Skip to content

MCP tool reference

The Aerospike Voyager MCP server exposes the following tools to AI coding agents. Tools are organized by category. The Browse and read only and All tools enabled columns indicate which access profile includes each tool.

Response shape

Every tool call returns two complementary views in the MCP response:

  • content[0].text: a formatted, human-readable rendering. Most MCP clients (Claude Desktop, Cursor) display this to the user.
  • structuredContent: the same data as a JSON object. AI agents that support structured content can consume this directly without parsing text.

Example (get_record):

{
"content": [{
"type": "text",
"text": "Record:\n Key: user8 | Digest: 00d8... | Partition: 2048 | Node: BB9C5F97288A0D6\n Generation: 1 | TTL: namespace default\n\n Bins (7):\n active [bool ] false\n age [int ] 43\n ..."
}],
"structuredContent": {
"key": "user8",
"digest": "00d8362e4cac83f58f538f81d8d8a3f8ec8fbacc",
"node": "BB9C5F97288A0D6",
"partitionId": 2048,
"generation": 1,
"expiration": 0,
"bins": {
"active": { "type": "bool", "value": false },
"age": { "type": "int", "value": 43 },
...
}
}
}

Connection management

ToolDescriptionBrowse and read onlyAll tools enabled
list_connectionsList all saved connectionsYesYes
get_connectionGet details of a specific connectionYesYes
create_connectionCreate a new cluster connectionNoYes
update_connectionUpdate an existing connectionNoYes
delete_connectionDelete a saved connectionNoYes
connectConnect to a saved clusterYesYes
disconnectDisconnect from a clusterYesYes
test_connectionTest connectivity to a clusterYesYes

Cluster browsing

ToolDescriptionBrowse and read onlyAll tools enabled
list_namespacesList all namespaces in the connected clusterYesYes
list_setsList all sets in a namespaceYesYes
get_nodesGet cluster node informationYesYes

Record operations

ToolDescriptionBrowse and read onlyAll tools enabled
get_recordRead a record by key or digestYesYes
record_existsCheck if a record existsYesYes
queryScan or filter records; paginated (see below)YesYes
create_recordCreate a new recordNoYes
update_recordUpdate an existing recordNoYes
delete_recordDelete a recordNoYes
delete_binDelete a bin from a recordNoYes
truncate_setRemove all records from a setNoYes

Cluster info

ToolDescriptionBrowse and read onlyAll tools enabled
execute_infoRun an info command on the clusterNoYes
execute_info_on_nodeRun an info command on a specific nodeNoYes

Query pagination

The query tool paginates results automatically. Defaults and limits:

  • Default page size: 20 records
  • Maximum page size: 256 records (set via policy.maxRecords)
  • Pagination cursor: the server returns a nextPageToken in structuredContent when more records are available. Pass it as the pageToken argument on the next call to fetch the next page.
  • Text signal: the human-readable summary includes “(more pages available)” when additional pages exist.

The nextPageToken is a large hex-encoded binary cursor (typically 50+ KB). Store it verbatim; do not truncate or modify.

Supported bin types

Write operations (create_record, update_record) accept bins as typed BinInput objects:

{ "name": "age", "type": "int", "value": 30 }

Supported type values: int, float, string, bool, blob, list, map, geo, nil.

Errors

Errors are returned with isError: true in the MCP result. The text content is a human-readable message that includes a short summary, additional detail where relevant, and remediation guidance.

Common error categories you may encounter:

  • Internal errors, including profile-blocked tool calls and unhealthy connections.
  • Query timeouts or cancellations — narrow the filter or add a secondary index.

Next steps

Feedback

Was this page helpful?

What type of feedback are you giving?

What would you like us to know?

+Capture screenshot

Can we reach out to you?