{"id":"c904e994-6a7b-4c16-9ee4-94d7b627b791","shortId":"butUEk","kind":"skill","title":"mcp","tagline":"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","description":"# 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","tags":["mcp","gemini","cli","extension","pinecone-io","agent-skills","agentic-ides","gemini-cli","gemini-cli-extension","pinecone","semantic-search","vector-search"],"capabilities":["skill","source-pinecone-io","skill-mcp","topic-agent-skills","topic-agentic-ides","topic-gemini-cli","topic-gemini-cli-extension","topic-pinecone","topic-semantic-search","topic-vector-search"],"categories":["gemini-cli-extension"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/pinecone-io/gemini-cli-extension/mcp","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add pinecone-io/gemini-cli-extension","source_repo":"https://github.com/pinecone-io/gemini-cli-extension","install_from":"skills.sh"}},"qualityScore":"0.461","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 23 github stars · SKILL.md body (3,947 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-01T07:01:44.846Z","embedding":null,"createdAt":"2026-04-18T22:24:46.188Z","updatedAt":"2026-05-01T07:01:44.846Z","lastSeenAt":"2026-05-01T07:01:44.846Z","tsv":"'/guides/operations/mcp-server#tools).':80 '1':218 '1889':333 '3.5':410,491,543 'across':438,462 'agent':44,65 'ai':64 'architectur':335 'array':285,455,558 'automat':194,264,354 'avail':11 'aw':206 'azur':209 'bge':403,484,536 'bge-reranker-v2-m3':402,483,535 'breakdown':170 'built':95,331 'built-in':94 'cascad':35,435 'cascading-search':34,434 'categori':334 'chunk':249,325,423 'cli':116 'cloud':138,204,212 'coher':408,489,541 'cohere-rerank':407,488,540 'configur':132,270 'contain':244,298 'count':165 'creat':24,91,177,181 'create-index-for-model':23,176 'current':125 'dedupl':443 'describ':17,20,129,154 'describe-index':16,128 'describe-index-stat':19,153 'detail':133 'dimens':140 'direct':316 'docs.pinecone.io':79 'docs.pinecone.io/guides/operations/mcp-server#tools).':78 'document':9,40,515,520,556,575 'e.g':214,248,422 'e5':230 'east':217 'eiffel':328 'emb':226,247,351 'embed':98,109,142,189,193,221,265 'embed.fieldmap.text':238 'embed.model':219 'english':236 'eq':391 'exampl':320 'expos':59 'extern':108,196 'field':144,242,296,301,311,418,499,579 'fieldmap':307 'filter':385 'final':505 'first':531 'follow':61 'gcp':207 'get':131,157 'gt':394 'gte':395 'guid':77 'handl':192 'id':293,295,323 'ide':67 'includ':162 'index':15,18,21,25,89,90,106,119,122,130,137,151,155,161,174,178,185,202,261,268,275,305,345,357,363,440,453,476 'insert':254 'instal':71 'instruct':72 'integr':88,188,260,344 'json':322 'key':81 'larg':231 'limit':82 'list':14,118,120,451 'list-index':13,117 'llama':224 'llama-text-embed-v2':223 'lt':396 'lte':397 'm3':406,487,539 'map':145 'mcp':1,6,50,52,57,75,85,350 'metadata':313,384 'metric':141 'model':27,99,110,143,180,190,197,222,271,359,401,482,533 'mongodb':388 'mongodb-styl':387 'multilingu':229 'multilingual-e5-large':228 'multipl':439 'must':290 'name':149,152,172,175,200,203,273,276,361,364,457 'namespac':169,277,279,365,367,458 'ne':392 'need':45,198 'nest':310 'new':183 'number':377,427,470,506,567 'object':459 'oper':390 'option':383,399,417,426,504,573 'options.rankfields':572 'options.topn':565 'paramet':148,171,199,272,360,452,532 'pass':346 'per':168,475 'per-namespac':167 'perform':527 'pinecon':5,49,51,56,84,97,115,126,191,234,413,494,546 'pinecone-rerank-v0':412,493,545 'pinecone-sparse-english-v0':233 'plain':347 'project':127 'put':314 'queri':353,374,467,525,549,552 'query.filter':382 'query.inputs.text':370,463 'query.topk':375,468 'rank':450 'rec1':324 'record':30,33,164,241,253,257,262,283,287,289,319,321,338,522,562,577 'refer':2,54 'region':139,210,213 'requir':150,173,201,205,211,220,239,274,278,284,362,366,371,376,454,464,469,480,498,534,550,557,566 'rerank':39,400,404,409,414,420,433,445,478,481,485,490,495,501,512,514,516,537,542,547,554,564,582 'rerank-docu':38,513 'rerank.model':398,479 'rerank.rankfields':416,497 'rerank.topn':425,503 'result':379,429,446,472,508,569 'retriev':474 'return':381,431,510,571 'search':32,36,337,341,369,436,437,461,530 'search-record':31,336 'see':73 'semant':339 'server':7,58,76 'serverless':184 'set':518 'setup':69 'simultan':441 'singl':449 'skill' 'skill-mcp' 'source-pinecone-io' 'spars':235 'specif':136 'specifi':302 'standard':105 'stat':22,156 'statist':158 'status':147 'string':560 'style':389 'support':87 'text':225,245,250,300,326,340,348,373,424,466 'tool':8,12,53,62 'topic-agent-skills' 'topic-agentic-ides' 'topic-gemini-cli' 'topic-gemini-cli-extension' 'topic-pinecone' 'topic-semantic-search' 'topic-vector-search' 'total':163 'tower':329 'understand':47 'updat':256 'upsert':29,252,281 'upsert-record':28,251 'us':216 'us-east':215 'use':41,107,113,266,355,386 'v0':237,415,496,548 'v2':227,405,486,538 'vector':529 'without':526 'work':103","prices":[{"id":"18128048-366d-4c65-a67c-b156ddfc2962","listingId":"c904e994-6a7b-4c16-9ee4-94d7b627b791","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"pinecone-io","category":"gemini-cli-extension","install_from":"skills.sh"},"createdAt":"2026-04-18T22:24:46.188Z"}],"sources":[{"listingId":"c904e994-6a7b-4c16-9ee4-94d7b627b791","source":"github","sourceId":"pinecone-io/gemini-cli-extension/mcp","sourceUrl":"https://github.com/pinecone-io/gemini-cli-extension/tree/main/skills/mcp","isPrimary":false,"firstSeenAt":"2026-04-18T22:24:46.188Z","lastSeenAt":"2026-05-01T07:01:44.846Z"}],"details":{"listingId":"c904e994-6a7b-4c16-9ee4-94d7b627b791","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"pinecone-io","slug":"mcp","github":{"repo":"pinecone-io/gemini-cli-extension","stars":23,"topics":["agent-skills","agentic-ides","gemini-cli","gemini-cli-extension","pinecone","retrieval-augmented-generation","semantic-search","vector-search"],"license":"mit","html_url":"https://github.com/pinecone-io/gemini-cli-extension","pushed_at":"2026-04-24T19:30:56Z","description":"The official Pinecone Gemini CLI extension repo.","skill_md_sha":"354fcd9d414a8bc6346dfe827b1b7a08dcd000ac","skill_md_path":"skills/mcp/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/pinecone-io/gemini-cli-extension/tree/main/skills/mcp"},"layout":"multi","source":"github","category":"gemini-cli-extension","frontmatter":{"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."},"skills_sh_url":"https://skills.sh/pinecone-io/gemini-cli-extension/mcp"},"updatedAt":"2026-05-01T07:01:44.846Z"}}