Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 8 additions & 15 deletions content/develop/ai/context-engine/context-gateway/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -14,12 +14,16 @@ aliases:
- /develop/ai/context-engine/context-retriever/interactive-demo/
---

Give each agent one Model Context Protocol (MCP) endpoint for every tool it needs, with one key and no Upstream credentials in the agent.
## What is Context Gateway?

Context Gateway lists and calls the tools of its Upstreams. An Upstream is any MCP server the Gateway can reach over Streamable HTTP, or a Context Surface that serves the records of a Redis database as tools. Agents connect with any MCP client that supports Streamable HTTP.
Redis Context Gateway is a Model Context Protocol (MCP) gateway for AI agents that:

> [!NOTE]
> Upstreams are not limited to Redis. Attach any MCP server, whether a third-party service such as a ticketing, billing, or search server, or one your team builds. Context Surfaces are optional.
- **Works with any MCP server:** Attach third-party and in-house MCP servers as Upstreams, not only Redis tools.
- **Serves one endpoint per Gateway:** An agent connects to one Gateway instead of to every MCP server it uses.
- **Keeps credentials out of agents:** The Gateway stores each Upstream's credential in your secrets backend and sends it on every call.
- **Turns Redis data into tools:** Optionally, a Context Surface generates tools from a data model over a Redis database.
- **Scales to large tool sets:** In `search` mode, the agent searches for tools instead of loading every definition.
- **Handles large and repeated results:** An optional result cache serves repeated calls, and result handles keep large results out of the agent's context.

<div class="grid grid-cols-1 md:grid-cols-4 gap-6 my-8">
{{< tile-card icon="images/icon_logo/icon-data-structures-64-midnight.png" title="Concepts" description="Gateways, Upstreams, tool exposure modes, and result handles" url="/develop/ai/context-engine/context-gateway/concepts" >}}
Expand All @@ -28,17 +32,6 @@ Context Gateway lists and calls the tools of its Upstreams. An Upstream is any M
{{< tile-card icon="images/dev/icons/icon-redis-insight-64-duotone.png" title="Manage Gateways" description="Register MCP servers and Context Surfaces and set tool policies" url="/develop/ai/context-engine/context-gateway/manage-gateways" >}}
</div>

## What is Context Gateway?

Redis Context Gateway is an MCP gateway for AI agents that:

- **Works with any MCP server**: Attach third-party and in-house MCP servers, not only Redis tools
- **Serves one endpoint per Gateway**: An agent connects to one Gateway instead of to every MCP server it uses
- **Keeps credentials out of agents**: The Gateway stores each Upstream's credential in your secrets backend and sends it on every call
- **Turns Redis data into tools**: Optionally, a Context Surface generates tools from a data model over a Redis database
- **Scales to large tool sets**: In `search` mode, the agent searches for tools instead of loading every definition
- **Handles large and repeated results**: An optional result cache serves repeated calls, and result handles keep large results out of the agent's context

## Why use Context Gateway?

<div class="grid grid-cols-1 md:grid-cols-2 gap-6 my-6">
Expand Down
Loading