Daily · for agents

The Daily MCP

One key, nineteen tools, and your day where you already work.

In one paragraph

Daily speaks the Model Context Protocol. Approve it once from a client that runs OAuth, or mint a key inside the app and hand it to Claude Code, Codex, Claude Desktop or anything else that speaks MCP, and your agent can read today, plan it with you, tick things off as you finish them, and run an honest weekly review off your real numbers. The key decides whose day it is — an agent can only ever reach the one account that minted it — and every call is written to an audit trail you can read in the app.

1Get connected

Approve it, or mint a key

If your client can run OAuth — claude.ai connectors, Claude Desktop — paste the endpoint and press connect. Daily asks you to sign in and approve reading or writing, and no key ever leaves the browser. If your client wants a header instead, open Daily, tap your avatar, then Agent access → new key. The key is shown once. Tick read-only if the agent should look and never touch.

Point your client at the endpoint

The endpoint is https://getdaily.day/api/mcp — Streamable HTTP, bearer auth. It advertises its own authorization server, so a connector discovers the OAuth flow without being told. Pick your client below.

Ask for your day

Say "what's on today?" and watch it come back. Then try "plan my day", "close that out", "run my weekly review". The server ships its own instructions, so a good client already knows Daily's rules — including that the day rolls at 04:00, not midnight.


    
  

2The tools

Read tools work with any key. Write tools need a key with write access — a read-only key is refused, with a message saying so, and nothing is written.

the day
tasks
rituals
notes

3Prompts and resources

The server ships three prompts, so a client with a prompt picker gets the good version of each ritual without you writing it out: plan-my-day, evening-review, weekly-review. It also exposes three resources a client can pull as context — daily://today, daily://rituals and daily://stats/7d.

4How it is kept safe

The key decides whose day it is Your account id is derived from the key on every single call. It is not a parameter, so no prompt and no crafted argument can point an agent at somebody else's day.
Keys are stored hashed Only a SHA-256 hash and the first sixteen characters are kept. The plaintext exists once, on the screen where you minted it. Nobody at Daily can read your key back.
Revoke is instant One tap kills a key mid-session. Keys can also carry an expiry, and every key is checked for both on every call.
Read-only means read-only Scopes are enforced on the server, per tool, before a single row is touched — not in the tool description, where a model could talk itself around it.
Everything is written down Every call lands in an audit trail with the key name, the tool, whether it worked and how long it took. Read it in the app, or have your agent read it with agent_activity.
Marked, not smuggled Anything an agent writes is tagged at the database level and carries a quiet agent mark in the app. You can always see what was yours and what was not.
Rate limited 240 calls a minute per key. Past that you get a clean 429 with a Retry-After, so a runaway loop costs you nothing.
Your words are data, not orders Task and note text comes back as content, never as instructions. The server tells connecting clients so in its own instructions.

5Connecting over OAuth

For clients that will not take a pasted header. Nothing here is required reading to use Daily — it is here so you can see exactly what your client and Daily say to each other.

6Protocol notes

7Limits worth knowing

Mint a key free · open source · revoke it any time