2026-09-09 10:24Z
additive
Jina AI
Jina AI added to the registry — baseline recorded with 22 tools
https://mcp.jina.ai/sse
Fingerprint 1be9de82fe97c6fd · first seen 2026-09-09 ·
last checked 2026-09-09.
Vendor documentation.
Provenance Read from the declared URL with no redirect, over a direct POST. The response was an SSE-framed JSON-RPC result.
Everything this registry has observed for this endpoint.
As returned by tools/list on the last successful pulse.
Read from the declared URL with no redirect, over a direct POST. The response was an SSE-framed JSON-RPC result.
Screenshot a page as base64 JPEG. Use when the page must be seen rather than read.
Classify texts into labels you supply, using Jina embeddings. Zero-shot: no training data needed.
Select the top-k visually distinct images (URLs or base64) from a list, dropping near-duplicates.
Select the top-k semantically distinct strings from a list, dropping near-duplicates.
Rewrite one query into several diverse queries, for broader search coverage.
Extract figures, tables and equations from a PDF as images, by arXiv id or URL.
Guess when a page was published or last updated, with a confidence score. Checks HTTP headers, metadata, Schema.org, visible dates, feeds and sitemaps.
Read several URLs at once.
Run several arXiv searches at once. Give queries covering different research angles.
Run several SSRN searches at once. Give queries covering different research angles.
Run several web searches at once. Give queries covering different angles of the topic; expand_query can generate them.
Current time, user location and network environment for the session. Use before answering anything time- or location-dependent.
No parameters.
Fetch a URL (page or PDF) as clean markdown. Pass `question` to get only the passages answering it instead of the whole page - far cheaper than reading the full body into context.
Search arXiv preprints (physics, maths, CS, quantitative biology and finance).
Find papers and return ready-to-use BibTeX entries. Searches DBLP and Semantic Scholar.
Search the web for images. Returns base64 JPEGs by default.
Search Jina AI's news and blog at jina.ai/news: product announcements, model releases, technical write-ups.
Search SSRN working papers (social science, economics, law, finance, management).
Search the web. Returns titles, URLs and search-engine snippets.
Search the web, then read each result page and return the passage that best answers the query. Use when the answer is in page text rather than in titles or snippets. Slower than search_web (2-20s).
Return the bearer token from MCP settings. For debugging.
No parameters.
Rerank documents by relevance to a query, using Jina Reranker.
GET https://he110.github.io/mcp-drift-registry/api/servers/jina.json