Is this Split flag killed in production, and what does it serve?
Split, now Harness FME, runs your feature flags. Memtro reads projects and environments, the flags in each project with tags, traffic type and rollout status, and for one environment whether each flag is killed, its treatments, default treatment, traffic allocation and last traffic. It reads segments and how many keys each holds, never their members. When asked, and once an administrator has granted them by name, it can kill or restore a flag, which changes what live users get at once, create flags and segments, add keys to a segment, submit or approve change requests, and permanently delete a flag.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Split tool, reads what it needs, and answers with the source cited.
These tools change something in Split. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Once Split is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Split + MemtroIs paywall_beta killed in production?
Which flags in the checkout project are tagged experiment?
How many accounts are in the beta_testers segment in Production?
Kill paywall_beta in Production.
Add accounts 4417 and 5120 to the beta_testers segment in Staging.
Priya Sharma, on-call engineer at BigCo, asked during an incident whether paywall_beta was killed in production. Memtro read the flag definitions for Production and showed it killed, serving its default treatment, with the last change twenty minutes earlier.
Dan Fletcher, engineering lead at Northwind, asked Memtro to kill new_checkout in Production after error rates climbed. Memtro killed the flag, so every SDK served its default treatment to all users at once, and Split recorded the kill in its audit log. Once the fix shipped he asked Memtro to restore it.
The teams that lean on Split most, a question each of them asks, and what they connect beside it.
A record in Split is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
UptimeRobot
Honeycomb
Cronitor
FireHydrant
StatusCake
GlitchTip
GLPI
Langfuse
LibreNMS
NetBox
Snipe-IT
Woodpecker CI
Zabbix
LangSmith
Helicone
GrowthBook
Drata
Intruder
GitGuardian
Secureframe
ilert
JumpCloud
ConfigCat
Aikido Security
Astronomer
Comet Opik
CrowdStrike Falcon
Detectify
Domotz
LambdaTest
LangWatch
LlamaCloud
Logz.io
Lunary
NinjaOne
Northflank
Portkey
PromptLayer
PRTG Network Monitor
Raygun
Retell AI
Runpod
Shodan
Spike.sh
Squadcast
Tenable
UpGuard
Uptime.com
Vanta
Zenduty
Cortex
WorkOS
Kandji
Automox
Huntress
SimpleMDM
Healthchecks.io
Rapid7 InsightVM
ZenhubIn Split, open Admin settings → API keys and create an API key of type Admin. A Harness personal access token or service account token also works.
Give it viewer roles for feature flags and segments, plus a workspace-admin role if Memtro should list projects and environments. Viewer roles keep Memtro to reading, so add the access for any actions an administrator will grant. Copy it now, as Split does not show it again.
In Memtro, open Connections → Split and paste it as Admin API key.
Ask: is paywall_beta killed in production?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Split tools are the same everywhere.
Only when you ask, and only what it has been granted: kill a feature flag in one environment, so every user gets its default treatment; restore a killed feature flag in one environment; create a feature flag for a traffic type; change a flag's description, add a tag or set its rollout status; delete a feature flag permanently from every environment; submit a change request to kill or restore a flag, notifying the named approvers; approve, reject or withdraw a change request; add keys (users, accounts) to a segment in one environment; create a segment for a traffic type. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
Admin API key. In Split, open Admin settings → API keys and create an API key of type Admin. A Harness personal access token or service account token also works.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time
