Celigo, the intelligent automation platform, has announced Celigo MCP Management, giving IT and security teams one place to govern how AI assistants and agents act in business systems. With MCP Management, teams can connect each workflow to only the systems and tools it needs, control which people can use which tools and discover every MCP server in use. Every call is tied to a verified user, not a shared credential.
Celigo has announced MCP Management, a centralized control plane for how AI assistants and agents interact with enterprise systems through Model Context Protocol.
Teams can connect each workflow to only the systems and tools it needs, control which people can use which tools, and discover every MCP server in use.
Every MCP server, whether built in Celigo or by a third-party vendor, runs behind one MCP Gateway with access tied to the organization's identity provider.
The MCP Registry shows every MCP server in the organization, which AI assistants and agents use them, and who has access.
Celigo composite MCP servers can work across several systems in a single tool, such as pulling an order from the CRM, invoice details from the ERP and payment status from billing in one call.
Celigo MCP Management is generally available starting today.
"AI assistants and agents are a new class of actors in the enterprise, and the old model of shared credentials and broad access was never designed for them. Enterprises need to know who is behind every AI request, what it is authorized to do and what actions it has taken," said Matt Graney, Chief Product Officer at Celigo. "MCP Management gives IT one governed path. Every call traces back to a real person, access is approved one tool at a time, and because Celigo runs the tools as well as governs them, teams can see exactly which systems AI touched and what it changed."
"Celigo's MCP was the missing piece. It's the layer in the middle connecting to all our third-party tools in the cloud. Now we get the start, the middle and the end in one dashboard. That's a total game changer for analytics and visibility," said Antoine Millet, Head of IT, Nidecker Group.
Model Context Protocol has become a standard way for AI assistants and agents to connect to business systems, and many SaaS vendors now offer their own MCP servers. Each MCP server exposes a set of tools, the specific actions AI can take in that system, such as looking up a customer in a CRM, checking an invoice in an ERP or updating a ticket in a service desk.
Access that once sat with a small group of integration specialists can now extend to any employee using AI assistants such as Claude, ChatGPT, Copilot or Cursor, as well as autonomous agents that act without human intervention. Each MCP server comes with its own access model, and many are broad by default, giving every connected person or agent the full set of tools rather than only what the job requires. Many also run on shared service credentials, meaning systems of record may log the application rather than the person on whose behalf the assistant or agent acted.
Celigo MCP Management provides a centralized control plane for managing how AI assistants and agents interact with enterprise systems through MCP. The platform brings MCP servers built in Celigo and those built by third-party vendors under a common governance layer, allowing organizations to authenticate users, define access at the individual tool level and maintain an auditable record of AI activity across all MCP servers.
With Celigo MCP Management, enterprises can:
Connect MCP servers grounded in company knowledge. Teams turn existing integrations, more than 1,000 app connections and company knowledge bases into MCP servers built for specific jobs. Unlike a vendor's native MCP server, which only sees its own system, a Celigo composite MCP server can work across several systems in a single tool.
Control who uses which tools with the MCP Gateway. Every MCP server, whether built in Celigo or by a third-party vendor, runs behind one gateway. Teams can determine which tools each person can use, with access tied to the organization's identity provider.
Discover every MCP server with the MCP Registry. The registry shows every MCP server in the organization, which AI assistants and agents use them and who has access. Employees can request the tools they need, while administrators approve access to specific tools.
MCP Management runs on Celigo's intelligent automation platform, which enables teams to build and govern AI tools in the same place. Standalone MCP gateways typically only govern tools built elsewhere. Celigo builds governed tools from existing integrations and more than 1,000 app connections, including on-premises and legacy systems that may never have their own MCP server.
"Through an acquisition, system consolidation and workflows tailored to how we operate, Celigo has been a consistent platform for connecting data and systems across our business," said Christina M. Lanham, Director, Business Technology, Interplay Learning. "That foundation puts us in a stronger position as we expand our use of automation and AI, because our systems and data are already working together."
About Celigo
Celigo is the intelligent automation platform that connects the data and systems your business relies on, automates the work between them and brings in AI where it earns its place. Build integrations, workflows and agents, run them reliably at scale and control what they can access and do. All in one platform. The platform is recognized by G2 as #1 in iPaaS and a Leader in API Management, API Marketplace, and EDI and a 2025 & 2026 Gartner Peer Insights Customers' Choice for iPaaS.
