unntak-mcp is an open-source MCP server that facilitates integration with the unntak.no agent API. Below are 34 frameworks & sdks apps with similar functionality to unntak-mcp, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
ucm-mcp is an open-source MCP server designed for AI-agent code navigation and mapping. It supports AST parsing and integrates with AI agents to facilitate code analysis and automation. The tool is aimed at developers building intelligent code navigation solutions or automating codebase understanding.
MCP Server for Claude Desktop - Agent OS kernel primitives including code safety verification, CMVK multi-model review, and IATP trust
itu-mcp is an open-source Model Context Protocol (MCP) server that connects İTÜ Ninova (LMS) and OBS student portals to AI tools like Claude and Codex. It provides APIs for accessing courses, grades, deadlines, and transcripts, enabling developers to build educational integrations and AI-powered assistants.
agent-harnesses-mcp is an open-source MCP server that provides recommendations, search, and head-to-head decision guides for over 100 agent harnesses. It is designed for AI developers and researchers working with LLM-based agents, offering weekly rescoring and structured comparison tools.
agentdrive-mcp is an open-source MCP server designed for use with Claude Code, enabling agent-driven automation and integration via API. It is suitable for developers building automation systems and agent frameworks.
Memanto is an open-source, on-premises memory agent designed to provide persistent semantic memory for AI agents. It addresses the challenge of enabling AI agents to retain, organize, and recall information across sessions, helping them avoid forgetting decisions, conventions, and context between interactions. The tool is built on an information-theoretic search engine and is structured to run entirely on a user's local machine, requiring no API keys, vector databases, or external backend services. Memanto supports instant ingestion of information, with memories becoming searchable immediately after being written, and boasts recall latency of under 90 milliseconds. It implements features such as conflict resolution, semantic categorization into 13 types, verifiable memory sources, deterministic search, temporal queries, and info-theoretic scoring. The system is designed to prioritize freshness, ensuring that new facts outrank outdated ones, and automatically resolves conflicting data as it is ingested. The platform offers a range of integrations, supporting over 17 different agents and frameworks, including Claude Code, Cursor, Codex, GitHub Copilot, Gemini, and others. Users can manage agents, store memories, and perform retrieval-augmented generation (RAG) directly from the command line interface. Additionally, Memanto provides a local interactive dashboard for managing agents and memories, viewing conflicts and connections, and migrating from other memory solutions. Embeddings and answers are processed locally, ensuring that no data leaves the user's laptop. Installation is streamlined through a single pip install command, and users can choose between cloud and on-premises backends, with the on-premises option requiring Docker and running on localhost. Memanto is positioned as a solution for developers and teams building or operating AI agents who require reliable, persistent, and private memory infrastructure. The tool is offered completely free of charge under an open-source license.
canopy-mcp is an open-source MCP proxy server and agentic hook tool that enables developers to write and enforce policies on agent tool flows. It provides a CLI interface for managing and customizing agent behaviors in automated systems.
mcp-agent-handoff is an open source portable MCP server designed for managing agent handoff states and review tracking in AI agent workflows. It implements the MCP protocol and can be self-hosted for integration into agentic systems.
Works With Agents MCP Server — 14 native tools for AI agent infrastructure. Facts, Pitfalls, Skills, Handoff Protocol, Blueprint Registry, Trust Scores, Identity Verification, SLA Validation, Compliance-as-Code.
contextl-mcp is an open-source MCP server designed for AI coding agents. It provides repository intelligence, code search, and integrates with the Model Context Protocol, allowing developers to build advanced AI-powered code tools. Distributed under the MIT license.
unraid-mcp is an open-source MCP server and CLI/API toolkit for interacting with Unraid servers through their GraphQL API. It supports automation, monitoring, and integration with homelab setups using the Model Context Protocol.
agentsync-mcp is an open-source Python package for decentralized coordination among AI agents. It enables agents to claim work, survey peers, detect conflicts, and reconcile changes using the Model Context Protocol (MCP) and git branch operations. Ideal for developers building distributed agent systems.
mcp-missioncache is an open-source MCP server designed for project management and time tracking, integrating with the Claude Code plugin. It enables developers to manage tasks and track time efficiently using the Model Context Protocol.
mcp-agent-tester is an open-source tool for inspecting, testing, and running MCP servers and agents. It provides both a web UI and CLI, supports JSON trace export, and is designed for developers working with Model Context Protocol agents and infrastructure.
MCP Servers is a marketplace and discovery platform that enables users to search for and explore a variety of MCP servers, clients, command-line tools, integrations, and reusable workflows. The platform is organized into categories such as Developer Tools, AI & Agents, Cloud & Infrastructure, Memory & Knowledge, and Media & Design, making it easier to find production-ready servers and related resources. The service highlights featured servers and clients, including those supporting payments, analytics, code editing, and database management. It lists both remote and local servers, as well as official and agent-ready CLI tools for tasks like JavaScript runtime management, database querying, audio/video processing, and cloud development. MCP Servers also showcases reusable prompts and workflows, referred to as "loops," which can automate tasks such as testing, accessibility auditing, code coverage, and continuous integration monitoring. In addition to servers and CLI tools, the platform features agent skills tailored for AI agents, covering areas like brainstorming, systematic debugging, writing plans, and skill invocation. These resources are designed to facilitate the connection of AI applications to various tools, data sources, and automated workflows. The platform also provides a feed of trending and newly published servers, offering insights into what the community is installing and using. MCP Servers is aimed at developers and those building AI-powered applications who need to integrate diverse tools and automate workflows. The platform is web-based and includes a registry of available servers, clients, and integrations.
Minimal stdio MCP server for parallel task execution by AI agents
rutherford-mcp-server is an open-source MCP server designed to orchestrate a crew of agentic coding agents using the Agent Client Protocol (ACP). It enables developers to coordinate multiple code-generating agents, manage consensus, and automate complex coding workflows. Ideal for AI developers building agentic systems.
maa-mcp is an open-source MCP server based on MaaFramework, enabling automation of Android and Windows desktop tasks for AI assistants. It supports integration with OCR and various automation workflows for developers building AI-powered automation solutions.
postman-mcp is an open-source MCP server that generates and updates Postman requests directly from your API code, providing diffs before every write. It is designed for API developers who want to automate and streamline their API testing workflows.
Engrava is a memory database designed specifically for AI agents, providing a local, embedded solution for managing agent memory with features such as graph memory, hybrid search, and an optional tamper-evident journal. It operates on SQLite and does not require a separate server, allowing all operations to run within the user's Python process. The platform is intended for developers building AI agents who need a deterministic, typed, and local data layer for storing and retrieving structured memory. The database supports hybrid search by combining FTS5 (full-text search), vector search, recency, priority, and graph-based queries, fusing five different signals for retrieval. Engrava includes primitives for storing and recalling memories with simple function calls, and it features auto-embedding of data without requiring manual vector management or record assembly. The system manages memory structure using typed thoughts and typed edges, all contained within a single SQLite file. It also provides lifecycle management for data, with states such as CREATED, ACTIVE, DONE, and ARCHIVED. Additional capabilities include an algorithmic memory consolidation feature called "dreaming," which operates deterministically based on configurable signals and gates, without relying on language model calls. The optional audit trail records mutations in a SHA-256 hash-linked journal, making the journal tamper-evident. Engrava offers a query language called MindQL, supporting commands like FIND, COUNT, and SELECT, and allows bi-temporal queries using valid-time attributes for facts, enabling time-travel queries and logical invalidation without deletion. Multiple embedding providers are supported, including local models, OpenAI-compatible services, Ollama, and HuggingFace. Engrava can be installed via pip and configured with a YAML file. It includes a standalone MCP server (engrava-mcp) for connecting agents and offers a read-only mode. The tool supports isolated memory per service, with each managed in its own database file. Engrava is distributed under the MIT license, and there is no required service, per-operation metering, or data egress unless a remote provider is configured.
ai-firewall-mcp is an open-source MCP server component for AI Firewall, providing a security layer for large language models. It helps AI security engineers protect LLM deployments from prompt injection and jailbreak attacks using a multi-agent approach.
MCP Servers is a WordPress plugin designed to assist site administrators in configuring and exposing MCP servers with selected abilities on their WordPress sites. The tool facilitates integration between WordPress and AI agents by enabling secure authentication and permission management for server access. The plugin supports the configuration of user roles and authentication methods for AI agents interacting with the MCP server. It provides guidance on creating dedicated user accounts, such as a user named "mcp" with an appropriate role, and on generating application passwords for Basic Auth. For AI agents requiring OAuth2 authentication, the documentation suggests installing an additional plugin, such as WP Oauth Server, to enable OAuth2 support within WordPress. The plugin also addresses compatibility considerations for specific AI agents, including Mistral and Claude Desktop, and offers instructions for connecting via local proxies and token-based authentication when necessary. Installation of MCP Servers is handled through the standard WordPress plugin upload process, and the plugin is set to update automatically after the initial installation. Logging and debugging features are available: if WordPress debugging is enabled, internal events are recorded in the error log, and when logging is activated, MCP server activities are accessible via a dedicated logs page within the plugin. MCP Servers is available for download from GitHub.
MCP server for Link local agent memory — remember, recall, search, context, and graph traversal
okta-mcp-server is an open-source server implementing the Model Context Protocol (MCP) for Okta, allowing developers to integrate Okta management operations into LLMs and AI agents using natural language. It supports identity and access management workflows and is suitable for developers building AI-powered automation or agentic systems that require Okta integration.
MCPfinder is a free, open-source discovery and installation layer designed for AI agents to locate and configure Model Context Protocol (MCP) servers. It serves as an MCP server itself, enabling AI assistants to programmatically search multiple MCP registries, inspect trust signals, and generate install-ready JSON configurations for downstream MCP servers. The tool is intended primarily for AI agents, with humans only needing to install it once; after installation, the AI assistant can use MCPfinder repeatedly to expand its capabilities on demand. Key features include multi-registry search, aggregating MCP servers from the Official MCP Registry, Glama, and Smithery into a unified search interface. MCPfinder allows AI agents to find candidate servers by keyword, technology, or use case, inspect trust signals and required environment variables, and generate client-specific configuration snippets suitable for platforms such as Claude Desktop, Cursor, Claude Code, Cline, or Windsurf. The tool provides structured outputs, including confidence scores, recommendation reasons, warning flags, and install complexity, helping AI assistants make informed decisions about which servers to recommend or install. MCPfinder is delivered as an MCP server that can be added to any MCP-compatible AI client. Installation is flexible, supporting direct execution via NPX (no install needed), global installation with NPM, or project-based integration. Once installed, it operates as an always-up-to-date agent-facing layer, bootstrapping from published snapshots and syncing from upstream registries. This ensures that AI agents have access to the latest available MCP servers and their metadata, with freshness signals provided by snapshot manifests. 0 and is free to use, with the source code available for inspection, contribution, or forking. MCPfinder is built by the community for the community, and as of its latest published snapshot, it aggregates tens of thousands of MCP servers across multiple registries. Its focus on agent-native discovery, trust signal inspection, and install-ready configuration distinguishes it as an AI-centric solution within the ecosystem of MCP tools.
mcp-mcts is an open-source CLI tool for local MCP security scanning, attack chain analysis, inventory management, and CI integration. It supports optional Semgrep and LLM analysis, making it suitable for security engineers and DevOps teams focused on codebase security.
onb-mcp is an open-source Python package providing an MCP server that wraps the Open Notebook API. It enables developers to integrate and automate notebook workflows using the MCP protocol, facilitating interoperability and automation in data science and research environments.
mcp-server-microsoft-tasks is an open-source MCP server that enables unified access to Microsoft Tasks (Planner and To Do) for agents and developers. It supports read-only access by default and is designed for integration with agent frameworks.
miosa-mcp is an open-source MCP server that exposes MIOSA computer-use tools for integration with Claude Code and other agent frameworks. It provides a standardized API for agent developers to enable automation and computer control capabilities in their AI systems.
agentfetch-mcp is an open-source MCP server designed for AI agents to fetch web URLs, estimate token usage, and route requests intelligently. It supports smart caching and is built for integration with agent frameworks and AI pipelines.
tappy-mcp is an open-source command-line tool for discovering, configuring, running, inspecting, and monitoring Model Context Protocol (MCP) servers across AI clients. It provides infrastructure engineers and developers with essential tools to manage and monitor MCP-based AI deployments efficiently.
imap-mcp-server is an open-source CLI tool that acts as a minimal MCP server, enabling MCP-capable agents to interact with IMAP mailboxes. It is designed for developers who need to automate email processing or bridge agent frameworks with email systems. The package is lightweight and easy to deploy.
KeeperHub serves as an execution layer for onchain agents, enabling reliable transaction delivery for workflows in decentralized finance (DeFi). It is designed for agents that manage strategy while KeeperHub ensures transactions are executed as intended. The platform supports calling DeFi workflows from agents via the Model Context Protocol (MCP) or REST interfaces, with additional compatibility for x402 and MPP standards. KeeperHub is ERC-8004 registered and offers integrations with 12 EVM-compatible chains and over 20 DeFi protocols, including Aave, Spark, Lido, Safe, Morpho, Pendle, Compound, Yearn, Curve, Uniswap, CowSwap, and Chronicle. Users can build workflows using a graphical UI or programmatically through agents, specifying triggers such as cron schedules or onchain events, and defining multi-step actions. The system includes features like transaction retries, smart gas pricing based on network averages, exponential backoff, nonce management, and multi-RPC failover to enhance reliability and cost efficiency. Each workflow execution is logged with full records, including trigger events, transaction submissions, gas usage, outcomes, and timestamps, and every run is replayable from a single interface. KeeperHub provides a marketplace for DeFi strategies, allowing users to publish workflows, keep their logic private, and earn per call. Workflows can be called by agents or users over MCP or REST, and callers pay per execution in USDC using x402 or MPP. The platform incorporates enterprise-grade wallet security with embedded cross-chain non-custodial wallet infrastructure, where each organization receives a wallet secured by Turnkey, ensuring that keys remain in secure enclaves and never touch KeeperHub's infrastructure. Workflows are able to sign transactions directly, including unattended operations. KeeperHub is fully open source and is positioned for AI agents, protocol teams, DAOs, and enterprises seeking reliable, programmable onchain execution in DeFi environments. It is accessible via web UI, CLI, and API, and supports agent-native surfaces for seamless integration with MCP runtimes. The platform is in beta and offers hosted DeFi strategies with per-execution pricing paid in USDC.
agent-brain-ag-mcp is an open-source Model Context Protocol (MCP) server that exposes Agent Brain as MCP tools, resources, and prompts. It enables developers to integrate Agent Brain capabilities into agent-based applications, supporting RAG workflows and Claude integration. Ideal for AI developers seeking extensible agent frameworks.
