Rize MCP Server
Your Rize workspace, available to any AI assistant that speaks MCP
The Rize MCP server connects Claude, ChatGPT, Codex, Cursor, and other AI assistants to your Rize workspace. Read tracked time and live dashboards, start focus sessions, review AI suggestions, manage clients and projects, prepare invoices, and configure reports and routines. Every action uses your Rize account and permissions.
Quickstart
Add the connector
In Claude Desktop or claude.ai: Customize → Connectors → Add custom connector. Paste https://mcp.rize.io/mcp as the URL. Other clients take the same URL — see Setup per client below.
Authorize
Your client opens a browser to sign in to Rize with Google or an emailed sign-in code, then shows a consent screen naming the client and the redirect URL it will send you back to. Approve it.
Orient the assistant
Ask it to call get_current_user, then get_help. These return your timezone, workspace, role, and tool guidance. Ask for get_setup_checklist if you want to check which parts of your workspace still need setup.
Try a prompt
"How much time did I track today?" or "Show me my pending time entry suggestions and approve the ones tagged to Acme."
What you can do
| Workflow | Tools to start with |
|---|---|
| Read time totals by client, project, task, or label | get_my_time_allocation; use list_my_time_entries for individual entries. |
| Start or stop a focus, meeting, or break timer | get_current_session, start_session, stop_session. |
| Review, split, merge, or retag time entries | approve_time_entries, split_time_entry, merge_time_entries, batch_update_time_entries. |
| Read or manage saved dashboards | list_dashboards, get_dashboard, create_dashboard, update_dashboard, delete_dashboard. |
| Prepare and manage client invoices | list_uninvoiced_time_entries, create_invoice, send_invoice, record_invoice_payment. |
| Check contracts and profitability | list_contracts, get_contract_profitability, get_org_profitability. |
| Create, schedule, or run reports and routines | create_report, update_report, run_report, list_routine_templates, create_routine, run_routine. |
| Reuse Skills and standing guidance | list_skills, get_skill, update_team_agent_context, update_workspace_agent_context. |
Availability depends on your role and workspace plan. See the tool reference for each tool's inputs and permissions.
Connection
| Setting | Value |
|---|---|
| Server URL | https://mcp.rize.io/mcp |
| Transport | Streamable HTTP |
| Authentication | OAuth 2.0 (authorization code + PKCE) |
| Authorization server metadata | https://mcp.rize.io/.well-known/oauth-authorization-server |
| Protected resource metadata | https://mcp.rize.io/.well-known/oauth-protected-resource |
| Dynamic client registration | Supported (RFC 7591) |
Clients that support dynamic client registration — Claude Desktop, Claude Code, ChatGPT, Codex, Cursor, Zed, and anything on the official MCP SDKs — register themselves the first time you connect. There is no client ID or secret for you to create.
Signing up without an account
People who don't have a Rize account yet can use https://mcp.rize.io/mcp/public.
It needs no sign-in and exposes two tools: sign_up, which emails a 6-digit
sign-in code, and get_login_url, which returns the sign-in, sign-up,
and desktop app download links. Once the account exists, connect to
https://mcp.rize.io/mcp for everything else.
ChatGPT can call sign_up and get_login_url on https://mcp.rize.io/mcp
before linking an account. Every other tool there asks ChatGPT to link the
account first.
Authentication
The server uses the OAuth 2.0 authorization code flow with PKCE. On first connection:
- Your MCP client requests the server's authorization metadata and registers itself.
- The client opens your browser to sign in to Rize with Continue with Google or an emailed sign-in code — the same way you sign in normally.
- Rize shows a consent screen naming the client, the exact redirect URL it will return you to, and the scopes it is asking for. Denying sends the client an
access_deniederror and grants nothing. - After you approve, the browser redirects back to the client with an authorization code, which it exchanges for an access token.
Access tokens expire after two hours and clients refresh them silently, so you should only need to re-authorize if you disconnect the connector or revoke it from Rize. PKCE is required for every client, public or confidential.
What the assistant can reach
Tokens are issued with the read and write scopes. In practice, the boundary
that matters is not the scope — it is your own role:
| You are | You get |
|---|---|
| Any member | Your own time entries, activity, apps used, calendar events, keywords, tagging settings, Skills, reports, and routines. |
| Team admin | Everything above, plus team-wide time entries and allocation, the team roster, member rates, invites, and labels. |
| Manager | Your direct reports in the roster and allocation views. |
| Org admin | Contracts, expenses, revenue entries, and profitability across the workspace; invoices on plans that include invoicing. |
| Finance permission | Profitability reads plus expense and revenue writes, without being an org admin. |
An assistant calling a tool you do not have permission for gets an error, not someone else's data. The server never widens access — it forwards your bearer token to the same API the Rize apps call.
The MCP server operates entirely within the workspaces you belong to. It cannot access data outside your permissions. Team and workspace views can include other members' data only when your role allows it.
Setup per client
Connect to Claude · Connect to ChatGPT
The Claude link prefills the connector name and server URL. Review the values and confirm to add the connector. The ChatGPT link opens the Rize listing.
Claude Desktop and claude.ai
Connect to Claude, review the prefilled name and URL, and confirm. Connect Rize, sign in, and approve access. In Claude Desktop, open Customize → Connectors to use the same remote connector.
To add the connector manually:
- Open Customize → Connectors.
- Click Add custom connector.
- Enter the name
Rizeand the URLhttps://mcp.rize.io/mcp. - Click Add, then Connect next to Rize. A browser window opens.
- Sign in, approve the consent screen, and return to Claude. The Rize tools are available in any chat.
Claude Code
Register the server:
claude mcp add --transport http rize https://mcp.rize.io/mcp
Or commit a .mcp.json to your project root so the whole team picks it up:
{
"mcpServers": {
"rize": {
"type": "http",
"url": "https://mcp.rize.io/mcp"
}
}
}
Start or restart a session, run /mcp, select rize, and choose
Authenticate. A browser window opens; once it says Authorization
successful you can close it. Run /mcp again to confirm the connection.
Codex
Register the remote server and sign in:
codex mcp add rize --url https://mcp.rize.io/mcp
codex mcp login rize
Codex stores MCP settings in ~/.codex/config.toml, not .mcp.json.
For a trusted project, you can instead add this to .codex/config.toml:
[mcp_servers.rize]
url = "https://mcp.rize.io/mcp"
Run /mcp inside Codex to check the connection. See the
Codex MCP documentation.
Cursor
Add Rize to .cursor/mcp.json in your project, or ~/.cursor/mcp.json
to make it available across projects:
{
"mcpServers": {
"rize": {
"url": "https://mcp.rize.io/mcp"
}
}
}
Open Cursor's MCP settings, connect Rize, and complete the browser sign-in. Use Rize from Agent chat; no API key or client secret is needed. See the Cursor MCP documentation.
ChatGPT
- Open the Rize listing in ChatGPT.
- Click Connect (or Try in chat, then Connect when prompted).
- Sign in to Rize with Continue with Google or an emailed sign-in code.
- Approve access and return to ChatGPT. Type
@Rizeto use the connector.
To connect the MCP server manually, subject to your account and workspace permissions:
- Open Plugins.
- Select + → Add custom MCP server.
- Enter a name and description, then set the connection URL to
https://mcp.rize.io/mcp. - Choose OAuth, review the risk warning, and select I understand and want to continue.
- Select Create as a plugin, review the discovered tools, and complete sign-in and consent.
The current Plugins flow does not require enabling Developer Mode first. See OpenAI's custom MCP setup instructions.
Raycast
Raycast connects to remote MCP servers natively and signs in with OAuth, so no bridge is needed.
- Open Raycast and run Install MCP Server.
- Enter the name
Rize, choose the HTTP transport, and paste the URLhttps://mcp.rize.io/mcp. - Leave the OAuth type on Dynamic and click Sign In. A browser window opens; sign in and approve the consent screen.
- Back in Raycast, type
@Rizein AI Chat or Quick AI to use the tools.
Raycast asks for approval before each tool call by default, so the first few prompts will confirm what Rize is about to read or change; you can relax that per server in its MCP settings.
Zed
Open Settings → AI → MCP Servers → Add Server → Add Remote Server and
enter https://mcp.rize.io/mcp. You can also add it to your Zed settings:
{
"context_servers": {
"rize": {
"url": "https://mcp.rize.io/mcp"
}
}
}
Zed prompts you to authenticate through OAuth. No stdio bridge is required. See the Zed MCP documentation.
Any other MCP client
Any client that speaks Streamable HTTP with OAuth 2.0 can connect directly —
point it at https://mcp.rize.io/mcp and the rest is negotiated. A typical
config entry looks like:
{
"mcpServers": {
"rize": {
"url": "https://mcp.rize.io/mcp"
}
}
}
Key names differ per client (url, httpUrl, type, transport), so check
your client's documentation for the exact shape. Clients that only support
stdio can bridge with mcp-remote:
{
"mcpServers": {
"rize": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.rize.io/mcp"]
}
}
}
How to drive it well
These are the things that separate an assistant that gets Rize right from one that guesses.
Start with get_current_user
It returns your timezone, default team, team memberships with roles, and your
org id and role. Almost every other tool needs at least one of those, and the
profitability tools all need org_id.
Let the server explain itself
get_help returns workflow guides by topic — time tracking,
profitability, team management, clients and projects, keywords, skills.
get_product_docs searches these docs, so an assistant can answer
product questions with a real URL instead of inventing one.
Times are ISO 8601, in your timezone
Every response carries a _user_timezone field. Convert
user-relative times ("2pm yesterday") into that zone before sending them —
assuming UTC is the single most common source of entries landing on the
wrong day.
Use evidence, not vibes, when tagging
list_my_keyword_matches returns deterministic keyword-rule hits
over a time window, and list_my_time_entries with
include_activity: true attaches top apps, window titles, and
overlapping matches per entry. Both are far stronger signals than a title.
Read totals without rebuilding them
Use get_my_time_allocation for your own totals or the team and workspace
allocation tools when your permissions allow them. Use get_dashboard for
the live numbers behind a saved Tracked Time, Timesheets, Personal Productivity,
or widget dashboard. These tools return calculated totals; an assistant should
quote them rather than add up a page of time entries.
list_my_time_entries returns compact summaries and calculated totals.
When totals.partial is true, those totals cover only the current page.
Use get_time_entry for one entry's full details or include_details: true
for a detailed list. Add include_activity: true only when you need app,
window-title, and keyword evidence.
Time entry statuses
Time entries move through statuses, and filtering on the wrong one is the usual reason a query comes back empty:
| Status | Meaning |
|---|---|
tracking | Time being tracked live right now. |
segmenting | Tracked activity being cut into candidate entries. |
generating | An AI suggestion is being written for the entry. |
pending | An AI suggestion waiting for you to approve or reject. |
failed | Generation failed; the entry is still reviewable. |
active | A confirmed entry — what reports and invoices are built from. |
Rejected entries are not returned by the public API or accepted as a status
filter. When someone says "my suggestions", they mean pending, generating,
and failed.
list_my_time_entries includes all listed statuses by default.
get_my_time_allocation defaults to active, so pass the same status filter
to both tools when comparing their results.
Conventions worth knowing
- IDs, not names. Time entry writes take
client_id,project_id, andtask_id. Resolve names first withlist_clients,list_projects, andlist_tasks, all of which accept aquery. - Pagination. Most list tools take
limitandcursorand returnhas_moreandnext_cursor. Dashboard lists instead takefirstandafterand returnpage_info.has_next_pageandpage_info.end_cursor. Follow each tool's schema and page through all results before claiming a list is complete. - Idempotency.
create_time_entryaccepts anidempotency_key. Pass one on every create so a retried call cannot double-log an hour. - Money is in cents. Every monetary value in the contract and profitability tools is an integer number of cents.
- Async AI.
generate_time_entriesandregenerate_time_entryreturn immediately and finish in the background. Polllist_my_time_entrieswithstatuses: ["generating", "pending"]. - Preview before saving.
add_notewithblocksdefaults tosave: falseand returns what it would create, including overlaps with existing entries. Confirm, then call again withsave: true. - Preview bulk changes.
batch_update_time_entriesdefaults todry_run: true. Show the count and sample, get confirmation, then call withdry_run: false. - Timers start now.
start_sessionstarts a live timer and ends any running session. For work that already happened, useadd_noteorcreate_time_entry. - Draft before sending.
create_invoicecreates a draft, not an email. Review it withget_invoicebefore usingsend_invoice. - Reuse instructions.
list_skillsandget_skillexpose saved Skills, and the agent context tools manage standing guidance for people, teams, and workspaces. - Read finished AI output.
list_report_runs,get_report_run,list_routine_runs, andget_routine_runreturn report analyses and routine briefs without re-running the same prompt.
Rate limits
| Limit | Applies to |
|---|---|
| 100 requests per minute, per user | All authenticated tool calls, across every tool. |
| 10 requests per minute, per tool | The unauthenticated tools, sign_up and get_login_url. |
| 15 per minute and 100 per day | AI generation — generate_time_entries and regenerate_time_entry share one quota. |
| 3 regenerations per entry | regenerate_time_entry, counted for the life of the entry. |
| 20 registrations per minute, per IP | Dynamic client registration during first connect. |
Exceeding the per-user limit returns a RATE_LIMITED error carrying
retry_after_seconds, so a well-behaved assistant knows exactly how long to
wait. The AI generation quotas are enforced by the API and surface as an
ordinary error message rather than a RATE_LIMITED code.
Error handling
Every tool error comes back as a JSON object with an error field. The codes an
assistant will actually encounter:
| Code | Meaning | What to do |
|---|---|---|
AUTHENTICATION_ERROR | No token, or the token is expired or revoked. | Re-authorize the connector. |
TOKEN_EXPIRED_ERROR / TOKEN_REVOKED_ERROR / INVALID_TOKEN_ERROR | The bearer token was rejected by the API. | Re-authorize the connector. |
RATE_LIMITED | Per-user rate limit hit. Includes retry_after_seconds. | Wait that long, then retry. |
SUBSCRIPTION_ERROR | No active subscription on the account. | Surface the message. Do not retry. |
INVALID_TIER_ERROR | The workspace plan does not include this capability. | Surface the message. Do not retry. |
GRAPHQL_ERROR | Validation failure, missing record, or insufficient permission. Carries a messages array. | Read messages — it names the problem. Correct the input rather than retrying blind. |
HTTP_5xx | Transient server error. | Retry once, then surface it. |
INTERNAL_ERROR | Unexpected server-side failure. | Surface the message. |
GRAPHQL_ERROR is the catch-all: a bad ID, an out-of-range value, and "you must
be a team admin" all arrive under it, distinguished by the messages array
rather than by code.
Troubleshooting
"Not authenticated" on every call — the token expired or was revoked. Reconnect the connector and sign in again.
The OAuth window opens but never redirects back — some browsers block redirects to 127.0.0.1. Complete the flow in Chrome or Edge, and make sure the callback tab is not blocked by an extension.
Queries return nothing for a day you know you worked — check the status filter first. active alone excludes every AI suggestion. Then check the timezone: a date interpreted in UTC instead of your zone shifts the whole window.
generate_time_entries produces no entries — Rize only generates from tracked activity. If the desktop app was not running for that range, there is nothing to cluster. Very short ranges often produce nothing too; try a full workday.
"Admin only" style errors — list_team_time_entries, get_team_time_allocation, invite_team_member, and the label tools need team admin. The contract and profitability tools need org admin or the finance permission. Use the _my_ variants, or ask an admin.
Stale tool list after an update — some clients cache the tool list. Fully quit and relaunch, then open a new chat.
Example prompts
- "How much time did I track today, grouped by client?"
- "Show me my pending suggestions and approve the ones that are clearly the Acme redesign."
- "What did I actually work on between 2pm and 5pm yesterday? Use my app activity, not just the entry titles."
- "Create a keyword rule so anything with 'Figma' in the window title tags to the Acme project."
- "Log 2 hours on the NVIDIA pitch deck this afternoon."
- "What is the margin on the Acme retainer this quarter, and how much of the included hours have we burned?"
- "Pull my last weekly report run and list every recommendation it made."
- "Read my latest start-of-day routine brief and turn it into a short plan."
- "Use my 'Client profitability review' Skill before summarizing this report run."
- "Read my saved Timesheets dashboard for this week and show the totals by member."
- "Start a 45-minute focus session for the Acme redesign."
- "Prepare a draft invoice for Acme's uninvoiced time this month. Don't send it."
Tool reference
Every tool, with parameters, defaults, and permissions.
Reports in the API and MCP
Read finished report and routine runs from an agent instead of re-analyzing raw entries.
Skills and Agent Context
Reuse standing guidance across chat, reports, routines, and MCP clients.
GraphQL API
The same data over a plain API key, for integrations that are not agents.
Rize AI agent
The agent built into Rize, which uses these same capabilities.
Support
- Contact: rize.io/contact
- Privacy policy: rize.io/privacy-policy
- Terms of service: rize.io/terms-of-service