugMCP.
Este registro no indica ninguna variable de entorno obligatoria.
@absmartly/mcp se ejecuta localmente por stdio.
Última comprobación: 2026-11-15. MCP server for ABsmartly — experimentation platform API access for AI assistants