pinecone-mcp

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Pinecone MCP Tools Reference

Pinecone MCP 工具参考

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.

Pinecone MCP server 向 AI Agent 和 IDE 提供以下工具。有关设置和安装说明,请参阅 MCP server 指南。
关键限制: Pinecone MCP 仅支持集成索引——即使用内置 Pinecone embedding 模型创建的索引。它不支持使用外部 embedding 模型的标准索引。对于此类索引,请使用 Pinecone CLI。

list-indexes

list-indexes

List all indexes in the current Pinecone project.

列出当前 Pinecone 项目中的所有索引。

describe-index

describe-index

Get configuration details for a specific index — cloud, region, dimension, metric, embedding model, field map, and status.
Parameters:
  • name
    (required) — Index name

获取指定索引的配置详情,包括云、区域、维度、度量指标、embedding 模型、字段映射和状态。
参数:
  • name
    (必填)— 索引名称

describe-index-stats

describe-index-stats

Get statistics for an index including total record count and per-namespace breakdown.
Parameters:
  • name
    (required) — Index name

获取索引的统计信息,包括总记录数以及按 namespace 细分的数据。
参数:
  • name
    (必填)— 索引名称

create-index-for-model

create-index-for-model

Create a new serverless index with an integrated embedding model. Pinecone handles embedding automatically — no external model needed.
Parameters:
  • name
    (required) — Index name
  • cloud
    (required) —
    aws
    ,
    gcp
    , or
    azure
  • region
    (required) — Cloud region (e.g.
    us-east-1
    )
  • embed.model
    (required) — Embedding model:
    llama-text-embed-v2
    ,
    multilingual-e5-large
    , or
    pinecone-sparse-english-v0
  • embed.fieldMap.text
    (required) — The record field that contains text to embed (e.g.
    chunk_text
    )

使用集成 embedding 模型创建新的 serverless 索引。Pinecone 会自动处理 embedding,无需使用外部模型。
参数:
  • name
    (必填)— 索引名称
  • cloud
    (必填)—
    aws
    、
    gcp
    或
    azure
  • region
    (必填)— 云区域(例如
    us-east-1
    )
  • embed.model
    (必填)— Embedding 模型:
    llama-text-embed-v2
    、
    multilingual-e5-large
    或
    pinecone-sparse-english-v0
  • embed.fieldMap.text
    (必填)— 包含待 embedding 文本的记录字段(例如
    chunk_text
    )

upsert-records

upsert-records

Insert or update records in an integrated index. Records are automatically embedded using the index's configured model.
Parameters:
  • name
    (required) — Index name
  • namespace
    (required) — Namespace to upsert into
  • 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.
Example record:
json
{ "_id": "rec1", "chunk_text": "The Eiffel Tower was built in 1889.", "category": "architecture" }

在集成索引中插入或更新记录。系统会使用索引配置的模型自动为记录生成 embedding。
参数:
  • name
    (必填)— 索引名称
  • namespace
    (必填)— 要写入的 namespace
  • records
    (必填)— 记录数组。每条记录必须包含
    id
    或
    _id
    字段,并包含索引
    fieldMap
    中指定的文本字段。不要将字段嵌套在
    metadata
    下,应直接放在记录顶层。
记录示例:
json
{ "_id": "rec1", "chunk_text": "The Eiffel Tower was built in 1889.", "category": "architecture" }

search-records

search-records

Semantic text search against an integrated index. Pass plain text — the MCP embeds the query automatically using the index's model.
Parameters:
  • name
    (required) — Index name
  • namespace
    (required) — Namespace to search
  • query.inputs.text
    (required) — The text query
  • query.topK
    (required) — Number of results to return
  • query.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-v0
  • rerank.rankFields
    (optional) — Fields to rerank on (e.g.
    ["chunk_text"]
    )
  • rerank.topN
    (optional) — Number of results to return after reranking

针对集成索引执行语义文本搜索。传入纯文本即可——MCP 会使用索引的模型自动为查询生成 embedding。
参数:
  • name
    (必填)— 索引名称
  • namespace
    (必填)— 要搜索的 namespace
  • query.inputs.text
    (必填)— 文本查询
  • query.topK
    (必填)— 返回的结果数量
  • query.filter
    (可选)— 使用 MongoDB 风格运算符(
    $eq
    、
    $ne
    、
    $in
    、
    $gt
    、
    $gte
    、
    $lt
    、
    $lte
    )的元数据过滤器
  • rerank.model
    (可选)— 重排序模型:
    bge-reranker-v2-m3
    、
    cohere-rerank-3.5
    或
    pinecone-rerank-v0
  • rerank.rankFields
    (可选)— 用于重排序的字段(例如
    ["chunk_text"]
    )
  • rerank.topN
    (可选)— 重排序后返回的结果数量

cascading-search

cascading-search

Search across multiple indexes simultaneously, then deduplicate and rerank results into a single ranked list.
Parameters:
  • indexes
    (required) — Array of
    { name, namespace }
    objects to search across
  • query.inputs.text
    (required) — The text query
  • query.topK
    (required) — Number of results to retrieve per index before reranking
  • rerank.model
    (required) — Reranking model:
    bge-reranker-v2-m3
    ,
    cohere-rerank-3.5
    , or
    pinecone-rerank-v0
  • rerank.rankFields
    (required) — Fields to rerank on
  • rerank.topN
    (optional) — Final number of results to return after reranking

同时搜索多个索引,然后对结果去重并重排序,合并为单个排名列表。
参数:
  • indexes
    (必填)— 要搜索的
    { name, namespace }
    对象数组
  • query.inputs.text
    (必填)— 文本查询
  • query.topK
    (必填)— 重排序前从每个索引获取的结果数量
  • rerank.model
    (必填)— 重排序模型:
    bge-reranker-v2-m3
    、
    cohere-rerank-3.5
    或
    pinecone-rerank-v0
  • rerank.rankFields
    (必填)— 用于重排序的字段
  • rerank.topN
    (可选)— 重排序后最终返回的结果数量

rerank-documents

rerank-documents

Rerank 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-v0
  • query
    (required) — The query to rerank against
  • documents
    (required) — Array of strings or records to rerank
  • options.topN
    (required) — Number of results to return
  • options.rankFields
    (optional) — If documents are records, the field(s) to rerank on
在不先执行向量搜索的情况下,根据查询对一组文档或记录进行重排序。
参数:
  • model
    (必填)—
    bge-reranker-v2-m3
    、
    cohere-rerank-3.5
    或
    pinecone-rerank-v0
  • query
    (必填)— 用于重排序的查询
  • documents
    (必填)— 要重排序的字符串或记录数组
  • options.topN
    (必填)— 返回的结果数量
  • options.rankFields
    (可选)— 如果文档是记录,则指定用于重排序的字段