Apollo GraphQL, the graph-based API orchestration leader, is introducing Apollo GraphOS Agent Services, giving AI agents secure, governed, and auditable access to an enterprise’s systems and APIs.
Built on GraphOS, Apollo’s platform for connecting and orchestrating enterprise APIs, Agent Services extends that infrastructure to AI agents, so companies can control what each agent can access and do, according to the company.
Additionally, Apollo is expanding the GraphOS MCP Server into a full suite of agent-ready tools for building and managing the graph.
GraphOS Agent Services sits between AI agents and an enterprise’s systems. It translates each agent request into the right API calls, brokers the credentials for each one, and enforces controls on what a human or agent is allowed to see or do, field by field, with no LLM in the judgement loop, the company said.
It does this through a new set of capabilities: search, so agents can find the right data and tools; identity, to manage credentials for an agent acting autonomously or on behalf of a human; policy, so companies can control exactly what each agent can see and do, down to an individual field; and audit, so there is a precise log of everything that happened for observability, insights, and compliance. With these new services, GraphOS provides one governed system in place of the ad hoc access used today, said the vendor.
“Enterprises need to adapt their APIs for AI agents,” said Matt DeBergalis, CEO and co-founder, Apollo GraphQL. “They need to do it scalably, securely, and sustainably, with a common architecture that supports customer-facing AI, always-on business agents, and traditional software. GraphOS Agent Services adds the context they need, and provides a complete domain model for AI. It's the essential next step.”
Apollo also announced continued platform investment to improve graph performance and help teams use agents to build and operate their graphs. The biggest update is in the core of how operations are processed: GraphOS Router 3.0, now in preview, introduces a new request pipeline and query planner that dramatically improve performance and reduce resource consumption.
The GraphOS MCP Server has also grown into a full suite of agent-ready tools for building and managing the graph. The GraphOS Platform API is how teams automate GraphOS from their own code, from publishing schemas and running checks to managing variants and reading insights.
The GraphOS MCP Server now exposes more of that API to agents, so those same actions can be driven in natural language instead of custom code.
Two more updates support agents operating the graph itself. Apollo's library of Skills, which teaches agents Apollo's own expertise in Federation, Connectors, the Router, and much more, has grown to 14 skills with more than 47,000 installs. And the GraphOS Operator for Kubernetes can now centrally deploy and manage the Apollo MCP Server alongside other GraphOS infrastructure, simplifying operations for platform teams, the company said.
For more information about this news, visit www.apollographql.com.