Radar is an optional discovery mode for MCP Gateways with large tool libraries. Instead of handing your AI agent every tool definition from every connected server up front, Radar exposes a small set of built-in tools that let the agent search for the specific capability it needs and call it on demand. The initial tool list stays short no matter how many servers or tools the gateway has behind it.
Why Use Radar?
Every tool definition you expose to a model consumes context tokens, and agents tend to make worse decisions when forced to choose between dozens or hundreds of options at once. Radar solves this by replacing a gateway’s full tool list with:
- Three built-in discovery tools (
radar_search, radar_execute_tool, and radar_manage_cache)
- Any tools the agent has already discovered and used before, which stay directly callable
This means a gateway with hundreds of tools behind it can still start a conversation with only a handful of tool definitions in context.
Radar works best on gateways with a large or varied tool library. For a small, focused gateway with only a handful of tools, the standard /mcp endpoint is simpler and just as effective.
Enabling Radar
Radar is a per-gateway setting, toggled with the Use Radar switch when creating or editing a gateway.
When enabled, every connection URL and client install snippet shown for that gateway (Cursor, Claude Desktop, Claude Code, etc.) automatically points at the gateway’s /radar endpoint instead of /mcp.
If you’re wiring up a client manually, the only difference between the two modes is the URL:
Standard: https://mcp-gateway.airia.com/gateway/{gateway-id}/mcp
Radar: https://mcp-gateway.airia.com/gateway/{gateway-id}/radar
When a gateway you’re creating or editing exposes more than 50 tools, Airia suggests turning on Radar with a dismissible banner. You’re always free to keep the full tool list instead.
tools/list returns only:
- The three Radar tools described below
- Tools the agent has previously discovered and hasn’t lost from its personal memory (see Discovered-Tool Memory)
The gateway’s full, fixed tool list is never sent; the agent has to ask for what it needs.
radar_search
Searches every tool available on the gateway using a natural-language description of what you’re trying to do, and returns full tool definitions (name, description, and input schema) for the closest matches.
| Parameter | Description | Type | Required | Default |
|---|
query | Natural-language description of the capability you’re looking for, e.g. “find bugs assigned to me in Jira.” | string | Yes | N/A |
max_results | Maximum number of tools to return. | integer | No | 5 |
min_relevance | Minimum relevance score (0–1) a tool must meet to be included. | number | No | 0.5 |
radar_search doesn’t error. It returns a normal response indicating no tools were found, so the agent can try a different phrasing.
Runs a tool that was returned by radar_search. This step exists because tools found through search usually aren’t part of the agent’s initial callable tool list. radar_execute_tool dispatches the call to whichever MCP server actually owns that tool and returns its normal result.
| Parameter | Type | Required | Description |
|---|
tool_name | string | Yes | The exact name of the tool, as returned by radar_search. |
arguments | object | No | Arguments to pass to the tool, matching its input schema. |
radar_manage_cache
Lets the agent inspect and curate its own discovered-tool memory.
| Action | Description |
|---|
list | Lists every cached tool, along with whether it’s pinned, how many times it’s been used, and when it was last used. |
pin | Protects specific tools from ever being dropped from memory, regardless of how long it’s been since they were used. |
unpin | Removes pin protection from specific tools. |
remove | Drops specific tools from memory. |
clear | Empties the cache. Set include_pinned: true to also remove pinned tools; otherwise pinned tools are kept. |
radar_search for the same capability every time. Once a tool is discovered and called successfully, it’s added to a memory scoped to you and that gateway, and it appears directly in tools/list on future requests, without needing to search for it again.
- Memory persists between sessions. Closing and reopening a conversation doesn’t reset it.
- By default, up to 20 tools stay in memory at once. When memory is full, the least valuable tool is dropped to make room for a new discovery.
- Up to 5 tools can be pinned at a time (via
radar_manage_cache) to guarantee they’re never evicted, no matter how little they’re used.
Reconnecting Integrations Through Radar
If one of your connected apps needs attention (credentials were never set up, or an existing connection has expired or been revoked), Radar can still surface it. A radar_search result for that app includes a tool that, when run, walks you through reconnecting rather than failing outright. This means agents using Radar can guide you through fixing a broken connection instead of just reporting a dead end.
When to Use Radar
| Scenario | Recommendation |
|---|
| Gateway exposes 50+ tools | Enable Radar |
| Gateway spans several unrelated apps or domains | Enable Radar |
| Small, focused gateway (a handful of tools, single purpose) | Standard /mcp is simpler |
| You want every tool visible to the agent up front | Standard /mcp |
