--- title: "Don't Let AI Agents Improvise Against Production GraphQL" url: https://daily.dev/posts/don-t-let-ai-agents-improvise-against-production-graphql-8scnqsfxt source_url: https://wundergraph.com/blog/governing-ai-agent-access-to-graphql-mcp-gateway type: article source: "WunderGraph" published: 2026-06-10T00:42:07.095Z updated: 2026-06-10T00:42:31.401Z tags: ["security", "ai-agents", "graphql", "mcp"] reading_time: 10 upvotes: 2 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Don't Let AI Agents Improvise Against Production GraphQL **[WunderGraph](https://daily.dev/sources/wundergraph)** · 10 min read · 2 upvotes · 0 comments ## Summary AI agents should never run arbitrary GraphQL operations against production systems. The recommended pattern is to use an open-world setup in development — full schema introspection and ad-hoc queries — so agents can discover useful operations, then promote those to named, reviewed persisted operations exposed as tools via the Cosmo Router MCP Gateway in production. Five governance rules are outlined: no arbitrary execution in production, no default schema visibility, higher bar for mutations, intention-revealing tool names, and treating the safelist as a public API contract. The safelist bounds the failure surface, enabling rate limits, scopes, and human-approval gates to be applied to a finite set of reviewed operations rather than an open-ended graph. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [What developers can do to combat the growing threat of rogue AI agents](https://daily.dev/posts/what-developers-can-do-to-combat-the-growing-threat-of-rogue-ai-agents-le8ldopan) · Dev Interrupted · 1 upvotes · 0 comments - [How to Prepare GraphQL APIs For AI Agents](https://daily.dev/posts/how-to-prepare-graphql-apis-for-ai-agents-g3vyhofvd) · Nordic APIs · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#graphql](https://daily.dev/tags/graphql), [#mcp](https://daily.dev/tags/mcp) [View this post on daily.dev](https://daily.dev/posts/don-t-let-ai-agents-improvise-against-production-graphql-8scnqsfxt)