-
Lint email HTML before you send it. One rule set, three interfaces: a library, a CLI for CI, and an MCP server for agents.
Version check not run yet
Email npm Local 26 a week MIT
WM
windbg-mcp io.github.kanren3/windbg-mcp 1.7 · 33/100 MCP server that drives cdb.exe/kd.exe (WinDbg): crash dump analysis, live user-mode debugging, and kernel debugging
Version check not run yet
Developer tools npm Local 26 a week MIT
HT
Harvey Tools io.github.meltingpixelsai/harvey-tools 1.7 · 33/100 Web scraping, code review, content generation, and analysis tools. Pay-per-call USDC.
Version check not run yet
Developer tools Official MCP Registry Remote
-
MCP proxy server that filters tools from upstream MCP servers via regex-based deny list
Crashes on start
Developer tools Official MCP Registry · npm Local 1.1k a week MIT
-
MCP server that exposes CodeRabbit IDE extension review comments as tools, resources, and a triage prompt over stdio (Cursor, Claude, VS Code).
Version check not run yet
Developer tools npm Local MIT
-
An model context protocol adapted to running and list graphql queries
Version check not run yet
Developer tools npm Local MIT
-
MCP server for org-press - exposes code intelligence and tools to AI assistants
Version check not run yet
Developer tools npm Local GPL-2.0
@M
@testrelic/mcp io.github.testrelic-ai/testrelic-mcp-server 1.7 · 33/100 TestRelic MCP Server — cloud-wired intelligent testing context (test creation, auto-healing, coverage gaps, test impact). One token; everything else is resolved.
Version check not run yet
Developer tools npm Local 25 a week AGPL-3.0-ONLY
-
YuanCheng (元呈) — a universal result-presentation layer for AI agents: turn any AI output (JSON / Markdown / plain text) into a standard content object, pick a presentation form (conclusion card / tabl
Version check not run yet
Developer tools npm Local 25 a week MIT
-
Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation.
Version check not run yet
Memory and context npm Local 25 a week MIT
-
MCP server for live JupyterLab notebooks over RTC: read, edit and run cells in the document the user is looking at.
Version check not run yet
Developer tools npm Local 25 a week MIT
PM
pmat io.github.paiml/paiml-mcp-agent-toolkit 1.7 · 33/100 PMAT - Zero-config AI context generation and code quality toolkit (CLI, MCP, HTTP)
Version check not run yet
Developer tools crates.io Local
-
SAP Test Case Search MCP Server - Search and retrieve SAP test cases from Azure AI Search vector database
Version check not run yet
Search and retrieval (RAG) npm Local MIT
-
16 engines, 28 MCP tools for Python code quality. Zero external dependencies.
Version check not run yet
Developer tools Official MCP Registry Local
-
MCP server for Zephyr Scale Cloud API - Manage projects, folders, test cases, test steps, and test scripts
Version check not run yet
Developer tools npm Local MIT
-
CAP MCP: Model Context Protocol server for codebase awareness
Version check not run yet
Developer tools PyPI · Open VSX Local APACHE-2.0
-
Enterprise-ready MCP Server for Google Stitch SDK - AI-powered UI generation for Claude, Cursor, Cline, and VS Code. Generate beautiful web interfaces from text prompts using Model Context Protocol.
Crashes on start
Model and agent tools npm Local 59 a week MIT
UM
unravel-mcp io.github.eruditecoder108/unravelai 1.7 · 33/100 Unravel MCP Server — Zero-hallucination AST evidence for AI coding agents. Deterministic tree-sitter analysis, mutation chains, cross-file call graphs, and claim verification.
Version check not run yet
Coding agent tools npm Local 11 a week BSL-1.1
AC
actlint io.github.formael/actlint-cli 1.7 · 33/100 A static action-risk linter for MCP servers. Reads a server's advertised tools, derives an honest action-risk profile, compares it against what each tool declares, and reports the gaps as a scorecard,
Version check not run yet
Developer tools npm Local 6 a week APACHE-2.0
OP
openqa io.github.openqa-labs/openqa 1.7 · 33/100 Agent Harness for Browser Test Automation — write tests in natural language, powered by Claude Code or OpenCode
Version check not run yet
Developer tools npm Local 6 a week MIT