Can I use Jina AI as a CLI?

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

Can I expose Jina AI through MCP?

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

Where are Jina AI credentials stored?

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

Can I deny write access for Jina AI MCP tools?

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

data

Jina AI CLI for AI Agents

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

Jina AI CLI Setup

Jina AI can be configured headlessly with `kosmokrator integrations:configure jinaai`.

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 jinaai --set api_key="$JINAAI_API_KEY" --enable --read allow --write ask --json
kosmokrator integrations:doctor jinaai --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`	`JINAAI_API_KEY`	Secret `secret`	yes	API Key
`url`	`JINAAI_URL`	URL `url`	no	API Base URL

Command Patterns

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

Generic CLI call

kosmo integrations:call jinaai.jinaai_search '{"q":"example_q"}' --json

Provider shortcut

kosmo integrations:jinaai jinaai_search '{"q":"example_q"}' --json

Discovery

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

Discovery commands

kosmo integrations:docs jinaai --json
kosmo integrations:docs jinaai.jinaai_search --json
kosmo integrations:schema jinaai.jinaai_search --json
kosmo integrations:search "Jina AI" --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.

`jinaai.jinaai_search`

Search the web using Jina AI. Returns search results with titles, URLs, descriptions, and extracted content. Useful for finding up-to-date information on any topic.

Read read

Parameters: q

Generic call

kosmo integrations:call jinaai.jinaai_search '{"q":"example_q"}' --json

Shortcut

kosmo integrations:jinaai jinaai_search '{"q":"example_q"}' --json

`jinaai.jinaai_read`

Read and extract clean content from a URL using Jina AI Reader. Returns the main text content of a web page, stripping away navigation, ads, and other clutter. Useful for reading articles, documentation, or any web page.

Read read

Parameters: url

Generic call

kosmo integrations:call jinaai.jinaai_read '{"url":"example_url"}' --json

Shortcut

kosmo integrations:jinaai jinaai_read '{"url":"example_url"}' --json

`jinaai.jinaai_ground`

Ground a statement against provided context using Jina AI. Verifies whether a claim or statement is supported by the given reference text. Returns grounding results indicating which parts of the statement are supported or contradicted.

Read read

Parameters: statement, references, context

Generic call

kosmo integrations:call jinaai.jinaai_ground '{"statement":"example_statement","references":"example_references","context":"example_context"}' --json

Shortcut

kosmo integrations:jinaai jinaai_ground '{"statement":"example_statement","references":"example_references","context":"example_context"}' --json

`jinaai.jinaai_embeddings`

Generate text embeddings using Jina AI. Converts text into dense vector representations useful for semantic search, similarity comparison, clustering, and retrieval-augmented generation (RAG).

Read read

Parameters: input, model

Generic call

kosmo integrations:call jinaai.jinaai_embeddings '{"input":"example_input","model":"example_model"}' --json

Shortcut

kosmo integrations:jinaai jinaai_embeddings '{"input":"example_input","model":"example_model"}' --json

`jinaai.jinaai_rerank`

Rerank documents by relevance to a query using Jina AI. Takes a query and a list of text documents, then returns them sorted by relevance with scores. Useful for improving search results or filtering the most relevant content.

Read read

Parameters: query, documents, model, top_n

Generic call

kosmo integrations:call jinaai.jinaai_rerank '{"query":"example_query","documents":"example_documents","model":"example_model","top_n":1}' --json

Shortcut

kosmo integrations:jinaai jinaai_rerank '{"query":"example_query","documents":"example_documents","model":"example_model","top_n":1}' --json

`jinaai.jinaai_classify`

Classify text or image inputs using Jina AI Classifier. Provide labels for zero-shot classification or classifier configuration for few-shot classification.

Read read

Parameters: input, labels, model, classifier_id, top_k

Generic call

kosmo integrations:call jinaai.jinaai_classify '{"input":"example_input","labels":"example_labels","model":"example_model","classifier_id":"example_classifier_id","top_k":1}' --json

Shortcut

kosmo integrations:jinaai jinaai_classify '{"input":"example_input","labels":"example_labels","model":"example_model","classifier_id":"example_classifier_id","top_k":1}' --json

`jinaai.jinaai_segment`

Tokenize or segment long text using Jina AI Segmenter before embedding, reranking, or LLM processing.

Read read

Parameters: content, tokenizer, return_tokens, return_chunks, max_chunk_length

Generic call

kosmo integrations:call jinaai.jinaai_segment '{"content":"example_content","tokenizer":"example_tokenizer","return_tokens":true,"return_chunks":true,"max_chunk_length":1}' --json

Shortcut

kosmo integrations:jinaai jinaai_segment '{"content":"example_content","tokenizer":"example_tokenizer","return_tokens":true,"return_chunks":true,"max_chunk_length":1}' --json

Function Schemas

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

jinaai.jinaai_search 1 parameters

Schema command

kosmo integrations:schema jinaai.jinaai_search --json

Parameter	Type	Required	Description
`q`	string	yes	The search query string.

jinaai.jinaai_read 1 parameters

Schema command

kosmo integrations:schema jinaai.jinaai_read --json

Parameter	Type	Required	Description
`url`	string	yes	The URL to read and extract content from.

jinaai.jinaai_ground 3 parameters

Schema command

kosmo integrations:schema jinaai.jinaai_ground --json

Parameter	Type	Required	Description
`statement`	string	yes	The statement or claim to verify.
`references`	array	no	Optional references or URLs to restrict grounding sources.
`context`	string	no	Deprecated compatibility field. Prefer references when restricting sources.

jinaai.jinaai_embeddings 2 parameters

Schema command

kosmo integrations:schema jinaai.jinaai_embeddings --json

Parameter	Type	Required	Description
`input`	array	yes	An array of strings to generate embeddings for. Each string is embedded independently.
`model`	string	no	The embedding model to use (e.g., "jina-embeddings-v3"). Defaults to the Jina AI default model.

jinaai.jinaai_rerank 4 parameters

Schema command

kosmo integrations:schema jinaai.jinaai_rerank --json

Parameter	Type	Required	Description
`query`	string	yes	The query to rank documents against.
`documents`	array	yes	An array of document strings to rank by relevance to the query.
`model`	string	no	The reranking model to use (e.g., "jina-reranker-v2-base-multilingual"). Defaults to the Jina AI default model.
`top_n`	integer	no	Maximum number of top results to return. Defaults to all documents.

jinaai.jinaai_classify 5 parameters

Schema command

kosmo integrations:schema jinaai.jinaai_classify --json

Parameter	Type	Required	Description
`input`	array	yes	Inputs to classify. Text inputs may be strings or objects accepted by Jina.
`labels`	array	no	Zero-shot classification labels.
`model`	string	no	Embedding or classifier model id.
`classifier_id`	string	no	Few-shot classifier id when using a trained classifier.
`top_k`	integer	no	Maximum labels per input to return.

jinaai.jinaai_segment 5 parameters

Schema command

kosmo integrations:schema jinaai.jinaai_segment --json

Parameter	Type	Required	Description
`content`	string	yes	Text content to tokenize or segment.
`tokenizer`	string	no	Tokenizer or model-compatible tokenizer to use.
`return_tokens`	boolean	no	Whether to include token text in the response.
`return_chunks`	boolean	no	Whether to include segmented chunks in the response.
`max_chunk_length`	integer	no	Maximum chunk length when chunking is enabled.

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.