BotMape for AI agents
BotMape is a platform for building AI agents that businesses use to manage knowledge bases, hold conversations, and track usage across their bots. 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 BotMape.
Look up an AI agent's config
Read-only pull of an AI agent's settings and knowledge entries before making any changes.
Add knowledge to an agent
Add a new knowledge entry to an agent's knowledge base after the user approves the content.
Require approval before deleting knowledge
Treat deleting a knowledge entry as destructive since it removes information the agent relies on to answer.
8 BotMape actions, graded by risk.
Every BotMape action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- botmape.get_ai_agentGet AI Agent
- botmape.list_ai_agentsList AI Agents
- botmape.get_platform_analyticsGet Platform Analytics
- botmape.list_knowledge_entriesList Knowledge Entries
write
3Create and change things. Allow, or ask the user first.
- botmape.add_knowledgeAdd Knowledge
- botmape.create_ai_agentCreate AI Agent (No API Delete)
- botmape.send_message_to_ai_agentSend Message to AI Agent
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- botmape.delete_knowledge_entryDelete Knowledge Entry
BotMape in three steps.
- 01Your users connect BotMapeThey add their BotMape api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create AI Agent (No API Delete)” can wait for the user, and “delete Knowledge Entry” can be denied outright.
- 03Any agent can actYour agent calls BotMape through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('botmape', { read: 'allow', write: 'ask', // create_ai_agent destructive: 'deny', // delete_knowledge_entry }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How BotMape connects.
Users add their BotMape 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 BotMape 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 BotMape from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
BotMape and Arc0, answered.
Can I use BotMape with Claude, ChatGPT or Cursor?
Yes. Connect BotMape 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 BotMape actions you allow.
How do users connect BotMape?
Users add their BotMape 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 BotMape actions can my agent take?
8 in total: 4 read, 3 write and 1 destructive, such as “create AI Agent (No API Delete)”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in BotMape?
Yes. Actions like “delete Knowledge Entry” 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 BotMape too?
Yes. The same BotMape connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug BotMape into your agent.
Your users connect BotMape once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan