Webex Integration for AI Agents
Connect your AI agent to 115 Webex actions via MCP, A2A, or SDK, with agent authentication, tool-calling execution, and security built-in, plus 27 events to subscribe to.
Webex AI Agent Actions
115 production-ready actions for your agent to do more on Webex.
Webex Webhook Events
27 real-time Webex events your AI agent can subscribe to.
- Active Check Responds with 200 OK to any Webex webhook delivery that does not carry a recognized resource and event pair.
- Message Created Fired when a new message is posted into a room the authorizing user or bot is a member of.
- Message Deleted Fired when a message is deleted from a room the authorizing user or bot is a member of.
- Room Created Fired when a new room (space) is created by the authorizing user or one of their integrations.
- Room Updated Fired when a room the authorizing user is in is updated, most often when it is locked or unlocked.
- Room Migrated Fired when a room the authorizing user or bot is in is migrated to a different geography.
- Membership Created Fired when someone joins a room the authorizing user is in, or the authorizing user is added to a new room.
- Membership Updated Fired when a membership changes in a room the authorizing user is in, primarily to signal moderator changes.
- Membership Deleted Fired when someone leaves or is removed from a group room the authorizing user is in.
- Card Action Submitted Fired when a user submits an adaptive card the authorizing bot or integration posted.
- Meeting Created Fired when a new meeting is scheduled.
- Meeting Updated Fired when a scheduled meeting is modified.
- Meeting Deleted Fired when a scheduled meeting is cancelled or deleted.
- Meeting Started Fired when a scheduled meeting actually starts.
- Meeting Ended Fired when a live meeting ends.
- Meeting Participant Joined Fired when a participant joins a meeting.
- Meeting Participant Left Fired when a participant leaves a meeting.
- Meeting Transcript Created Fired when a transcript becomes available for a recorded meeting.
- Recording Created Fired when a new meeting recording becomes available.
- Recording Updated Fired when an existing meeting recording is modified.
- Recording Deleted Fired when a meeting recording is permanently deleted.
- Converged Recording Created Fired when a new converged (call) recording becomes available.
- Converged Recording Updated Fired when an existing converged (call) recording is modified.
- Converged Recording Deleted Fired when a converged (call) recording is deleted.
- Call Started Fired when the authorizing user originates or receives a call.
- Call Updated Fired when a call the authorizing user is on changes state.
- Call Ended Fired when a call the authorizing user was on is disconnected.
Do More, Build Less
Integration Infrastructure for Webex AI Agents
"What impressed us most about StackOne is its ambition and clarity. They're creating infrastructure that modern software and the entire AI agent ecosystem can rely on. The depth of secure integrations, the pace of delivery, and the team's foresight into AI's future uniquely position StackOne to redefine this category."
Luna Schmid, Partner at GV
"We've been impressed by how quickly and deeply StackOne integrates with complex enterprise systems -- and now, with their focus on agent-to-agent interoperability, they're unlocking even more powerful use cases for customers. StackOne delivers all of the above in a universal layer -- without compromise."
Barbry McGann, SVP at Workday Ventures
Webex AI agent integration resources
Webhooks for AI agents: why agentic workflows need them purpose-built
AI agents can act the moment a system changes, using webhooks. But webhooks built for software hit three limits in agentic workflows. Here is how to fix each.
7 min read
Agentic Context Engineering: Why AI Agents Kill Their Own Context Windows
AI agents exceed their context windows without knowing it. Six failure patterns and seven survival architectures for agentic context engineering.
15 min
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.