Bland AI for AI agents
Bland AI is a platform for building and running AI voice agents that make and receive phone calls, following scripted conversation pathways for support and sales teams. 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 Bland AI.
List recent calls
Read-only lookup of recent calls placed through a pathway before deciding whether to change anything.
Organize conversation pathways
Create or rename a pathway folder to keep the call scripts a voice agent follows organized by team.
Review knowledge bases before reuse
List the knowledge bases and tools already on the account so an agent reuses one instead of duplicating it.
10 Bland AI actions, graded by risk.
Every Bland AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- bland_ai.list_callsList Calls
- bland_ai.list_toolsList Tools
- bland_ai.list_contactsList Contacts
- bland_ai.list_pathwaysList Pathways
- bland_ai.get_account_detailsGet Account Details
- bland_ai.list_knowledge_basesList Knowledge Bases
- bland_ai.list_pathway_foldersList Pathway Folders
write
2Create and change things. Allow, or ask the user first.
- bland_ai.create_pathway_folderCreate Pathway Folder
- bland_ai.rename_pathway_folderRename Pathway Folder
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- bland_ai.delete_pathway_folderDelete Pathway Folder
Bland AI in three steps.
- 01Your users connect Bland AIThey add their Bland AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Pathway Folder” can wait for the user, and “delete Pathway Folder” can be denied outright.
- 03Any agent can actYour agent calls Bland 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('bland_ai', { read: 'allow', write: 'ask', // create_pathway_folder destructive: 'deny', // delete_pathway_folder }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Bland AI connects.
Users add their Bland AI 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 Bland 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
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Bland AI from any agent.
Bland AI and Arc0, answered.
Can I use Bland AI with Claude, ChatGPT or Cursor?
Yes. Connect Bland 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 Bland AI actions you allow.
How do users connect Bland AI?
Users add their Bland AI 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 Bland AI actions can my agent take?
10 in total: 7 read, 2 write and 1 destructive, such as “create Pathway Folder”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Bland AI?
Yes. Actions like “delete Pathway Folder” 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 Bland AI too?
Yes. The same Bland AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Bland AI into your agent.
Your users connect Bland AI once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan