0.3.0 → 0.4.0
minor release, 29 October 2026Added: create-document-index, search-document-index, upsert-documents
MCP servers / @pinecone-database/mcp
3 of its last 5 updates changed what the agent reads: 13 tool descriptions rewritten, up to 0.4.0.
npm package · last recorded on 13 November 2026 on a clean machine with placeholder settings; only tools/list was sent. A changed description is not a vulnerability. npm page · Method and limits · this data as JSON.
Added: create-document-index, search-document-index, upsert-documents
No tool definition changed.
cascading-search: input schema changed; new arguments: llm_model, llm_provider
describe-index: input schema changed; new arguments: llm_model, llm_provider
describe-index-stats: input schema changed; new arguments: llm_model, llm_provider
list-indexes: input schema changed; new arguments: llm_model, llm_provider
rerank-documents: input schema changed; new arguments: llm_model, llm_provider
search-docs: input schema changed
search-records: input schema changed; new arguments: llm_model, llm_provider
upsert-records: input schema changed; new arguments: llm_model, llm_provider
No tool definition changed.
Releases tried: 0.1.16 (2025-09-15); 0.1.17 (2025-09-25); 0.2.0 (2026-01-27); 0.2.1 (2026-02-05); 0.3.0 (2026-08-07); 0.4.0 (2026-10-29).
The pin is the SHA-256 of the tool's name, description and input schema, as verfy.lock records it. The same pin in your lock means your agent reads this exact definition. Verfy 0.16.0 and later also pin a tool's title, annotations and output schema when the server sends them, so such a tool shows a different pin in your lock.
| Tool | Description | Pin |
|---|---|---|
| search-docs | Search the official Pinecone documentation for relevant information. Use this before writing Pinecone code or explaining Pinecone behavior, rather than relying on assumptions. | 05858ae99269 |
| list-indexes | List all Pinecone indexes in the project, including each index's configuration and readiness status. Use this to discover valid index names before calling other tools. | 139fcc436aa7 |
| describe-index | Describe the configuration of a Pinecone index, including its embedding model and the "fieldMap" that names the record field holding the text to embed. Call this before upsert-records to learn the required field name. Check "status.ready" in the response to confirm the index can accept upserts and queries. | 227665ce653d |
| describe-index-stats | Describe the statistics of a Pinecone index, including record counts per namespace. Use this to discover which namespaces exist in an index. Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry. | 368a44713b23 |
| create-document-index | Create a Pinecone document index: an index defined by a schema of searchable "string" fields. Each field can declare "fullTextSearch" (indexed for keyword search with BM25), "embed" (Pinecone embeds the text with a hosted dense model for semantic search), "sparseEmbed" (a hosted sparse model), or a combination. A good default is one field with both, for example {"chunk_text": {"fullTextSearch": {"language": "en"}, "embed": {}}}, which supports search by meaning and by exact terms on the same text. Fields you only need to filter on are not declared here; send them as document metadata. Use upsert-documents and search-document-index with the new index. This call blocks until the index is ready. If an index with the same name already exists, it is returned unchanged instead of erroring. | 54c02a9879ee |
| upsert-documents | Insert or update documents in a Pinecone document index (one created with create-document-index). Each document needs an "_id" and plain text in every field the index declares with "embed"; Pinecone embeds that text on write, so never send vectors. Call describe-index first to see the schema. Fields not in the schema are stored as metadata you can filter on. Documents with an existing "_id" are replaced. Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry. | 4d4d497da41b |
| search-document-index | Search a Pinecone document index (one created with create-document-index). Call describe-index first to see which fields declare "embed", "sparseEmbed", or "fullTextSearch". Rank with one or more "scoreBy" clauses: - "embed": search by meaning on a field with "embed". Pass the query as plain text; Pinecone embeds it with the field's model. - "sparse_embed": search a field with "sparseEmbed" the same way. - "text": keyword (BM25) search on one or more full-text fields. Good for exact terms like IDs, error codes, and names. - "query_string": Lucene-style query syntax. Don't pass "fields" (the API rejects it); target fields with qualifiers inside the query, for example 'chunk_text:"exact phrase"', or omit qualifiers to search every full-text field. An "embed" or "sparse_embed" clause must be the only clause; "text" and "query_string" clauses can be combined. To rank by meaning and by exact terms, run two separate searches: their scores are on different scales, so don't compare them across searches. Returns matches with "_id", "_score", and the fields named in "includeFields". Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry. | 7d74be9c17e8 |
| create-index-for-model | Create a Pinecone index with integrated inference, which automatically embeds the text field named in "fieldMap". Supports AWS, GCP, and Azure cloud providers. This call blocks until the index is ready to accept upserts and queries, so no readiness polling is needed afterwards. If an index with the same name already exists, it is returned unchanged instead of erroring. For a new index, prefer create-document-index, which supports full-text search and integrated embedding on the same field. | db70f4c45976 |
| upsert-records | Insert or update records in an integrated Pinecone index. For a document index, use upsert-documents instead. Text in the field named by the index's "fieldMap" is embedded automatically — call describe-index first to confirm that field name. Records with an existing "id" are overwritten. Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry. | 03281f56289c |
| search-records | Search an index for records that are semantically similar to the query text. Only works with integrated-inference indexes (e.g. created with create-index-for-model), which embed the query automatically; it fails on standard indexes and document indexes (use search-document-index for those) — use describe-index to check the index type. Returns hits with "_id", "_score", and the record's stored "fields". Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry. | d57e3ca3a38e |
| rerank-documents | Rerank a set of provided documents by relevance to a query. Use this for documents that did not come from a Pinecone search (e.g. externally sourced text). To rerank the results of a single-index search, prefer the "rerank" parameter of search-records instead of calling this tool separately. | ed730240d768 |
| cascading-search | Search across multiple indexes for records that are similar to the query text, then deduplicate and rerank the combined results. Reranking is required for this tool. Only works with integrated-inference indexes. To search a single index, use search-records instead. | 377ad43dd3db |
Pin what @pinecone-database/mcp serves you today, commit the lock, and a pull request fails when a tool changes, with the text before and after. Pin the package version in your MCP config as well.
$ pip install verfy
$ verfy lock check --update # shows each tool, then writes verfy.lock
$ git add verfy.lock# .github/workflows/verfy.yml, after actions/checkout
- uses: verfy-dev/verfy-action@v1Maintain this server? Run the same check on your releases and add the Locked by Verfy badge to your README.