Packages

h1-brain is an MCP server that connects an AI assistant to HackerOne. It syncs a user’s rewarded reports, programs, and scopes via the HackerOne API into a local SQLite database, queries a pre-bundled database of public disclosed bounty reports, and exposes MCP tools (notably hack(handle)) to search/analyze that data and generate structured attack briefings.

kube-apiserver is the Kubernetes API server process. It exposes Kubernetes REST APIs used to authenticate/authorize clients, validate requests, and persist/retrieve cluster state via etcd, while orchestrating core Kubernetes APIs (e.g., resources, watches, admission control, and federation/aggregation).

MCP server that bridges to any LSP. One binary, multiple language servers.

mcp2py turns MCP (Model Context Protocol) servers into Python modules by spawning/connecting to an MCP server and exposing MCP tools/resources/prompts as Python methods/attributes/template helpers. It also supports interactive server flows (elicitation), and can handle LLM sampling for servers using Anthropic/OpenAI via LiteLLM (or a custom sampling handler).

CLI tool that generates MCP servers from OpenAPI specs or scraped API docs. It can optimize/curate endpoint toolsets for agent use, generate deterministic workflow-oriented tools, and includes diff/update and smoke-testing for generated servers.

Bridges Google Ads with Claude AI and Cursor, enabling advertising professionals to query campaign performance, keyword analytics, and ad metrics through natural language without writing code.

mcp-mysql-server is a Model Context Protocol (MCP) server that connects to a MySQL database and exposes tools for querying data and managing schema (e.g., list/describe tables, create/alter/drop columns/tables, and browse schema/resources).

mcp-rdf-explorer is an MCP (Model Context Protocol) server that lets AI clients explore RDF data using FastMCP tools/resources. It supports RDF Turtle local-file mode and SPARQL endpoint mode, providing SPARQL execution utilities, graph statistics, schema/resource discovery, and some prompt-to-SPARQL style capabilities.

mcp-scan is a locally-run CLI security scanner for Model Context Protocol (MCP) server configurations. It auto-detects configurations for multiple AI tool clients and performs checks such as secret exposure, prompt injection risk, supply-chain/package risk, data exfiltration indicators, and permission/transport issues. It can output JSON and integrate with GitHub Actions via SARIF.

A Go-based multi-protocol (HTTP/REST, gRPC, WebSocket, SSE) AI gateway/MCP server that unifies access to multiple LLM providers (notably AWS Bedrock and Azure OpenAI) behind a consistent API, including worker-pool parallelism, streaming, sessions, Redis/PostgreSQL persistence, and observability (Prometheus/Grafana/Jaeger).

MCP server (Go) that exposes SQLite database operations as Model Context Protocol tools. It restricts database access to user-specified allowed directories, supports switching between databases, and provides CRUD/query/table/index/maintenance actions (including transactions).

Reporecall is a local developer-tool and MCP server/daemon that indexes a codebase (AST parsing + hybrid keyword/vector search + call-graph expansion) and injects relevant code and persistent “memory” into Claude Code prompts via a pre-submit hook. It also provides MCP tools for searching code and storing/recalling project memories on disk.

Self-hostable tool that generates short-form videos from text by producing TTS audio, auto-captions, selecting background videos (via Pexels), composing the result with Remotion, and rendering the final short video. Exposes both an MCP server (SSE/messages) and a REST API for creating videos and checking status.

Provides a Telnyx Local Model Context Protocol (MCP) server (Python/fastmcp) that exposes tools for telephony (calls/DTMF/audio), messaging (SMS/MMS), phone numbers, voice connection configuration, cloud storage (S3-like buckets), embeddings-related operations, and Telnyx secrets management. Includes an optional webhook receiver with ngrok tunneling and a parent-process monitoring/cleanup behavior.

Provides an MCP (Model Context Protocol) gateway that aggregates many external MCP tools/services behind two meta-tools—`search` to discover tools and `execute` to run a selected tool—with authentication via API key or OAuth2.

Xcode-mcp-server is an MCP (Model Context Protocol) server that lets an MCP-compatible AI client trigger Xcode project builds and test runs (with schemes/configurations/destinations), stream logs, and persist build/test artifacts and reports to a specified logs directory. It exposes MCP tools such as build_project and run_tests and a resource for the latest log.

Provides a global dataset of countries, states/regions, and cities (including ISO codes, names, coordinates, and timezones for countries) distributed as downloadable files and via an associated REST API ecosystem. Exports are available in many formats (e.g., JSON, CSV, SQL/MySQL/PostgreSQL, SQLite, MongoDB, XML, YAML, GeoJSON, and TOON).

Provides a Model Context Protocol (MCP) server (Java) that reads Excel-like files (XLSX/XLS/CSV), extracts sheet names, parses header rows into column specs, and reads data rows with values associated to headers. Includes in-memory caching utilities and enforces access to files via an allowed-workspace mechanism configured with env var MCP_WORKSPACES.

FinanceToolkit is an open-source Python library for transparent financial analysis. It fetches historical market data and financial statements (primarily via Financial Modeling Prep, with fallback to Yahoo Finance unless enforced), and computes a wide set of financial ratios, models, technical indicators, options analytics/Greeks, performance metrics, and risk metrics (e.g., Sharpe ratio, Value at Risk).

mcpadapt is a Python library that adapts Model Context Protocol (MCP) servers into tool collections usable from various agentic frameworks (e.g., smolagents, LangChain, CrewAI, google-genai). It supports local MCP servers via stdio and remote MCP servers via SSE, and can flatten tools from multiple MCP servers into a single framework-compatible tool list.