3,839 servers in this category
MCP plugin that validates AI agent edits in RAM before they touch disk. Spectral clustering, architecture diffs, bridge detection, dead code oracle, and cross-file semantic checks for TypeScript, Go (gopls), and Python (pyright). Zero cloud dependencies.
Pre-execution governance for AI agents. Validates tool calls before they execute.
Biologically-inspired persistent memory engine for Claude Code MCP agents
Convert AI Skills (Claude Skills format) to MCP server resources - Part of BioContextAI
MCP Memory Server with DuckDB backend
A Model Context Protocol (MCP) proxy server that translates tool calls into TypeScript code generation. Instead of making multiple tool calls back and forth, LLMs can write TypeScript code that calls multiple tools naturally, reducing token overhead and leveraging the LLM's superior code generation capabilities.
A local proxy that strips web pages down to clean text before they enter your AI agent's context window. 704K tokens → 2.6K tokens. No LLM required.
🔬 MCP server for AI-powered napari control. Connect Claude, ChatGPT, Cursor, and other LLMs to napari for interactive image analysis. Perfect for automating microscopy workflows and building intelligent image analysis tools.
53 tools for LLM Conveyors: job hunting, B2B sales, ATS scoring, resume tools.
Model Context Protocol server for Tick.md - enables AI agents to coordinate tasks programmatically
Cuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.
Bitcoin data for AI agents. 27 tools with x402 micropayments. No API keys needed.
Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.
Pipes Claude Code session output into Claude Chat — no more copy-paste between tools
CI-1T prediction stability engine. Detect ghosts, evaluate drift, monitor fleets. 20 tools.
An MCP server for processing images using Florence-2
AI-powered MCP server for analyzing Architectural Decision Records (ADRs).
Nia is a context-augmentation layer for agents, primarily designed for coding agents. It provides them with an up-to-date knowledge base and improves their performance by 27%.
Content-addressed semantics: fail-closed handshakes over 453 cognitive patterns.
MCP proxy that reduces Claude context token usage by ~85-96% via lazy tool loading. Works with Claude Code, Claude Desktop, and any MCP client.