Slite for AI agents
Slite is a company knowledge base where teams write and organize documentation, and where an agent can find answers instead of searching scattered notes. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Slite.
Answer a question from the knowledge base
Ask a question against the knowledge base and return the relevant note instead of searching manually.
Flag an outdated note
Flag a note as outdated when its content no longer matches current process, prompting an owner to review it.
Confirm before deleting a note
Look up a note's owner and content before deleting it, since removing a note takes it out of the knowledge base for good.
16 Slite actions, graded by risk.
Every Slite action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- slite.list_notesList Notes
- slite.search_notesSearch Notes
- slite.search_usersSearch Users
- slite.search_groupsSearch Groups
- slite.get_note_by_idGet Note By ID
- slite.get_note_childrenGet Note Children
- slite.get_authenticated_userGet authenticated user
- slite.verify_noteVerify Note
write
7Create and change things. Allow, or ask the user first.
- slite.create_noteCreate Note
- slite.update_noteUpdate Note
- slite.update_tileUpdate Tile in Note
- slite.update_note_ownerUpdate Note Owner
- slite.update_note_archived_stateUpdate Note Archived State
- slite.ask_questionAsk Question
- slite.flag_note_as_outdatedFlag Note as Outdated
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- slite.delete_note_by_idDelete Note By ID
Slite in three steps.
- 01Your users connect SliteThey add their Slite api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Note” can wait for the user, and “delete Note By ID” can be denied outright.
- 03Any agent can actYour agent calls Slite through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('slite', { read: 'allow', write: 'ask', // create_note destructive: 'deny', // delete_note_by_id }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Slite connects.
Users add their Slite api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Slite connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Slite from any agent.
Slite and Arc0, answered.
Can I use Slite with Claude, ChatGPT or Cursor?
Yes. Connect Slite to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Slite actions you allow.
How do users connect Slite?
Users add their Slite api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Slite actions can my agent take?
16 in total: 8 read, 7 write and 1 destructive, such as “create Note”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Slite?
Yes. Actions like “delete Note By ID” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Slite too?
Yes. The same Slite connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Slite into your agent.
Your users connect Slite once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan