diff --git a/docs/querying/query-context.md b/docs/querying/query-context.md
index 1ac3af1127c4..2299c98ab070 100644
--- a/docs/querying/query-context.md
+++ b/docs/querying/query-context.md
@@ -67,6 +67,7 @@ Unless otherwise noted, the following parameters apply to all query types.
 |`setProcessingThreadNames`|`true`| Whether processing thread names will be set to `queryType_dataSource_intervals` while processing a query. This aids in interpreting thread dumps, and is on by default. Query overhead can be reduced slightly by setting this to `false`. This has a tiny effect in most scenarios, but can be meaningful in high-QPS, low-per-segment-processing-time scenarios. |
 |`maxNumericInFilters`|`-1`|Max limit for the amount of numeric values that can be compared for a string type dimension when the entire SQL WHERE clause of a query translates only to an [OR](../querying/filters.md#or) of [Bound filter](../querying/filters.md#bound-filter). By default, Druid does not restrict the amount of of numeric Bound Filters on String columns, although this situation may block other queries from running. Set this parameter to a smaller value to prevent Druid from running queries that have prohibitively long segment processing times. The optimal limit requires some trial and error; we recommend starting with 100.  Users who submit a query that exceeds the limit of `maxNumericInFilters` should instead rewrite their queries to use strings in the `WHERE` clause instead of numbers. For example, `WHERE someString IN (‘123’, ‘456’)`. This value cannot exceed the set system configuration `druid.sql.planner.maxNumericInFilters`. This value is ignored if `druid.sql.planner.maxNumericInFilters` is not set explicitly.|
 |`inSubQueryThreshold`|`2147483647`| Threshold for minimum number of values in an IN clause to convert the query to a JOIN operation on an inlined table rather than a predicate. A threshold of 0 forces usage of an inline table in all cases; a threshold of [Integer.MAX_VALUE] forces usage of OR in all cases. |
+|`federatedClusterBrokers`|`null`| If multiple Druid clusters need to support federated queries, each cluster should select a broker or router. Separate the connection information for each cluster with commas. |
 
 ## Druid SQL parameters
 
diff --git a/processing/src/main/java/org/apache/druid/query/QueryContexts.java b/processing/src/main/java/org/apache/druid/query/QueryContexts.java
index bf8003658c17..f108a3514065 100644
--- a/processing/src/main/java/org/apache/druid/query/QueryContexts.java
+++ b/processing/src/main/java/org/apache/druid/query/QueryContexts.java
@@ -85,7 +85,7 @@ public class QueryContexts
   public static final String SERIALIZE_DATE_TIME_AS_LONG_INNER_KEY = "serializeDateTimeAsLongInner";
   public static final String UNCOVERED_INTERVALS_LIMIT_KEY = "uncoveredIntervalsLimit";
   public static final String MIN_TOP_N_THRESHOLD = "minTopNThreshold";
-  public static final String FEDERATED_CLUSSTER_BROKERS = "federatedClusterBrokers";
+  public static final String FEDERATED_CLUSTER_BROKERS = "federatedClusterBrokers";
 
   // SQL query context keys
   public static final String CTX_SQL_QUERY_ID = BaseQuery.SQL_QUERY_ID;
diff --git a/server/src/main/java/org/apache/druid/client/CachingClusteredClient.java b/server/src/main/java/org/apache/druid/client/CachingClusteredClient.java
index aa776f8f3936..2629b4a6ce0f 100644
--- a/server/src/main/java/org/apache/druid/client/CachingClusteredClient.java
+++ b/server/src/main/java/org/apache/druid/client/CachingClusteredClient.java
@@ -24,6 +24,7 @@
 import com.google.common.annotations.VisibleForTesting;
 import com.google.common.base.Function;
 import com.google.common.base.Preconditions;
+import com.google.common.base.Strings;
 import com.google.common.collect.ImmutableMap;
 import com.google.common.collect.Iterables;
 import com.google.common.collect.Iterators;
@@ -680,8 +681,9 @@ private void addSequencesFromFederatedCluster(
         final List<Sequence<T>> listOfSequences
     )
     {
-      if (query.context().containsKey(QueryContexts.FEDERATED_CLUSSTER_BROKERS)) {
-        String[] brokers = query.context().getString(QueryContexts.FEDERATED_CLUSSTER_BROKERS).split(",");
+      String federatedClusterBrokersStr = query.context().getString(QueryContexts.FEDERATED_CLUSTER_BROKERS);
+      if (!Strings.isNullOrEmpty(federatedClusterBrokersStr)) {
+        String[] brokers = federatedClusterBrokersStr.split(",");
         for (String hostName : brokers) {
           if (hostName.length() > 0) {
             final QueryRunner serverRunner = serverView.getAndAddServer(hostName).getQueryRunner();
@@ -690,7 +692,7 @@ private void addSequencesFromFederatedCluster(
             final Sequence<T> serverResults = serverRunner.run(
                 queryPlus.withQuery(queryPlus.getQuery()
                                              .withOverriddenContext(ImmutableMap.of(
-                                                 QueryContexts.FEDERATED_CLUSSTER_BROKERS,
+                                                 QueryContexts.FEDERATED_CLUSTER_BROKERS,
                                                  ""
                                              )))
                          .withMaxQueuedBytes(maxQueuedBytes),
diff --git a/server/src/test/java/org/apache/druid/client/CachingClusteredClientTest.java b/server/src/test/java/org/apache/druid/client/CachingClusteredClientTest.java
index bdb0a3035600..64078955748b 100644
--- a/server/src/test/java/org/apache/druid/client/CachingClusteredClientTest.java
+++ b/server/src/test/java/org/apache/druid/client/CachingClusteredClientTest.java
@@ -3150,7 +3150,7 @@ public void testAddSequencesFromFederatedCluster()
   {
 
     Map<String, Object> context = new HashMap<>();
-    context.put(QueryContexts.FEDERATED_CLUSSTER_BROKERS, "test1");
+    context.put(QueryContexts.FEDERATED_CLUSTER_BROKERS, "test1");
     context.putAll(CONTEXT);
 
     final Druids.TimeseriesQueryBuilder builder = Druids.newTimeseriesQueryBuilder()