- Prompt Switchboard MCP Sidecar @xiaojiou176-open/prompt-switchboard-mcpCompare-first local MCP sidecar for browser AI workflows.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
- Claude Prompt Optimizer @rishiatlan/claude-prompt-optimizerScores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- bundlebox @blackswanalpha/bundleboxWhere the work is, packed before the agent reads: brief, symbol tables, findings, token bill.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Hermes Prime @hermes-labs-ai/hermes-primeRead-only stdio MCP server for a versioned convention card in Claude Code.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- NerdyChefs Prompts @mayeu20/nerdychefs-mcpSearch, browse and pick from the free NerdyChefs.ai prompt library from any MCP client.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Stateark @askrion/statearkLocal-first version control for AI work. Savepoint and resume your project state across chats.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- StackGuide @taimiralain/stackguide-mcpDynamic context loading for AI assistants with TDD workflow and AST analysis6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- AgentForge @sciscale/agentforge-mcpTurn rough requests into rigorously structured prompts, for any coding agent.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Context Bridge @prateekg7/context-bridgeContext portability MCP server for compressing, formatting, and resuming AI conversation handoffs.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Afterpaths @burnssa/afterpathsSession memory for AI coding agents. Search past sessions, extract rules, and track what works.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- aide-memory @aide-memory/aide-memoryPersistent memory layer for AI coding agents — your agent remembers what you taught it.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- A2CR @a2cr/a2cr-mcpSave AI-agent handoff checkpoints, WorkStash notes, and WorkThreads in a local A2CR workspace.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Context First @xjtlumedia/context-first-mcp37-tool MCP server: context health, memory, reasoning, truthfulness & research pipeline.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Context Fabric @vikas9793/context-fabricContext sync layer for AI agents. Ensures continuity and eliminates memory drift automatically.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Engram Cc @morous-dev/engram-ccUniversal AI coding assistant memory — session handoff, SLM compression, and semantic retrieval.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- fish-bridge — Session Knowledge Graph @makeamouse/fish-bridge-mcpCompresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- LynxPrompt @geiserx/lynxprompt-mcpMCP server for LynxPrompt — browse, search, and manage AI configuration blueprints5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Repomemory @danielguru/repomemoryPersistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- McpOrchestrator @byggarepop/dotnet-mcp-orchestratorRoute one agent through one MCP server to many, with progressive tool discovery to shrink context.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.2 GitHub stars.
- ljos @leidarljos/ljosLocal memory, a work tracker and a shell-command guard shared by coding agents on one machine.Not assessed yet.Runs on your machine, installed from cargo.1 GitHub stars.
- Brevet @brightbeamai/brevetChange control for what AI agents learn: humans promote, releases are signed, rules can be recalled3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- okl — Observed Knowledge Ledger @emeraldleaf/oklLessons your coding agent can trust: briefed before each task, proven by checks, flagged on change.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- craftbag @craftbag/craftbag-mcpMCP server to list, load, explain, and validate Agent Skills.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.1 GitHub stars.
- AI Workbench MCP @alptugharun/ai-workbench-mcpRead-only MCP server for reusable AI prompts and assistant blueprints.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
