npx claudepluginhub pinecone-io/pinecone-claude-code-plugin --plugin pineconeThis skill is limited to using the following tools:
The Pinecone MCP server exposes the following tools to AI agents and IDEs. For setup and installation instructions, see the [MCP server guide](https://docs.pinecone.io/guides/operations/mcp-server#tools).
Queries Pinecone integrated indexes using natural language text via MCP server. For indexes with built-in embeddings like multilingual-e5-large. Requires PINECONE_API_KEY and configured MCP.
Creates, manages, and queries Databricks Vector Search endpoints and indexes with filters and embeddings. Use for RAG apps, semantic search, similarity matching.
Provides setup and TypeScript examples for Upstash Vector DB: semantic search, namespaces, auto-embedding with MixBread. Use for vector search features on Vercel.
Share bugs, ideas, or general feedback.
The Pinecone MCP server exposes the following tools to AI agents and IDEs. For setup and installation instructions, see the MCP server guide.
Key Limitation: The Pinecone MCP only supports integrated indexes — indexes created with a built-in Pinecone embedding model. It does not work with standard indexes using external embedding models. For those, use the Pinecone CLI.
list-indexesList all indexes in the current Pinecone project.
describe-indexGet configuration details for a specific index — cloud, region, dimension, metric, embedding model, field map, and status.
Parameters:
name (required) — Index namedescribe-index-statsGet statistics for an index including total record count and per-namespace breakdown.
Parameters:
name (required) — Index namecreate-index-for-modelCreate a new serverless index with an integrated embedding model. Pinecone handles embedding automatically — no external model needed.
Parameters:
name (required) — Index namecloud (required) — aws, gcp, or azureregion (required) — Cloud region (e.g. us-east-1)embed.model (required) — Embedding model: llama-text-embed-v2, multilingual-e5-large, or pinecone-sparse-english-v0embed.fieldMap.text (required) — The record field that contains text to embed (e.g. chunk_text)upsert-recordsInsert or update records in an integrated index. Records are automatically embedded using the index's configured model.
Parameters:
name (required) — Index namenamespace (required) — Namespace to upsert intorecords (required) — Array of records. Each record must have an id or _id field and contain the text field specified in the index's fieldMap. Do not nest fields under metadata — put them directly on the record.Example record:
{ "_id": "rec1", "chunk_text": "The Eiffel Tower was built in 1889.", "category": "architecture" }
search-recordsSemantic text search against an integrated index. Pass plain text — the MCP embeds the query automatically using the index's model.
Parameters:
name (required) — Index namenamespace (required) — Namespace to searchquery.inputs.text (required) — The text queryquery.topK (required) — Number of results to returnquery.filter (optional) — Metadata filter using MongoDB-style operators ($eq, $ne, $in, $gt, $gte, $lt, $lte)rerank.model (optional) — Reranking model: bge-reranker-v2-m3, cohere-rerank-3.5, or pinecone-rerank-v0rerank.rankFields (optional) — Fields to rerank on (e.g. ["chunk_text"])rerank.topN (optional) — Number of results to return after rerankingcascading-searchSearch across multiple indexes simultaneously, then deduplicate and rerank results into a single ranked list.
Parameters:
indexes (required) — Array of { name, namespace } objects to search acrossquery.inputs.text (required) — The text queryquery.topK (required) — Number of results to retrieve per index before rerankingrerank.model (required) — Reranking model: bge-reranker-v2-m3, cohere-rerank-3.5, or pinecone-rerank-v0rerank.rankFields (required) — Fields to rerank onrerank.topN (optional) — Final number of results to return after rerankingrerank-documentsRerank a set of documents or records against a query without performing a vector search first.
Parameters:
model (required) — bge-reranker-v2-m3, cohere-rerank-3.5, or pinecone-rerank-v0query (required) — The query to rerank againstdocuments (required) — Array of strings or records to rerankoptions.topN (required) — Number of results to returnoptions.rankFields (optional) — If documents are records, the field(s) to rerank on