The Model Context Protocol (MCP) lets coding agents like Claude Code, Cursor, and Codex call external tools, from databases and browsers to docs and design files. This list covers MCP servers, gateways, and clients that developers plug into their agents.
How we rank: Tools whose review mentions MCP or the Model Context Protocol. Tools where MCP is named in the name, tags, or summary rank higher.
01Quick answer
Top pick: Screen Browser (Paid). Screen Browser is a polished, agent-first way to produce narrated web app walkthroughs, with a genuinely useful free check step, no charge for failed runs, and clean credential handling. The trade-offs are real: no free plan, minutes-based pricing that shrinks with richer settings, a five-minute video cap, and strict login and reachability requirements that rule out many internal or OAuth-protected apps.
Best free option: BashCut. Developers and creators on macOS who want coding agents (Claude Code, Codex) to script and automate video edits through a CLI or MCP while keeping edits visible and undoable in a real timeline.
Also strong: BashCut, DBX.
02At a glance
| # | Tool | Pricing | Category | Best for |
|---|---|---|---|---|
| 01 | Screen Browser MiCCA OÜ | Paid | Productivity | Product, developer and DevRel teams with a deployed web app who want repeatable narrated demo or tutorial vid… |
| 02 | BashCut Nolan / dongnguyenvie | Open Source | Productivity | Developers and creators on macOS who want coding agents (Claude Code, Codex) to script and automate video edi… |
| 03 | DBX DBX | Free | Productivity | Developers who want a fast, free multi-database client and want their coding agents to query the same connect… |
| 04 | agentgateway Agentic AI Foundation (Linux Foundation) | Open Source | Productivity | Platform teams that need to secure, govern and observe LLM, MCP and agent-to-agent traffic across many agents… |
| 05 | Fast Agent EvalState | Open Source | CLI Agents | Developers building complex agentic workflows, coding assistants, or data analysis tools that require deep MC… |
| 06 | codebase-memory-mcp DeusData | Open Source | Codebase AI | Teams working in large monorepos or complex codebases (over 50 files) who need to reduce token usage and impr… |
| 07 | ADR Uber | Open Source | Code Review | Security and platform teams that need visibility into which AI coding agents and MCP servers employees run, a… |
| 08 | MCPJam MCPJam | Freemium | CLI Agents | Developers and teams building MCP servers who need to ensure reliability, protocol compliance, and consistent… |
| 09 | Claude Code Templates Daniel Avila | Open Source | Productivity | Claude Code users who want to quickly bootstrap projects with proven agents, hooks, and MCP setups while gain… |
| 10 | Chrome DevTools MCP Google | Open Source | Productivity | Frontend developers and AI agents needing to debug runtime issues, optimize web performance, or verify code c… |
| 11 | Mobile MCP Mobile Next | Open Source | Productivity | Automating multi-step user journeys, native app testing, data extraction, and scripted form interactions driv… |
| 12 | Reqode Almware Ltd. | Freemium | Productivity | Software teams using AI coding agents like Codex, Cursor, and Claude Code on complex products where features… |
| 13 | OpenHuman Tiny Humans | Open Source | Async Agents | Developers who want a lightweight, self-hosted agent harness they can run locally, embed in Rust code, or sca… |
| 14 | Odysseus odysseus-dev | Open Source | General AI | Developers and homelab users who want one private, self-hosted workspace for agents, local models and everyda… |
| 15 | Headroom Headroom Labs | Open Source | Productivity | Developers and teams running coding agents on large logs, JSON or codebases who want to cut token spend and c… |
| 16 | Docker Agent Docker | Open Source | Async Agents | Developers and platform teams already using Docker who want versionable, shareable agent definitions they can… |
| 17 | Archestra Archestra Inc. | Freemium | AI IDEs | Platform teams needing to secure, scale, and govern AI agents and LLM usage across an enterprise Kubernetes e… |
| 18 | Atomic Chat Atomic Local Ai | Free | AI IDEs | Users seeking a private, offline-capable AI experience across desktop and mobile, and developers needing a lo… |
| 19 | Goose Agentic AI Foundation (Linux Foundation) | Free | CLI Agents | Developers and teams who require a vendor-neutral, highly extensible agent platform that supports local execu… |
| 20 | iFlow CLI iFlow | Freemium | CLI Agents | Developers and DevOps operators needing a terminal-native agent for repository onboarding, automated refactor… |
| 21 | Floot Floot | Freemium | Web Builders | Founders, non-technical operators, and agencies building MVPs, internal tools, or SaaS products who want to a… |
| 22 | ContextStream ContextStream | Freemium | Codebase AI | Developers and teams who want their AI coding assistants to maintain long-term project context, avoid repetit… |
| 23 | Tseha MH Mariusz Henn | Freemium | Codebase AI | Engineering teams needing to enforce architectural consistency, coding standards, and design system usage acr… |
| 24 | Brain Scanner Kevin Lozada Santos | Free | Codebase AI | Developers working with coding agents who need to visualize project structure and track changes across sessio… |
| 25 | Gortex zzet | Open Source | Codebase AI | Developers working on large, polyglot, or multi-repository codebases who want to optimize AI agent performanc… |
03Ranked list
Screen BrowserMiCCA OÜ
Screen Browser is a polished, agent-first way to produce narrated web app walkthroughs, with a genuinely useful free check step, no charge for failed runs, and clean credential handling. The trade-offs are real: no free plan, minutes-based pricing that shrinks with richer settings, a five-minute video cap, and strict login and reachability requirements that rule out many internal or OAuth-protected apps.
BashCutNolan / dongnguyenvie
BashCut is a compelling, MIT-licensed option for agent-driven video editing on macOS, with a genuinely novel CLI/MCP surface and no extra AI cost if you already pay for Claude or ChatGPT. The trade-offs are its macOS-only scope and in-progress status, so expect rough edges and some unverified features.
DBXDBX
A remarkably capable, lightweight database client whose MCP server makes it a practical data bridge for AI coding agents.
agentgatewayAgentic AI Foundation (Linux Foundation)
A foundation-hosted, enterprise-grade gateway that is becoming a standard connectivity layer for MCP and A2A workloads.
Fast AgentEvalState
A powerful, developer-centric toolkit that excels in MCP-native agent orchestration and provides a highly flexible, scriptable environment for advanced AI automation.
codebase-memory-mcpDeusData
A highly efficient, local-first tool that is an essential utility for power users of AI coding agents, offering massive token savings and superior structural awareness at the cost of a slight learning curve for setup.
ADRUber
ADR is a credible, production-proven foundation for governing AI coding agents in an enterprise, backed by Uber's deployment and a peer-reviewed paper. It is strongest for discovery, observability and detection research; teams wanting enforcement will need to add their own prevention layer.
MCPJamMCPJam
MCPJam is the industry-standard 'Postman for MCP,' offering an essential, robust toolkit for any developer serious about shipping reliable AI-integrated software.
Claude Code TemplatesDaniel Avila
An essential, community-driven hub for Claude Code users that simplifies configuration and adds valuable observability, though users should review third-party components for security as they execute with agent permissions.
Chrome DevTools MCPGoogle
An essential, high-leverage tool for any developer using AI coding assistants; it eliminates the friction of manual copy-pasting by giving AI direct, actionable visibility into the browser.
Mobile MCPMobile Next
A powerful, highly capable tool for developers and agents needing to bridge the gap between LLMs and mobile environments, though users should prioritize accessibility-based interaction over coordinate-based tapping for better reliability.
ReqodeAlmware Ltd.
Reqode offers a structured, traceable way to keep AI coding agents aligned with product intent and architecture, with transparent credit-based AI pricing and self-hosting options. However, AI credits cost extra on most plans, self-hosting is pricey, and there are no user reviews yet to validate real-world value.
OpenHumanTiny Humans
A fast-moving, unusually efficient open-source harness with strong adoption signals; promising for local and fleet-scale agent work, but still early beta with frequent releases and rough edges.
Odysseusodysseus-dev
A feature-rich, open-source alternative to hosted AI assistants for people who want agents and local models on their own hardware.
HeadroomHeadroom Labs
A widely adopted, actively maintained way to make coding agents cheaper and less context-starved, with unusually broad agent integrations and a local-first design.
Docker AgentDocker
A pragmatic, YAML-first way to build and share agents that fits naturally into existing Docker tooling.
ArchestraArchestra Inc.
A robust, security-first infrastructure layer that effectively bridges the gap between developer-favorite AI tools and enterprise compliance requirements.
Atomic ChatAtomic Local Ai
A highly versatile, all-in-one local AI tool that stands out for its cross-platform availability, agent-focused features, and seamless integration with developer workflows.
GooseAgentic AI Foundation (Linux Foundation)
Goose is the premier open-source infrastructure for vendor-neutral agentic AI. While it requires more initial configuration than commercial alternatives like Claude Code, its flexibility, foundation-backed governance, and cost-optimization capabilities make it the superior choice for power users and organizations prioritizing long-term portability.
iFlow CLIiFlow
A highly capable and extensible terminal AI assistant that offers excellent automation and multi-model support, though its upcoming shutdown makes it unsuitable for new long-term project adoption.
FlootFloot
Floot is a highly efficient, all-in-one platform that effectively bridges the gap between AI-generated code and live, production-ready applications without requiring technical DevOps knowledge.
ContextStreamContextStream
An essential tool for power users of AI coding agents who need to bridge the gap between ephemeral chat sessions and a durable, project-wide knowledge base.
TsehaMH Mariusz Henn
A robust, highly secure governance layer for AI-assisted development that eliminates manual synchronization of project rules by providing an always-current source of truth for AI agents.
Brain ScannerKevin Lozada Santos
A useful, specialized utility for agent-assisted developers to maintain transparency and auditability in AI-generated codebases during its beta stage.
Gortexzzet
Gortex is a powerful, locally-run tool that transforms how AI agents interact with code by replacing inefficient file-reading loops with structured, graph-based queries, making it an essential utility for power users of AI coding assistants.
04FAQ
What are the best MCP servers for AI coding in October 2026?+
Screen Browser ranks first for October 2026. Screen Browser is a polished, agent-first way to produce narrated web app walkthroughs, with a genuinely useful free check step, no charge for failed runs, and clean credential handling. The trade-offs are real: no free plan, minutes-based pricing that shrinks with richer settings, a five-minute video cap, and strict login and reachability requirements that rule out many internal or OAuth-protected apps. Also consider BashCut and DBX.
How are these tools ranked?+
Tools whose review mentions MCP or the Model Context Protocol. Tools where MCP is named in the name, tags, or summary rank higher. The list is rebuilt from the directory's reviews every month.
Are any of these MCP tools free?+
17 of the 25 tools listed are free or open source. See the comparison table for each tool's pricing model.