{"id":23226,"plugin_id":"plugins_6ab1957381a88191b41034b7a47dc51f","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:17:33.706Z","digest":"40e51478acad704511518e19e8d186182997751d3b63c943d7e69ae060b8c493","against":null,"payload":{"description":"Query integrated indexes using text with Pinecone MCP. IMPORTANT - This skill ONLY works with integrated indexes (indexes with built-in Pinecone embedding models like multilingual-e5-large). For standard indexes or advanced vector operations, use the pinecone:cli skill instead. Requires PINECONE_API_KEY environment variable and Pinecone MCP server to be configured.","included_files":[],"name":"query","skill_md_contents":"---\nname: query\ndescription: Query integrated indexes using text with Pinecone MCP. IMPORTANT - This skill ONLY works with integrated indexes (indexes with built-in Pinecone embedding models like multilingual-e5-large). For standard indexes or advanced vector operations, use the pinecone:cli skill instead. Requires PINECONE_API_KEY environment variable and Pinecone MCP server to be configured.\nargument-hint: query [q] index [indexName] namespace [ns] topK [k] reranker [rerankModel]\n---\n\n# Pinecone Query Skill\n\nSearch for records in Pinecone integrated indexes using natural language text queries via the Pinecone MCP server.\n\nWhenever this skill asks the user to choose between options, confirm a destructive step, or pick from a list, ask in plain prose, list the options, and wait for their answer before continuing.\n\n## What is this skill for?\n\nThis skill provides a simple way to query **integrated indexes** (indexes with built-in Pinecone embedding models) using text queries. The MCP server automatically converts your text into embeddings and searches the index.\n\n### Prerequisites\n\n**Required:**\n1. ✅ **Pinecone MCP server must be configured** - Check if MCP tools are available\n2. ✅ **PINECONE_API_KEY environment variable must be set** - Get a free API key at https://app.pinecone.io/?sessionType=signup\n3. ✅ **Index must be an integrated index** - Uses Pinecone embedding models (e.g., multilingual-e5-large, llama-text-embed-v2, pinecone-sparse-english-v0)\n\n### When NOT to use this skill\n\n**Use the pinecone:cli skill instead if:**\n- ❌ Your index is a standard index (no integrated embedding model)\n- ❌ You need to query with custom vector values (not text)\n- ❌ You need advanced vector operations (fetch by ID, list vectors, bulk operations)\n- ❌ Your index uses third-party embedding models (OpenAI, HuggingFace, Cohere)\n\n**MCP Limitation**: The Pinecone MCP currently only supports integrated indexes. For all other use cases, use the pinecone:cli skill.\n\n## How it works\n\nUtilize Pinecone MCP's `search-records` tool to search for records within a specified Pinecone integrated index using a text query.\n\n## Workflow\n\n**IMPORTANT: Before proceeding, verify the Pinecone MCP tools are available.** If MCP tools are not accessible:\n- Inform the user that the Pinecone MCP server needs to be configured\n- Check if `PINECONE_API_KEY` environment variable is set\n- Direct them to the MCP setup documentation or the `pinecone:help` skill\n\n1. Parse the user's input for:\n   - `query` (required): The text to search for.\n   - `index` (required): The name of the Pinecone index to search.\n   - `namespace` (optional): The namespace within the index.\n   - `reranker` (optional): The reranking model to use for improved relevance.\n\n2. If the user omits required arguments:\n   - If only the index name is provided, use the `describe-index` tool to retrieve available namespaces and ask the user to choose.\n   - If only a query is provided, use `list-indexes` to get available indexes, ask the user to pick one, then use `describe-index` for namespaces if needed.\n\n3. Call the `search-records` tool with the gathered arguments to perform the search.\n\n4. Format and display the returned results in a clear, readable table including field highlights (such as ID, score, and relevant metadata).\n\n---\n\n## Troubleshooting\n\n**`PINECONE_API_KEY` is required.** Get a free key at https://app.pinecone.io/?sessionType=signup\n\nIf you get an access error, the key is likely missing. Ask the user to set it and restart their IDE or agent session:\n- Codex CLI: run `export PINECONE_API_KEY=\"your-key\"` in the shell you start `codex` from. The bundled MCP server reads it from Codex's environment.\n- Codex Desktop on macOS: run `launchctl setenv PINECONE_API_KEY \"your-key\"`, then quit Codex fully and open it again.\n- For scripts, you can also use `uv run --env-file .env scripts/...`.\n\n**IMPORTANT** At the moment, the pinecone:query skill can only be used with integrated indexes, which use hosted Pinecone embedding models to embed and search for data.\nIf a user attempts to query an index that uses a third party API model such as OpenAI, or HuggingFace embedding models, remind them that this capability is not available yet\nwith the Pinecone MCP server.\n\n- If required arguments are missing, prompt the user to supply them, using Pinecone MCP tools as needed (e.g., `list-indexes`, `describe-index`).\n- Guide the user interactively through argument selection until the search can be completed.\n- If an invalid value is provided for any argument (e.g., nonexistent index or namespace), surface the error and suggest valid options.\n\n## Tools Reference\n\n- `search-records`: Search records in a given index with optional metadata filtering and reranking.\n- `list-indexes`: List all available Pinecone indexes.\n- `describe-index`: Get index configuration and namespaces.\n- `describe-index-stats`: Get stats including record counts and namespaces.\n- `rerank-documents`: Rerank returned documents using a specified reranking model.\n- Ask the user interactively to clarify missing information when needed.\n\n---\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}