{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_pazrfttkvzme","handle":"kachedb-mcp","url":"https://wellknown.network/agents/kachedb-mcp","links":{"self":"https://wellknown.network/agents/kachedb-mcp/record.json","html":"https://wellknown.network/agents/kachedb-mcp","markdown":"https://wellknown.network/agents/kachedb-mcp/record.md","api":"https://wellknown.network/api/v1/agents/kachedb-mcp","status":"https://wellknown.network/api/v1/agents/kachedb-mcp/status","claim":"https://wellknown.network/agents/kachedb-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/kachedb-mcp/claim.json","badge":"https://wellknown.network/agents/kachedb-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/kachedb-mcp/history","tools":"https://wellknown.network/api/v1/agents/kachedb-mcp/tools"},"ard":{"identifier":"urn:air::server:kachedb-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"kachedb-mcp","summary":"High-performance Model Context Protocol (MCP) server for KacheDB — in-memory cache & SIMD semantic memory for AI agents","description":"# 🧠 KacheDB MCP Server\n\n[![PyPI](https://img.shields.io/pypi/v/kachedb-mcp.svg)](https://pypi.org/project/kachedb-mcp/)\n[![License](https://img.shields.io/badge/license-Apache--2.0%20%7C%20MIT-blue.svg)](LICENSE)\n[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](pyproject.toml)\n[![Languages](https://img.shields.io/badge/languages-Python%20%7C%20Rust%20%7C%20Go%20%7C%20TS%20%7C%20JS-success.svg)](pyproject.toml)\n\n**High-Performance Model Context Protocol (MCP) server for KacheDB** — exposing sub-millisecond in-memory caching, Tree-Sitter AST symbol intelligence, and SIMD semantic vector memory to **Antigravity IDE**, **Claude Desktop**, **Cursor**, and AI coding agents.\n\n---\n\n## ⚡ Why KacheDB for AI Agents?\n\nAI coding assistants repeatedly re-read large codebases, parse ASTs, and crawl directories, wasting tens of thousands of tokens and adding hundreds of milliseconds of latency per turn.\n\n`kachedb-mcp` connects your AI assistant directly to **KacheDB's Megaslab pure-RAM SwissTable**:\n- 🚀 **Sub-50 Nanosecond Retrieval:** Instant symbol inspection and exact KV hits in memory.\n- 🌳 **Tree-Sitter AST Code Intelligence:** Multi-language symbol graphs (functions, classes, structs, signatures, docstrings) across Python, Rust, Go, TypeScript, and JavaScript.\n- 🔍 **Upward Anchor Discovery:** Zero-config project root detection from any touched file — no arbitrary `$HOME` scans or guessing folder names.\n- 🔄 **Incremental Git Watermarks:** Sub-millisecond sync verification using commit SHA watermarks (`kache:meta:<ws>:commit`). Up-to-date projects are skipped with zero overhead.\n- 🧠 **SIMD Semantic Vector Memory:** Natural language concept and code recall powered by ARM NEON & AVX2/FMA cosine similarity kernels.\n- 🪙 **Live Financial Telemetry:** Tracks avoided latency, cumulative tokens saved, and real-time USD cost savings.\n\n---\n\n## 🛠️ MCP Tools Exposed (11 Tools)\n\n### 🌳 Codebase Intelligence Tools\n| Tool | Type | Description |\n| :--- | :---: | :--- |…","publisher":{"name":"KacheDB Core Team","url":null},"homepage":"https://github.com/vubon/kachedb-mcp#readme","repository":"https://github.com/vubon/kachedb-mcp/issues","version":"0.4.0","license":null,"protocols":["mcp"],"tags":["agent-memory","antigravity","claude-desktop","cursor","kachedb","mcp","model-context-protocol","semantic-cache"],"pricing":null,"endpoints":[{"url":"pypi:kachedb-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"derived"},{"slug":"code.generation","name":"Code Generation","confidence":0.917,"provenance":"derived"}],"categories":["code","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":"kachedb-mcp","registry":"pypi","observedAt":"2026-10-22T06:23:19.873Z","publishedAt":"2026-10-03T16:47:04.415279Z","latestVersion":"0.4.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"kachedb-mcp","url":"https://pypi.org/project/kachedb-mcp/","firstSeenAt":"2026-09-09T22:22:57.427Z","fetchedAt":"2026-10-22T06:20:56.087Z","normalizedAt":"2026-10-22T06:20:56.087Z"}]},"firstSeenAt":"2026-09-09T22:22:57.427Z","updatedAt":"2026-10-22T06:23:19.873Z"}