"A local vector-based search engine for personal documents" matching MCP servers:

A CLI-first semantic code search tool with MCP integration for AI assistants, enabling semantic search, AST-aware parsing, and code analysis across 13 languages.

A local, offline MCP server that enables AI agents to collaborate with SketchUp for controlled modeling, editing, and review tasks via 41 MCP tools.

A secure vector-based memory server that provides persistent semantic memory for AI assistants using sqlite-vec and sentence-transformers. It enables semantic search and organization of coding experiences, solutions, and knowledge with features like auto-cleanup and deduplication.

A secure, vector-based task management server for Claude Desktop using sqlite-vec and sentence-transformers. It provides intelligent task tracking with semantic search capabilities to organize and retrieve development tasks efficiently.

An MCP server that indexes local Python projects into a SQLite database to enable efficient symbol searching and dependency tracking. It allows users to find function or class definitions, trace module imports, and read file contents through natural language interfaces.

Provides full read/write access to the GitHub REST API via a single tool using a personal access token.

Eyes for AI coding agents: deterministic MCP server that tells the LLM which CSS rule wins, in which file, on which line — and why. Cascade verdicts, blast radius, interaction timelines, pixel-perfect audits.

Local MCP tools to create, preview, inspect, verify, and compile PDF documents from HTML/CSS and structured data with Fullbleed. Python/Rust engine, MIT licensed, with document paths confined to a chosen workspace.

A personal MCP server built with Python FastMCP, offering tools for paper retrieval, dataset analysis, project scaffolding, and directory utilities, with stdio and HTTP transport plus optional bearer token authentication.

Enables AI assistants to search and retrieve detailed documentation for Tracktion Engine classes and APIs.

MCP server (stdio, official Python SDK) exposing a single tool: quantity_execute. Performs dimensional calculation and unit conversion with evidence. Solves silent unit errors in LLM agent chains: 20 m/s × 3 h returns 216 km.

Enables programming agents to capture errors and conversation signals, reflect on root causes, consolidate reusable skills, and retrieve relevant context for future tasks, providing a self-learning memory loop.

A personal GitHub engineering assistant that enables repository management, project publishing, code and engineering-memory search, Project Euler solution workflows, and repo analysis through natural language.

This read-only MCP Server allows you to connect to XML Documents data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for XML Documents (https://www.cdata.com/drivers/xml/download/mcp).

Aggregates your digital footprint (GitHub, blogs, resume) into a single AI-readable profile and exposes it via MCP tools so AI agents can query your context live.

Enables indexing and semantic search of software project files via MCP, with automatic file watching for updates.

A local code-intelligence engine for AI agents that indexes repositories into a PostgreSQL-backed code graph and serves structured, token-budgeted context over MCP and HTTP, enabling targeted queries on symbols, dependencies, contracts, and impact analysis.

Enables clients to read files, list tests, and run tests through MCP tool calls, while refusing apply operations.

Claude Code MCP server to create and update local interactive web pages (Artifacts) that live-refresh via SSE.

Exposes personal portfolio data as tools for Claude to answer questions about the developer, including profile, skills, experience, projects, and contact information.