A task-aware transparent proxy that wraps stdio MCP servers (such as git, filesystem, and terminal) and compresses large tool outputs field-by-field using declarative YAML profiles, passing narrow intent queries through untouched. Discarded data is stored in SQLite and can be losslessly retrieved via an injected tool, either in full, by line range, or by grep, while errors are always preserved and failures fall back to the raw result.

Enables AI assistants to inspect and query a TPC-H sales warehouse through read-only, allowlisted catalog tools and schema resources, with ad-hoc SQL disabled by default. It enforces strict arguments and input-free errors, while a differential attack suite verifies that query protections hold across MCP transports.

Enables AI agents to store decisions as a versioned history, linking each new decision to the one it replaces so that recall always resolves to the decision currently in force instead of obsolete ones. It runs fully locally on a single SQLite file with BM25 search, and can optionally detect replacements automatically via an LLM or heuristic linker.

Enables MCP clients to authenticate with Feedbin, poll unread articles, fetch and cache full entry bodies in SQLite, and list or retrieve cached entries through the Feedbin v2 API.

Enables AI agents to connect to security cameras, detect objects with YOLOv8, recognize known faces, monitor restricted intrusion zones, capture annotated snapshots, and query a persistent SQLite event history.

Enables Claude Code and Codex to write, update, and retrieve durable long-term memories that survive session boundaries and context compaction. All recall runs locally against a single SQLite file using hybrid BM25, embedding, and recency ranking cut to an explicit token budget, with no cloud dependency.

Enables triaging incoming messages by classifying them into a small bounded set of action categories with a fast model, then routing each one to dismiss noise, send notifications for action items, or optionally auto-register calendar events. Users bring their own source, notifier, and calendar through small adapter interfaces, with verdicts and state kept in local SQLite storage.

Enables Claude and other MCP clients to safely query PostgreSQL data and perform limited order-status updates through scoped bearer tokens, read-only transactions, row caps, and an audit log.

Local MCP server that gives coding agents a verifiable project memory, trims what enters their context, and masks secrets — with honest accounting of what it saves and costs.

Governance standard and reference toolset for LLM-maintained knowledge corpora

Real-time execution trace and cost intelligence for Claude Code

Local MCP server that gives coding agents a verifiable project memory, trims what enters their context, and masks secrets — with honest accounting of what it saves and costs.

No description yet.

An MCP Multimodal AI Agent with eyes and ears!

EPO/USPTO search, citations, OCR, plus PATSTAT Portfolio Analytics, guarded SQL and Graph Analytics.

Coleções, busca vetorial, SQL e arquivos

Compare managed Postgres, auth, monitoring, and hosting, then purchase without leaving the session.

PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.

Give your agent its own cloud: run Postgres, Redis or any Docker image on a microVM in one call.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, ext

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of conte

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Portable AI code quality reviews for Codex, Cursor, Copilot and other coding agents: six Agent Skills for architecture, technical debt, tests and remediation.