{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_csd5bkma5g22","handle":"benostreamdb-mcp","url":"https://wellknown.network/agents/benostreamdb-mcp","links":{"self":"https://wellknown.network/agents/benostreamdb-mcp/record.json","html":"https://wellknown.network/agents/benostreamdb-mcp","markdown":"https://wellknown.network/agents/benostreamdb-mcp/record.md","api":"https://wellknown.network/api/v1/agents/benostreamdb-mcp","status":"https://wellknown.network/api/v1/agents/benostreamdb-mcp/status","claim":"https://wellknown.network/agents/benostreamdb-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/benostreamdb-mcp/claim.json","badge":"https://wellknown.network/agents/benostreamdb-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/benostreamdb-mcp/history","tools":"https://wellknown.network/api/v1/agents/benostreamdb-mcp/tools"},"ard":{"identifier":"urn:air::server:benostreamdb-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"benostreamdb-mcp","summary":"BenoStreamDB Model Context Protocol (MCP) Server","description":"# BenoStreamDB Model Context Protocol (MCP) Server\n\n[![crates.io](https://img.shields.io/crates/v/benostreamdb-mcp.svg)](https://crates.io/crates/benostreamdb-mcp)\n[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)\n\n`benostreamdb-mcp` is a high-performance Rust server implementing the open [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) for **BenoStreamDB**.\n\nIt exposes analytical streaming SQL, vector similarity search, reciprocal rank fusion (RRF) hybrid search, GraphRAG topological traversals, multi-modal ingestion (PDF, Excel, images, code, text), long-term agent memory, and live change data capture (CDC) directly to autonomous AI agents and IDEs (including Claude Desktop, Cursor, Antigravity IDE, and custom agentic frameworks) over standard input/output (stdio JSON-RPC).\n\n---\n\n## Key Capabilities\n\n- **Analytical Streaming SQL**: Powered by Apache DataFusion with native SIMD-accelerated execution.\n- **pgvector-Compatible Vector UDFs**: `vector_distance`, `l2_distance`, `cosine_distance`, and `inner_product` over `Vec<f32>` and stringified vector columns.\n- **Hybrid Search (BM25 + Dense Vectors)**: Reciprocal Rank Fusion (RRF) combining keyword BM25 retrieval with vector similarity.\n- **GraphRAG Search**: Simultaneous vector search and multi-hop CSR graph traversals for connected knowledge graphs.\n- **Persistent Long-Term Agent Memory**: `store_memory` and `recall_memory` tools with automated embedding generation, metadata tagging, and similarity scoring.\n- **Multi-Modal Document & Asset Ingestion**:\n  - **PDF Documents** (`.pdf`): In-memory full-text extraction via `pdf-extract` with line-bounded semantic chunking.\n  - **Excel & Spreadsheets** (`.xlsx`, `.xls`, `.xlsb`, `.ods`): Pure-Rust workbook parsing via `calamine` with automatic schema inference, sheet & row tracking, and typed columns.\n  - **Multimodal Images** (`.png`, `.jpg`, `.jpeg`, `.webp`, `.gif`, `.svg`): Byte conversion to base64 Data URIs (`data:im…","publisher":{"name":"Richard Albright and BenoStreamDB Contributors","url":null},"homepage":null,"repository":null,"version":"0.14.0","license":"MIT AND Apache-2.0","protocols":["mcp"],"tags":["database","mcp","llm","claude","ai","vector-search"],"pricing":null,"endpoints":[{"url":"pypi:benostreamdb-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":1,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":0.836,"provenance":"derived"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":0.779,"provenance":"derived"}],"categories":["data","documents","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"benostreamdb-mcp","registry":"pypi","observedAt":"2026-11-05T21:26:30.915Z","publishedAt":"2026-10-28T10:24:38.735484Z","latestVersion":"0.14.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"benostreamdb-mcp","url":"https://pypi.org/project/benostreamdb-mcp/","firstSeenAt":"2026-10-18T16:28:18.033Z","fetchedAt":"2026-11-05T21:24:37.956Z","normalizedAt":"2026-11-05T21:24:37.956Z"}]},"firstSeenAt":"2026-10-18T16:28:18.033Z","updatedAt":"2026-11-05T21:26:30.915Z"}