# GraphOS MCP Server: graph-aware tools for your AI agent

**URL:** <https://community.apollographql.com/t/graphos-mcp-server-graph-aware-tools-for-your-ai-agent/9969>\
**Category:** MCP Server\
**Tags:** graphos, ai, mcp\
**Created:** [July 22, 2026, 2:49pm UTC](https://community.apollographql.com/t/graphos-mcp-server-graph-aware-tools-for-your-ai-agent/9969 "2026-07-22T14:49:14Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![DaleSeo](https://sea1.discourse-cdn.com/flex019/user_avatar/community.apollographql.com/daleseo/32/5385_2.png) [@DaleSeo](https://community.apollographql.com/u/DaleSeo)\
**Post date:** [July 22, 2026, 2:49pm UTC](https://community.apollographql.com/t/graphos-mcp-server-graph-aware-tools-for-your-ai-agent/9969/1 "2026-07-22T14:49:14Z")

</div>

🚀 **GraphOS MCP Server now gives your AI agent read-only access to your graph.**

Point it at a graph and ask in plain language. It scans for issues across launches, schema lint, router config, and traffic metrics, then hands you a prioritized list, one prompt instead of a tour across Studio tabs.

It’s Apollo’s hosted MCP server, live at `[https://mcp.apollographql.com/mcp\`](https://mcp.apollographql.com/mcp%5C%60). If you’ve used it for docs search or the Connectors spec, that’s the same endpoint under a new name (formerly GraphOS MCP Tools), now with graph-aware tools too.

**🤖 What your agent can do**

- **Know your graph** : resolve your graph and its variants straight from your API key, no IDs to look up
- **Inspect a variant** : federation version, subgraph inventory, router status and config
- **Track deployments:** latest launch, launch history, and single-launch detail with composition errors
- **Watch traffic & performance:** top operations plus per-operation and per-subgraph request counts, p50/p99 latency, and errors (returned as compact CSV so agents don’t drown in JSON)
- **Check quality & security:** schema lint violations and persisted query list status

**💡 Try it**

- “Scan for issues across my graph and summarize the findings by severity.”
- “Which operations had the highest p99 latency over the last week?”
- “Have my recent launches been stable, or were there any failures?”

It surfaces issues in what these tools can see and ranks them, rather than declaring a graph “healthy.”

**🔐 Scoped by your key**

Pass a graph API key via the `x-api-key` header. An Observer-role key can run every tool, read-only, nothing more. Today the graph tools need a client that can send that header (Claude Code, Cursor, VS Code, Codex, Gemini CLI). OAuth for header-less clients like Claude Desktop is on the roadmap.

**🔗 Resources**

- Blog: [Graph Health Checks, Now a Prompt Away - Apollo GraphQL Blog](https://www.apollographql.com/blog/announcement/graph-health-checks-now-a-prompt-away)
- Install guide: [Install GraphOS MCP Server - Apollo GraphQL Docs](https://www.apollographql.com/docs/graphos/platform/graphos-mcp-server/install)
- Tool reference: [GraphOS MCP Server Tools - Apollo GraphQL Docs](https://www.apollographql.com/docs/graphos/platform/graphos-mcp-server/tools)

> **[Graph Health Checks, Now a Prompt Away - Apollo GraphQL Blog](https://www.apollographql.com/blog/announcement/graph-health-checks-now-a-prompt-away)**
>
> GraphOS MCP Server connects AI agents to GraphOS, so agents can run graph health checks: launch status, lint results, router config, and traffic metrics.

We’d love to hear what you’re checking with it, and what you wish your agent could run next. Tell us below. 👇