A Model Context Protocol server that extracts and analyzes Python code structures, focusing on import/export relationships between files to help LLMs understand code context.
Paybond Kit for Python is the PyPI package for tenant-bound Paybond integrations and delegated agent spend controls. It opens hosted Gateway sessions, verifies capability tokens, authorizes tool-call spend, signs intent and evidence payloads, uses Stripe Connect, Stripe ACH Direct Debit, or x402 / USDC-on-Base settlement rails, reads tenant-scoped Signal, fraud, ledger, protocol, and A2A data, and
Python Docs MCP Server gives AI coding agents local access to the official Python standard library docs. It can look up docs by Python version, return specific sections, and keep answers compact for clients like Claude Desktop, Cursor, and Codex. It runs without API keys or a hosted service.
A streamlined foundation for building Model Context Protocol servers in Python, designed to make AI-assisted development of MCP tools easier and more efficient.
Ephemeral MicroVM-isolated code execution for AI agents. Run Python, Node, or bash — fresh hardware-isolated VM per call, hard-purged after. No state persists between calls.
Calculates Vietnamese Tử Vi horoscope charts, generating structured JSON with Thiên Bàn and Địa Bàn, transit analysis, and local persistence via SQLite.
Audits a module against its test suite and reports the cases the tests are structurally unable to see, then proves each gap with a real failing test rather than a warning. Covers Python, TypeScript, JavaScript, Java, Rust and Go.
Zero-config SQL profiler for slow Python/SQLAlchemy jobs, built for agents: returns the exact call site, query count, and fix as compact machine-readable fields instead of raw query logs~55× fewer tokens per diagnosis (≈10k → ≈180) and the matching drop in API cost.
Enables AI agents to scaffold and upgrade modern projects across JavaScript/TypeScript and Python through a unified MCP interface, offering tools to list generators, inspect schemas, generate projects, and plan upgrades.
A Python web-scraping toolkit that exposes 22 tools for fetching structured web data (from any URL to search, finance, e-commerce, and reference sources) as validated JSON for AI agents.
Model Context Protocol (MCP) stdio server built with the official MCP Python SDK (FastMCP). Exposes 3 MCP tools: package_capability, generate_dockerfile, generate_claude_desktop_config — package AIMarket capabilities as Docker images + MCP manifest + Claude Desktop config. Entrypoint: mcp_stdio_server.py; root Dockerfile + glama.json in repo.
A local Python MCP server for driving, perceiving, and rendering terminal programs, using a pluggable PTY and pyte screen model to let AI agents interact with real TUIs.
Persistent project context for Google Gemini. 12 MCP tools for .faf
Project DNA — auto-detect your stack, validate, score, and sync across CLAUDE.md, GEMINI.md, and AGENTS.md. Python/FastMCP. IANA-registered format (application/vnd.faf+yaml). 183 tests. One file, every AI platform.
Tenant-bound MCP server for agent spend authorization, policy guardrails, evidence, escrow settlement, and portable receipts. Works with Cursor and Claude Code via stdio; npm (@paybond/kit) and Python (paybond-kit).
Deterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP. Python, TS/JS, Rust, Go, Java, C#.
Model Context Protocol server for pyobfus — the Python obfuscator. Lets Claude Desktop, Claude Code, Cursor, Windsurf, and Zed call pyobfus tools (preflight risk check, zero-config init, reverse stack-trace mapping) directly from an agent conversation.
Voice-powered bug reporting MCP server with 13 tools. Captures console logs, network errors, DOM traces, and developer voice descriptions. AI reads structured reports to find and fix bugs automatically. Chrome Extension + Python CLI.
Enables AI assistants to perform controlled Linux system administration tasks like reading logs, managing services, cron jobs, WordPress, and executing sandboxed Python code, with strict security constraints.
Persistent, correctable AI memory with zero dependencies. Corrections always surface first and never decay. SQLite-backed, 400 lines of pure Python, MCP server included.