Everything your agent can do on one key.
Ready-made skills your agent can run over one MCP endpoint — memory, research, writing, visuals and meetings.
Agent Memory Kit
r9-agent-memory-kitGive your agent a memory worth reading back.
Agent Memory
Recall before acting, save only what is durable, and supersede what turns out to be wrong — so the next session starts where this one ended instead of re-deriving it.
Social Graphics Kit
r9-social-graphicsOne brief in, a full set of on-brand post images out.
Creator & Social · Design & Visuals
Describe the post once and get every asset it needs — sized and restyled per platform, then published to a link your team can review.
Daily Brief
r9-daily-briefA dated, source-linked digest of what actually moved.
Research & Intelligence
Sweeps the sources that matter one at a time, drops anything outside your window, and returns three bullets per topic with a link to the primary — including the topics where nothing happened.
Deck Builder
r9-deck-builderDraft a slide deck with generated visuals, publish it as a link.
Docs & Decks · Design & Visuals
Turn an outline into a full deck: generated imagery per slide, consistent styling, and a shareable URL instead of a file attachment.
Human Voice Editor
r9-human-voice-editorTake the machine out of a draft without taking the author out with it.
Content & Writing
Cuts the words and rhythms that mark generated prose, then shows you what it cut and why — so the next draft needs less of it. Requires no tools; runs on any deployment.
Meeting Recap
r9-meeting-recapDrop in a recording; get a decisions-and-owners page.
Meetings & Voice · Docs & Decks
Transcribe the call, pull out decisions and action items, remember the running context, and publish a recap page the team can open.
Infographic Studio
r9-infographic-studioOne claim, drawn so it survives being screenshotted.
Design & Visuals
Settles the claim and every label before generating, then reads the image back to check the numbers survived — and publishes the data as text beside the graphic so the claim stays auditable.
Research Brief
r9-research-briefSearch the live web, read what it turns up, publish a cited brief.
Research & Intelligence
Sweep current sources, read the charts and screenshots they contain, and assemble a brief with citations you can hand to someone else.
Voice Loop
r9-voice-loopTalk to your agent and have it talk back.
Meetings & Voice
A full spoken round trip: it listens, answers out loud, and remembers what you covered so the next call picks up where the last one ended.
Screenshot to Spec
r9-screenshot-to-specHand it a UI screenshot; get a spec you can hand to an engineer.
Design & Visuals · Docs & Decks
Read a design or a competitor's screen, write out the components, states, and copy, and publish the spec as a page instead of a wall of chat.
Web search and artifact publishing are advertised over MCP when they are configured on the deployment — both are on for router9.com. See the MCP tool reference for the full schemas.
Set up in one minute
Paste the config into your MCP client. Router9 hosts the server — nothing to install.
https://api.router9.com/v1/mcp{
"mcpServers": {
"router9": {
"type": "http",
"url": "https://api.router9.com/v1/mcp",
"headers": {
"Authorization": "Bearer sk-r9k-..."
}
}
}
}Any client that speaks the MCP Streamable HTTP transport: point it at the URL and send your key as a Bearer token. Most clients also expand ${ROUTER9_API_KEY} from your environment, so the key never has to be committed.
Works with your harness
Router9 speaks the OpenAI API, so any agent runs on it as its model — then add the Skills over MCP (or call the REST endpoints directly). Pick yours for a setup guide.
Coding agents
Agents & CLIs
MCP tools = Skills exposed as native agent tools · REST endpoints = call them directly. Claude Code connects for the tools over MCP and keeps its own model provider. Using something else? See all integrations.