Can I use Milvus as a CLI?

Yes. KosmoKrator exposes a Milvus CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Milvus through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Milvus tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Milvus credentials stored?

Milvus credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Milvus MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

data

Milvus CLI for AI Agents

Use the Milvus CLI from KosmoKrator to call Milvus tools headlessly, return JSON, inspect schemas, and automate workflows from coding agents, scripts, and CI.

Milvus CLI Setup

Milvus can be configured headlessly with `kosmokrator integrations:configure milvus`.

Install, configure, and verify

# Install KosmoKrator first if it is not available on PATH.
curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash

# Configure and verify this integration.
kosmokrator integrations:configure milvus --set api_key="$MILVUS_API_KEY" --enable --read allow --write ask --json
kosmokrator integrations:doctor milvus --json
kosmokrator integrations:status --json

Credentials

Authentication type: API key api_key. Configure credentials once, then reuse the same stored profile from scripts, coding CLIs, Lua, and MCP.

Key	Env var	Type	Required	Label
`api_key`	`MILVUS_API_KEY`	Secret `secret`	yes	API Key
`url`	`MILVUS_URL`	URL `url`	no	Milvus API URL

Command Patterns

The generic command is stable across every integration. The provider shortcut is shorter for humans.

Generic CLI call

kosmo integrations:call milvus.milvus_list_collections '{"limit":1,"offset":1}' --json

Provider shortcut

kosmo integrations:milvus milvus_list_collections '{"limit":1,"offset":1}' --json

Discovery

These commands return structured output for coding agents that need to inspect capabilities before choosing a function.

Discovery commands

kosmo integrations:docs milvus --json
kosmo integrations:docs milvus.milvus_list_collections --json
kosmo integrations:schema milvus.milvus_list_collections --json
kosmo integrations:search "Milvus" --json
kosmo integrations:list --json

Automation Contexts

The same configured command surface works in these environments. The command does not change unless the host wrapper, credentials, or permissions change.

CI Run integration calls from CI jobs with JSON output, explicit credentials, and predictable exit status. Cron Jobs Schedule repeatable integration workflows from cron while keeping credentials in KosmoKrator config. Shell Scripts Call integration functions from shell scripts with stable JSON input and output. Headless Automation Use KosmoKrator as a non-interactive integration runtime for local automations and wrappers. Coding Agents Let coding agents discover schemas and execute integration functions through CLI commands or MCP.

CLI Functions

Every function below can be called headlessly. Commands are highlighted, copyable, and scroll horizontally when payloads are long.

`milvus.milvus_list_collections`

List all vector collections in Milvus. Returns collection names and details that can be used for further operations.

Read read

Parameters: limit, offset

Generic call

kosmo integrations:call milvus.milvus_list_collections '{"limit":1,"offset":1}' --json

Shortcut

kosmo integrations:milvus milvus_list_collections '{"limit":1,"offset":1}' --json

`milvus.milvus_get_collection`

Get details of a specific Milvus collection by its name, including schema and description.

Read read

Parameters: collection_name

Generic call

kosmo integrations:call milvus.milvus_get_collection '{"collection_name":"example_collection_name"}' --json

Shortcut

kosmo integrations:milvus milvus_get_collection '{"collection_name":"example_collection_name"}' --json

`milvus.milvus_create_collection`

Create a new vector collection in Milvus. A collection requires a name and the embedding dimension size.

Write write

Parameters: name, dimension, description, params

Generic call

kosmo integrations:call milvus.milvus_create_collection '{"name":"example_name","dimension":1,"description":"example_description","params":"example_params"}' --json

Shortcut

kosmo integrations:milvus milvus_create_collection '{"name":"example_name","dimension":1,"description":"example_description","params":"example_params"}' --json

`milvus.milvus_insert_documents`

Insert documents with embedding vectors into a Milvus collection. Each document requires a vector and an optional ID.

Write write

Parameters: collection_name, data

Generic call

kosmo integrations:call milvus.milvus_insert_documents '{"collection_name":"example_collection_name","data":"example_data"}' --json

Shortcut

kosmo integrations:milvus milvus_insert_documents '{"collection_name":"example_collection_name","data":"example_data"}' --json

`milvus.milvus_search_documents`

Search for similar documents in a Milvus collection using a query vector. Returns the most similar documents ranked by distance or similarity.

Read read

Parameters: collection_name, vector, limit, output_fields, filter

Generic call

kosmo integrations:call milvus.milvus_search_documents '{"collection_name":"example_collection_name","vector":"example_vector","limit":1,"output_fields":"example_output_fields","filter":"example_filter"}' --json

Shortcut

kosmo integrations:milvus milvus_search_documents '{"collection_name":"example_collection_name","vector":"example_vector","limit":1,"output_fields":"example_output_fields","filter":"example_filter"}' --json

`milvus.milvus_get_collection_stats`

Get statistics for a Milvus collection, including row count and index information.

Read read

Parameters: collection_name

Generic call

kosmo integrations:call milvus.milvus_get_collection_stats '{"collection_name":"example_collection_name"}' --json

Shortcut

kosmo integrations:milvus milvus_get_collection_stats '{"collection_name":"example_collection_name"}' --json

`milvus.milvus_get_health`

Check the health status of the Milvus vector database server. Returns health and version information.

Read read

Parameters: none

Generic call

kosmo integrations:call milvus.milvus_get_health '{}' --json

Shortcut

kosmo integrations:milvus milvus_get_health '{}' --json

Function Schemas

Use these parameter tables when building CLI payloads without calling integrations:schema first.

milvus.milvus_list_collections 2 parameters

Schema command

kosmo integrations:schema milvus.milvus_list_collections --json

Parameter	Type	Required	Description
`limit`	integer	no	Maximum number of collections to return (default: 100).
`offset`	integer	no	Number of collections to skip for pagination.

milvus.milvus_get_collection 1 parameters

Schema command

kosmo integrations:schema milvus.milvus_get_collection --json

Parameter	Type	Required	Description
`collection_name`	string	yes	The name of the collection.

milvus.milvus_create_collection 4 parameters

Schema command

kosmo integrations:schema milvus.milvus_create_collection --json

Parameter	Type	Required	Description
`name`	string	yes	The name of the collection to create.
`dimension`	integer	yes	The dimension of the embedding vectors to be stored in this collection.
`description`	string	no	An optional description of the collection.
`params`	object	no	Optional collection parameters such as index type and metric type (JSON object).

milvus.milvus_insert_documents 2 parameters

Schema command

kosmo integrations:schema milvus.milvus_insert_documents --json

Parameter	Type	Required	Description
`collection_name`	string	yes	The name of the collection to insert into.
`data`	array	yes	Array of document objects. Each object should contain a "vector" field (array of floats) and optional "id", "color", or other scalar fields.

milvus.milvus_search_documents 5 parameters

Schema command

kosmo integrations:schema milvus.milvus_search_documents --json

Parameter	Type	Required	Description
`collection_name`	string	yes	The name of the collection to search.
`vector`	array	yes	The query embedding vector (array of floats).
`limit`	integer	no	Maximum number of results to return (default: 10).
`output_fields`	array	no	Fields to include in the response, e.g. ["id", "color", "text"].
`filter`	string	no	Filter expression for scalar fields, e.g. 'color == "red"'.

milvus.milvus_get_collection_stats 1 parameters

Schema command

kosmo integrations:schema milvus.milvus_get_collection_stats --json

Parameter	Type	Required	Description
`collection_name`	string	yes	The name of the collection.

milvus.milvus_get_health 0 parameters

Schema command

kosmo integrations:schema milvus.milvus_get_health --json

Parameter	Type	Required	Description
No parameters.

Permissions

Headless calls still follow the integration read/write permission policy. Configure read/write defaults with integrations:configure. Add --force only for trusted automation that should bypass that policy.