ai
Jina AI MCP Integration for Generic MCP Clients
Connect Jina AI to Generic MCP Clients through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.
Connect Jina AI to Generic MCP Clients
Connect any stdio-compatible MCP client to local KosmoKrator integration tools.
Register kosmo mcp:serve as the command for a local stdio MCP server. The gateway is local, scoped to this integration, and starts with
--write=deny so MCP clients can inspect read-capable tools without receiving write access by default.
Jina AI MCP Config for Generic MCP Clients
Start with read-only write policy and expand only for trusted projects.
{
"mcpServers": {
"kosmokrator-jinaai": {
"type": "stdio",
"command": "kosmo",
"args": [
"mcp:serve",
"--integration=jinaai",
"--write=deny"
]
}
}
} Run the Gateway Manually
kosmokrator mcp:serve --integration=jinaai --write=deny Why Use KosmoKrator Here
Expose only Jina AI instead of a broad multi-service tool list.
Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.
Start read-only, then opt into ask or allow for trusted workspaces.
Jina AI Tools Visible to MCP clients
MCP clients sees stable MCP tool names generated from the Jina AI integration catalog.
| MCP tool | Source function | Type | Description |
|---|---|---|---|
integration__jinaai__jinaai_search | jinaai.jinaai_search | Read | 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. |
integration__jinaai__jinaai_read | jinaai.jinaai_read | 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. |
integration__jinaai__jinaai_ground | jinaai.jinaai_ground | Read | 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. |
integration__jinaai__jinaai_embeddings | jinaai.jinaai_embeddings | Read | Generate text embeddings using Jina AI. Converts text into dense vector representations useful for semantic search, similarity comparison, clustering, and retrieval-augmented generation (RAG). |
integration__jinaai__jinaai_rerank | jinaai.jinaai_rerank | Read | 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. |