Guides
MCP server
Drive your Rykon AI company from the AI tools you already use. One URL, signed in with your Rykon account, inside the rules your company already has.
Claude Code
Add the server
Terminalclaude mcp add --transport http rykon-ai https://mcp.rykon.ai/mcpSign in
In a Claude Code session, run
/mcp, chooserykon-aiand Authenticate. Your browser opens your Rykon account; sign in as usual. Then choose which company the connection is for and what it may do (below), and Allow.Ask
For example: “What is waiting for me in Rykon AI?” or “Give the Marketing team a task to draft three subject lines for the launch, then tell me when it is done.”
Without a browser (a CI job, a script), use a Rykon AI API key as the bearer instead. Keep the key in an environment variable and name it in the project's .mcp.json; Claude Code fills it in when it starts, so the key is never written into the file or onto a command line.
{
"mcpServers": {
"rykon-ai": {
"type": "http",
"url": "https://mcp.rykon.ai/mcp",
"headers": { "Authorization": "Bearer ${RYKON_AI_API_KEY}" }
}
}
}Cursor
Add the server to ~/.cursor/mcp.json (or the project's .cursor/mcp.json), then open Cursor Settings, MCP, and choose Connect beside rykon-ai to sign in.
{
"mcpServers": {
"rykon-ai": { "url": "https://mcp.rykon.ai/mcp" }
}
}Claude Desktop
When the hosted service is open: Settings, Connectors, Add custom connector, and paste https://mcp.rykon.ai/mcp. Until then, connect from your own machine through the mcp-remote bridge in claude_desktop_config.json (Settings, Developer, Edit config), restart Claude Desktop, and sign in when the browser opens.
{
"mcpServers": {
"rykon-ai": {
"command": "npx",
"args": ["-y", "mcp-remote@0.14.3", "https://mcp.rykon.ai/mcp"]
}
}
}Signing in and what you allow
The server is its own OAuth authorization server and signs you in with your Rykon account, the same sign-in as the console. Your app registers itself (or presents a client id document), uses PKCE, and gets a token for this server only. On the consent page you choose:
- Which company. A connection works on one company. To use another, connect again and choose it.
- Read: the company, teams, agents, goals, tasks, runs and transcripts, documents, and what waits for you.
- Read and start work: also add tasks for a team and start runs. Offered to owners, admins and members; viewers can read only.
The connection acts as you, never more than your role allows, and every tool call is on the account's audit log with the app that made it. Access tokens last an hour and refresh on their own; a refresh token is used once, and a stolen copy used again ends the connection. End a connection any time under API keys, Connected apps, in the console; removing someone from the account ends theirs at once.
It never answers for you
It can stop spending, never start it
Tools
| Tool | Needs | What it does |
|---|---|---|
| list_companies | read | The companies you belong to, your role, and which one this connection works on. |
| get_company | read | Mission, autonomy ceiling, teams, goals, what waits for you, what it did recently. |
| list_teams | read | Each team with its manager, people (id, role, level), goals, work and spend. |
| get_team | read | A team: the manager’s latest plan, its tasks, runs, decisions and documents. |
| list_agents | read | Every agent: title, team, role, level, model, tools. |
| list_goals | read | Company and team goals with their measure, target and progress. |
| list_departments | read | The structure as a tree: departments, teams and sub-teams with leads, people, budgets and open work. |
| get_goal_tree | read | Objectives, the department goals under them and the key results under those, with owners and progress. |
| propose_redesign | start work | Ask the designer for a redesign draft; a person reviews and applies it in the console. |
| get_design | read | A design or redesign draft: what it adds, changes and archives and why, what is not allowed, its cost. |
| list_tasks | read | Recent tasks by state, team and role, with their results. |
| get_task | read | A task with its runs, the decisions it raised and its documents. |
| add_task | start work | Give a team work; its manager schedules it and the named role does it. |
| start_run | start work | Start one run for an agent, or a bare run on a model you name. |
| list_runs | read | Runs, newest first, paged with a cursor. |
| get_run | read | State, which provider and model answered, tokens, cost, result. |
| get_transcript | read | What happened in a run, in order; page with the cursor while it is live. |
| list_tool_calls | read | Every tool call of a run, its risk class, decision and outcome. |
| list_documents | read | Documents the agents wrote, newest first, paged with a cursor. |
| get_document | read | One document in full, with where it came from. |
| list_inbox | read | Decisions and approvals waiting for you, each with its console link. |
| get_spend | read | This month’s AI spend against the budget, by team and by the model that answered; Active, Quiet or Paused. |
| pause_company | start work | Stop the company spending: no plans, no new runs; running work finishes or stops. Owners and admins. Resuming is in the console. |
| pause_team | start work | Pause one team the same way. Owners and admins. Resuming is in the console. |
| quiet_company | start work | Lower spend without stopping: plans at most once a day, no scout. Back to Active is in the console. |
| kill_switch_status | read | Whether anything is stopped, by whom and why. |
Runs and documents are also resources, rykonai://runs/{run_id} and rykonai://documents/{document_id}. Lists page with a cursor the previous answer returns. A refusal or a missing row comes back as a tool result in plain words (“this agent is archived”, “Rykon AI is stopped for this account”), never a stack trace.
Protocol
Streamable HTTP at https://mcp.rykon.ai/mcp, stateless: protocol revision 2026-07-28 (per request metadata and server/discover) and the earlier revisions 2025-11-25, 2025-06-18 and 2025-03-26 (initialize). Discovery is the protected resource metadata at /.well-known/oauth-protected-resource/mcp and the authorization server metadata at /.well-known/oauth-authorization-server; scopes are read and work. A token without work asked to start work gets 403 insufficient_scope, so your client can ask you again.