38,601 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Development-first MCP wrapper for smoke-testing stdio MCP servers from another MCP client during active development. Runs locally from the mcp-stdio-wrapper npm package.
★not rated 0 2mo agoA
tokens not measured
originalMIT
Your AI agents start from zero every session — users repeat themselves endlessly. Threadline fixes this in 2 lines. inject() before your LLM call, update() after. Persistent context across every session, model, and product. Structured extraction across 7 scopes. OAuth-style grant system so agents only see permitted…
MCP server "mcp-server-deepdive-deployment" as configured in manutrip-pm-AI-Defense/mcpdeployment. Runs locally from the mcp-server-deepdive-deployment Python package.
Operate the Agentic Swarm Marketplace API — x402-paid smart contract and airdrop intelligence, MCP HTTP tools, and machine discovery under /.well-known.
Rules for using the Model Context Protocol, a standard that lets AI models interact with external tools and resources. In this project, those tools provide access to an EdgeDB database, which stores application data.
The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction. This TypeScript SDK implements the full MCP specification, making it easy to.
The Wordware MCP (Master Control Program) server allows you to run your Wordware apps locally, with interactive setup. Runs locally from the wordware-mcp npm package.
★not rated 0 1y agoA
tokens not measured
originalMIT
A configured local MCP server launched from the vibelogic-mcp npm package. MCP is a standard way for applications to provide capabilities to AI clients.
★not rated 0 4mo agoA
tokens not measured
originalMIT
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Local Ollama-backed MCP server — 45 tools, smart buffer, execution filters, persistent scratchpad, settings GUI. Runs locally from the localthink-mcp Python package.
★not rated 0 5mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: