Update to Pinecone

{
  "name": "mcp",
  "description": "Reference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them, or what parameters they accept.",
  "included_files": [],
  "skill_md_contents": "---\nname: mcp\ndescription: Reference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them, or what parameters they accept.\n---\n\n# Pinecone MCP Tools Reference\n\nThe 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).\n\n> **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.\n\n---\n\n## `list-indexes`\n\nList all indexes in the current Pinecone project.\n\n---\n\n## `describe-index`\n\nGet configuration details for a specific index — cloud, region, dimension, metric, embedding model, field map, and status.\n\n**Parameters:**\n- `name` (required) — Index name\n\n---\n\n## `describe-index-stats`\n\nGet statistics for an index including total record count and per-namespace breakdown.\n\n**Parameters:**\n- `name` (required) — Index name\n\n---\n\n## `create-index-for-model`\n\nCreate a new serverless index with an integrated embedding model. Pinecone handles embedding automatically — no external model needed.\n\n**Parameters:**\n- `name` (required) — Index name\n- `cloud` (required) — `aws`, `gcp`, or `azure`\n- `region` (required) — Cloud region (e.g. `us-east-1`)\n- `embed.model` (required) — Embedding model: `llama-text-embed-v2`, `multilingual-e5-large`, or `pinecone-sparse-english-v0`\n- `embed.fieldMap.text` (required) — The record field that contains text to embed (e.g. `chunk_text`)\n\n---\n\n## `upsert-records`\n\nInsert or update records in an integrated index. Records are automatically embedded using the index's configured model.\n\n**Parameters:**\n- `name` (required) — Index name\n- `namespace` (required) — Namespace to upsert into\n- `records` (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.\n\n**Example record:**\n```json\n{ \"_id\": \"rec1\", \"chunk_text\": \"The Eiffel Tower was built in 1889.\", \"category\": \"architecture\" }\n```\n\n---\n\n## `search-records`\n\nSemantic text search against an integrated index. Pass plain text — the MCP embeds the query automatically using the index's model.\n\n**Parameters:**\n- `name` (required) — Index name\n- `namespace` (required) — Namespace to search\n- `query.inputs.text` (required) — The text query\n- `query.topK` (required) — Number of results to return\n- `query.filter` (optional) — Metadata filter using MongoDB-style operators (`$eq`, `$ne`, `$in`, `$gt`, `$gte`, `$lt`, `$lte`)\n- `rerank.model` (optional) — Reranking model: `bge-reranker-v2-m3`, `cohere-rerank-3.5`, or `pinecone-rerank-v0`\n- `rerank.rankFields` (optional) — Fields to rerank on (e.g. `[\"chunk_text\"]`)\n- `rerank.topN` (optional) — Number of results to return after reranking\n\n---\n\n## `cascading-search`\n\nSearch across multiple indexes simultaneously, then deduplicate and rerank results into a single ranked list.\n\n**Parameters:**\n- `indexes` (required) — Array of `{ name, namespace }` objects to search across\n- `query.inputs.text` (required) — The text query\n- `query.topK` (required) — Number of results to retrieve per index before reranking\n- `rerank.model` (required) — Reranking model: `bge-reranker-v2-m3`, `cohere-rerank-3.5`, or `pinecone-rerank-v0`\n- `rerank.rankFields` (required) — Fields to rerank on\n- `rerank.topN` (optional) — Final number of results to return after reranking\n\n---\n\n## `rerank-documents`\n\nRerank a set of documents or records against a query without performing a vector search first.\n\n**Parameters:**\n- `model` (required) — `bge-reranker-v2-m3`, `cohere-rerank-3.5`, or `pinecone-rerank-v0`\n- `query` (required) — The query to rerank against\n- `documents` (required) — Array of strings or records to rerank\n- `options.topN` (required) — Number of results to return\n- `options.rankFields` (optional) — If documents are records, the field(s) to rerank on\n"
}