Bring your tool server onto the canvas
Attach a Model Context Protocol tool server to an AI Agent on the canvas. WEXTL shows the MCP node next to the model — approved tools only, every call in run history.
- GDPR
- Data Encryption
- 2FA
- Local Data Region
AI Agent running with a Slack MCP tool server — its tools in the run result
What MCPs helps you do
Bring your tool server onto the canvas
- 1
Connect an MCP server
Point WEXTL at the MCP endpoint you trust.
- 2
Expose selected tools
Choose what the agent may call — nothing else is available.
- 3
Wire MCP under the agent
The MCP capability hangs off the AI Agent like the model — then act in Asana, Gmail, or CRM.
MCP beside the model, not instead of apps
MCP tools with the same audit trail as apps — not a side chat that forgets your CRM; tools run inside the workflow run.
An AI Agent can use your MCP server for internal tools while Asana and Gmail stay first-class app nodes on the same path.
Reviewers see the MCP node under the agent — not a mystery function call in another product.
MCP server picker — Slack, DeepWiki, GitHub, Linear and more
Policy before high-impact tool use
Pair MCP-backed agents with Filters and human review the same way you guard auto-send email.
Sensitive actions stay on a review branch; safe ones continue — logged either way.
Tools to include — all tools, an allow-list, or a deny-list