Fellow.ai for AI agents
Fellow.ai manages meeting notes, agendas, and action items, helping teams run structured meetings and track follow-through so commitments made in a call don't get lost. 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 Fellow.ai.
Pull a meeting's action items
Get the action items from a meeting to check what was assigned to a team member.
Write to a meeting agenda
Write a topic to an upcoming meeting's agenda once a team member requests it be added.
Read-only transcript search
Search meeting transcripts as a read-only step to find where a decision was discussed.
19 Fellow.ai actions, graded by risk.
Every Fellow.ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
11Look things up. Allowed by default.
- fellow_ai.list_channelsList channels
- fellow_ai.search_meetingsSearch meetings
- fellow_ai.get_action_itemsGet action items
- fellow_ai.get_agenda_templateGet agenda template
- fellow_ai.get_channel_detailsGet channel details
- fellow_ai.get_meeting_summaryGet meeting summary
- fellow_ai.get_meeting_transcriptGet meeting transcript
- fellow_ai.search_agenda_templatesSearch agenda templates
- fellow_ai.get_meeting_participantsGet meeting participants
- fellow_ai.read_agendaRead agenda
- fellow_ai.read_resourceRead resource
write
7Create and change things. Allow, or ask the user first.
- fellow_ai.create_agenda_templateCreate agenda template
- fellow_ai.edit_agendaEdit agenda
- fellow_ai.write_agendaWrite agenda
- fellow_ai.rename_agendaRename agenda
- fellow_ai.edit_agenda_templateEdit agenda template
- fellow_ai.apply_agenda_templateApply agenda template
- fellow_ai.set_default_agenda_templateSet default agenda template
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- fellow_ai.delete_agenda_templateDelete agenda template
Fellow.ai in three steps.
- 01Your users connect Fellow.aiThey sign in to Fellow.ai on Arc0 Connect, under your brand, and approve the access you ask for.
- 02You set the rulesReads run, writes like “create agenda template” can wait for the user, and “delete agenda template” can be denied outright.
- 03Any agent can actYour agent calls Fellow.ai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('fellow_ai', { read: 'allow', write: 'ask', // create_agenda_template destructive: 'deny', // delete_agenda_template }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Fellow.ai connects.
Fellow.ai runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Fellow.ai through the same endpoint, policies and audit log as every other app.
The same Fellow.ai 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
- OAuth 2.0 (MCP)
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Fellow.ai from any agent.
Fellow.ai and Arc0, answered.
Can I use Fellow.ai with Claude, ChatGPT or Cursor?
Yes. Connect Fellow.ai 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 Fellow.ai actions you allow.
How do users connect Fellow.ai?
Fellow.ai runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Fellow.ai through the same endpoint, policies and audit log as every other app.
Which Fellow.ai actions can my agent take?
19 in total: 11 read, 7 write and 1 destructive, such as “create agenda template”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Fellow.ai?
Yes. Actions like “delete agenda template” 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 Fellow.ai too?
Yes. The same Fellow.ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Fellow.ai into your agent.
Your users connect Fellow.ai once, under your brand. Your agent gets 19 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan