"Creating a Custom Local Knowledge Base" matching MCP servers:

A multi-agent RAG MCP server that answers questions from your documents with a human-in-the-loop approval step, using a coordinator, retriever, and synthesizer agents.

MCP server for creating, monitoring, and managing Devin AI sessions.

COS-MCP is an MCP server that provides AI-powered organizational continuity planning. It maintains a knowledge graph of employees, systems, projects, and relationships, and exposes tools, resources, and prompts for knowledge graph visualization, risk analysis, employee transition planning, and organizational knowledge base queries.

A template and demonstration project for building, testing, and deploying remote MCP servers using FastMCP and uv. It provides a foundational structure for creating MCP-compliant tools that can be hosted publicly and integrated with LLM agents.

A personal memory engine and MCP server that stores durable facts in markdown files managed via git, enabling hybrid search (lexical + semantic) through an MCP interface for persistent context across LLM sessions.

Spawn parallel autonomous AI agent sessions from a single MCP client. Each agent gets its own workspace, tools, and execution context.

Enables a Claude Code agent to drive Big Interview ResumeAI locally over stdio, exposing six tools for checking auth status, listing, starting, monitoring, retrieving feedback for, and deleting resume scans. Every call returns structured success or error payloads for reliable agent workflows.

Read-only MCP server for the Bucharest Stock Exchange, exposing instrument data, OHLCV candles, and fundamentals through a public backend with no authentication.

A secure MCP server that stores and retrieves API keys and credentials, featuring encrypted storage, masked retrieval, and AI-powered recommendation via MCP sampling.

Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.

A minimal MCP server that enables HTTP requests with any method, headers, and body types, supporting large responses through chunked transfers with disk-backed caching.

Connects AI agents to MAVLink drones (PX4, ArduPilot) via a capability layer with safety guardrails, enabling telemetry, flight control, and mission management through natural language.

MCP server that enables cloud models (like Gemini/Claude) to delegate coding tasks to a local llama.cpp server, preserving cloud usage limits through an AI-powered code review loop.

Enables management of Kylas CRM lead operations, including creating leads, searching and filtering records, and resolving user, product, or pipeline IDs. It provides specialized tools for monitoring idle leads and accessing lead schema instructions through natural language.

Enables local forensic analysis of files by orchestrating system binaries (file, exiftool, strings, Volatility) via safe subprocess execution.

Exposes a Kubernetes cluster to MCP-compatible AI clients, enabling read-only and optional write operations on cluster resources like pods, deployments, and namespaces through natural language.

Enables local agents to connect to and interact with Google Colab sessions running in the browser.

A Model Context Protocol server built with FastMCP that provides tools for retrieving the current local date and time. It allows LLMs to access precise temporal information directly from the host environment.

A blast-radius auditor for AI agents that computes combined effective permissions across all connected MCP tools, detects dangerous capability combinations deterministically, and provides a live risk graph and one-click policy fixes.

Bridges a local AI agent to a Colab session in the browser, enabling code execution and file operations through the Model Context Protocol.