KosmoKrator

database

Pinecone CLI for AI Agents

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

7 functions 5 read 2 write Bearer token auth
Submit Pinecone feedback View package source

Pinecone CLI Setup

Pinecone can be configured headlessly with `kosmokrator integrations:configure pinecone`.

# 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 pinecone --set access_token="$PINECONE_ACCESS_TOKEN" --enable --read allow --write ask --json
kosmokrator integrations:doctor pinecone --json
kosmokrator integrations:status --json

Credentials

Authentication type: Bearer token bearer_token. Configure credentials once, then use the same stored profile from scripts, coding CLIs, Lua code mode, and the MCP gateway.

KeyEnv varTypeRequiredLabel
access_token PINECONE_ACCESS_TOKEN Secret secret yes Access Token
url PINECONE_URL URL url no Pinecone API URL

Call Pinecone Headlessly

Use the generic call form when another coding CLI or script needs a stable universal interface.

kosmo integrations:call pinecone.pinecone_list_indexes '{}' --json

Use the provider shortcut form for shorter human-facing commands.

kosmo integrations:pinecone pinecone_list_indexes '{}' --json

Agent Discovery Commands

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

kosmo integrations:docs pinecone --json
kosmo integrations:docs pinecone.pinecone_list_indexes --json
kosmo integrations:schema pinecone.pinecone_list_indexes --json
kosmo integrations:search "Pinecone" --json
kosmo integrations:list --json

All CLI Functions

Every function below can be called headlessly. The generic form is stable across all integrations; the provider shortcut is shorter but specific to Pinecone.

pinecone.pinecone_list_indexes

Read read

List all vector indexes in your Pinecone project. Returns index names, dimensions, metrics, and status.

Parameters
none

Generic CLI call

kosmo integrations:call pinecone.pinecone_list_indexes '{}' --json

Provider shortcut

kosmo integrations:pinecone pinecone_list_indexes '{}' --json

pinecone.pinecone_get_index

Read read

Get detailed information about a specific Pinecone vector index, including its dimension, metric, host URL, and status.

Parameters
name

Generic CLI call

kosmo integrations:call pinecone.pinecone_get_index '{"name":"example_name"}' --json

Provider shortcut

kosmo integrations:pinecone pinecone_get_index '{"name":"example_name"}' --json

pinecone.pinecone_create_index

Write write

Create a new serverless vector index in Pinecone. Specify the index name, vector dimension, and similarity metric (cosine, euclidean, or dotproduct).

Parameters
name, dimension, metric

Generic CLI call

kosmo integrations:call pinecone.pinecone_create_index '{"name":"example_name","dimension":1,"metric":"example_metric"}' --json

Provider shortcut

kosmo integrations:pinecone pinecone_create_index '{"name":"example_name","dimension":1,"metric":"example_metric"}' --json

pinecone.pinecone_upsert_vectors

Write write

Upsert vectors into a Pinecone index using an index host URL.

Parameters
index_host, vectors

Generic CLI call

kosmo integrations:call pinecone.pinecone_upsert_vectors '{"index_host":"example_index_host","vectors":"example_vectors"}' --json

Provider shortcut

kosmo integrations:pinecone pinecone_upsert_vectors '{"index_host":"example_index_host","vectors":"example_vectors"}' --json

pinecone.pinecone_query_vectors

Read read

Search for similar vectors in a Pinecone index using a query embedding.

Parameters
index_host, vector, top_k, filter, include_metadata

Generic CLI call

kosmo integrations:call pinecone.pinecone_query_vectors '{"index_host":"example_index_host","vector":"example_vector","top_k":1,"filter":"example_filter","include_metadata":true}' --json

Provider shortcut

kosmo integrations:pinecone pinecone_query_vectors '{"index_host":"example_index_host","vector":"example_vector","top_k":1,"filter":"example_filter","include_metadata":true}' --json

pinecone.pinecone_list_collections

Read read

List all collections in your Pinecone project. Collections are static snapshots of indexes used for backups or creating new indexes.

Parameters
none

Generic CLI call

kosmo integrations:call pinecone.pinecone_list_collections '{}' --json

Provider shortcut

kosmo integrations:pinecone pinecone_list_collections '{}' --json

pinecone.pinecone_get_current_user

Read read

Get information about the currently authenticated Pinecone user, including email, name, and project details.

Parameters
none

Generic CLI call

kosmo integrations:call pinecone.pinecone_get_current_user '{}' --json

Provider shortcut

kosmo integrations:pinecone pinecone_get_current_user '{}' --json

Function Schemas

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

pinecone.pinecone_list_indexes

List all vector indexes in your Pinecone project. Returns index names, dimensions, metrics, and status.

Operation
Read read
Schema command
kosmo integrations:schema pinecone.pinecone_list_indexes --json
ParameterTypeRequiredDescription
No parameters.

pinecone.pinecone_get_index

Get detailed information about a specific Pinecone vector index, including its dimension, metric, host URL, and status.

Operation
Read read
Schema command
kosmo integrations:schema pinecone.pinecone_get_index --json
ParameterTypeRequiredDescription
name string yes The name of the index to retrieve.

pinecone.pinecone_create_index

Create a new serverless vector index in Pinecone. Specify the index name, vector dimension, and similarity metric (cosine, euclidean, or dotproduct).

Operation
Write write
Schema command
kosmo integrations:schema pinecone.pinecone_create_index --json
ParameterTypeRequiredDescription
name string yes The name for the new index. Must be unique within the project.
dimension integer yes The dimension size of the vectors to be stored (e.g., 1536 for OpenAI text-embedding-ada-002, 3072 for text-embedding-3-large).
metric string no The similarity metric to use: "cosine" (default), "euclidean", or "dotproduct".

pinecone.pinecone_upsert_vectors

Upsert vectors into a Pinecone index using an index host URL.

Operation
Write write
Schema command
kosmo integrations:schema pinecone.pinecone_upsert_vectors --json
ParameterTypeRequiredDescription
index_host string yes The index host URL, such as "https://example.svc.us-east-1.pinecone.io".
vectors array yes Vector records with id, values, and optional metadata.

pinecone.pinecone_query_vectors

Search for similar vectors in a Pinecone index using a query embedding.

Operation
Read read
Schema command
kosmo integrations:schema pinecone.pinecone_query_vectors --json
ParameterTypeRequiredDescription
index_host string yes The index host URL.
vector array yes Query embedding vector values.
top_k integer no Number of top matches to return (default: 10).
filter object no Optional metadata filter expression.
include_metadata boolean no Whether to include metadata in matches (default: true).

pinecone.pinecone_list_collections

List all collections in your Pinecone project. Collections are static snapshots of indexes used for backups or creating new indexes.

Operation
Read read
Schema command
kosmo integrations:schema pinecone.pinecone_list_collections --json
ParameterTypeRequiredDescription
No parameters.

pinecone.pinecone_get_current_user

Get information about the currently authenticated Pinecone user, including email, name, and project details.

Operation
Read read
Schema command
kosmo integrations:schema pinecone.pinecone_get_current_user --json
ParameterTypeRequiredDescription
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.