MCP servers and tools

• Playwright MCPOfficial Microsoft MCP server for Playwright browser automation

  Free / OSS · Apache-2.0 · 38.4k GitHub stars

  VerdictThe standard way to give MCP clients browser access.

  CatchIt is a control interface, not a complete solution. You still need browser infrastructure (local Chromium or Browserbase). No built-in session management, authentication, or scaling.

• GooseLocal-first Rust agent with MCP at its core

  Free / OSS · OSS/MIT

  VerdictLocal-first, MCP-native, model-agnostic. Bring your own brain.

  CatchGeneral-purpose agent means you configure it for your use case. You bring the model—Goose is the runtime, not the intelligence. Documentation is still maturing.

• Chrome DevTools MCPOfficial Chrome DevTools as an MCP server for coding agents

  Free / OSS · Apache-2.0 · 53.9k GitHub stars

  VerdictThe MCP browser for agents that need real DevTools, not just clicks.

  Catchchrome-devtools-mcp@1.8.0 engines: "^20.19.0 || ^22.12.0 || >=23". 20.16 and 20.17 fail; 20.19 LTS is in engines. “Node ≥ 22.12” and “Node 20 fails” are both too blunt — README “LTS” is marketing; engines is the catch. A CLI is provided for use without MCP; official CLI docs call it experimental. Complementary to Playwright MCP —DevTools-grade traces, Lighthouse, heap snapshots, and --autoConnect, not a generic scraper or a Playwright replacement. Officially supports Google Chrome and Chrome for Testing only. Exposes browser content to the MCP client—do not point it at sensitive sessions. Usage statistics on by default (opt out with --no-usage-statistics). Needs a current Chrome.

• CodeGraphMIT local AST code knowledge graph for coding agents

  Free / OSS · OSS/MIT · 74.6k GitHub stars

  VerdictMIT local code graph for agents. Free forever; packers are the text cousins.

  CatchIndex cost and residual context occupancy are real. Not a hosted SaaS brain. Distinct from Repomix/Gitingest (pack text) and Aider (edit loop).

• OpenCodeMIT OSS coding agent: CLI, TUI, desktop; BYOK/local

  Free / OSS · OSS/MIT · 219k GitHub stars

  VerdictMIT BYOK agent across CLI/desktop/IDE. The real catches are on /log: date stamp and compaction.

  CatchTwo catches worth reading on /log: “The date stamp is a trigger channel” (auto today’s-date × open-weight LoRA as a time-release fuse) and “Compaction ate the denial” (long sessions prune hard vetoes; compaction is untrusted rewrite). Re-read those two notes before you treat OpenCode as set-and-forget.

• Kilo CodeMIT OSS IDE+CLI agent; active Cline/Roo line + MCP marketplace

  Free / OSS · OSS/MIT · 27.7k GitHub stars

  VerdictMIT IDE+CLI agent with MCP marketplace. Roo’s active heir, not a second OpenCode.

  CatchPitch IDE+platform, not “another OpenCode.” Gateway/account is convenience; BYOK stays. Marketplace and modes are the differentiator vs plain CLI harnesses. Enterprise governance rides Anaconda — evaluate if that middle layer matters for your org.

• SerenaMIT MCP toolkit: symbol-level retrieve/edit via free LSP

  Free / OSS · OSS/MIT · 30.5k GitHub stars

  VerdictMIT symbol MCP for agents. Free LSP core; JetBrains plugin is optional paid.

  CatchComplements agents; it is not a turnkey SWE loop. JetBrains plugin backend is paid optional (free trial) — LSP path stays free. Symbol quality tracks whatever language server you wire.

• SuperGatewayMIT stdio↔SSE/WS bridge for MCP transports

  Free / OSS · OSS/MIT · 2.9k GitHub stars

  VerdictMIT MCP transport bridge. Wire stdio to remote clients; expect zero new capabilities.

  CatchPlumbing only — not a Playwright/Chrome DevTools MCP capability server. It does not add browser, docs, or symbol tools; it only rewires transport. If your client already speaks the server’s native transport, you do not need it.

• FastMCPApache-2.0 framework to build MCP servers/clients/apps

  Free / OSS · Apache-2.0 · 28.2k GitHub stars

  VerdictApache-2.0 MCP framework. Ship servers with it; do not confuse it with a tool marketplace.

  CatchBuild MCP apps ≠ use live MCP servers. Distinct from Playwright MCP / Context7 / Serena (capability servers) and from SuperGateway (transport glue). Horizon paid optional for ops at scale; day-one path is OSS FastMCP alone.

• VoltAgentMIT TypeScript agent framework + optional VoltOps console

  Free / OSS · OSS/MIT · 10.9k GitHub stars

  VerdictMIT TypeScript agent framework. VoltOps optional; core is the gem.

  CatchVs Mastra (TS runtime) and CrewAI/Agno (Python): VoltAgent is TS framework + platform surface, not a terminal coding agent. VoltOps is the paid/hosted ops layer; core stays MIT. Framework lock-in applies — you are building agents, not buying Claude Code.

• mcp-remoteMIT npx stdio↔remote MCP proxy with OAuth support

  Free / OSS · OSS/MIT · 1.6k GitHub stars

  VerdictMIT remote-MCP stdio shim. Use until your client speaks OAuth remote natively.

  CatchVs SuperGateway (bidirectional stdio↔SSE/WS bridge): mcp-remote is the client-side remote+OAuth drop-in, not a capability server and not a full gateway product. Some clients already speak unauth remote MCP — you only need this for OAuth/legacy stdio hosts. Adds a local Node process in the path.

• MCP InspectorMIT official MCP server debugger — web, CLI, and TUI

  Free / OSS · OSS/MIT · 11.1k GitHub stars

  VerdictOfficial MIT MCP inspector. Test servers here; ship them elsewhere.

  CatchDebug surface, not a production MCP gateway or registry (see Smithery) and not transport glue (SuperGateway/mcp-remote). You still author servers elsewhere (FastMCP, etc.). v2 is the active line; pin versions in CI.

• ComposioFreemium agent toolkits + managed OAuth across 1000+ apps

  Free / OSS · Freemium · 30.7k GitHub stars

  VerdictFreemium agent tool/auth fabric. Great connectors; you rent the OAuth middle.

  CatchVs github-mcp (one official GitHub surface) and raw MCP servers: Composio is a multi-app auth/tool platform — you depend on their connector quality and hosted auth. Free tier exists; production is seat/usage freemium. Not a coding agent and not a browser fleet.

• GitHub MCP ServerMIT official GitHub MCP — issues, PRs, code, workflows for agents

  Free / OSS · OSS/MIT · 33.8k GitHub stars

  VerdictOfficial MIT GitHub MCP. Use for GitHub; use Composio when you need 1000 apps.

  CatchVs Composio (multi-app auth fabric): this is GitHub-only, official, and PAT/OAuth scoped to GitHub. Hosted remote path ties to GitHub/Copilot auth; local mode is yours to run. Permissions are the catch — over-scoped tokens are how agents leak. Not a generic toolkit marketplace.

• mcp2cliMIT runtime MCP/OpenAPI/GraphQL→CLI — zero codegen

  Free / OSS · OSS/MIT · 2.4k GitHub stars

  VerdictMIT MCP/OpenAPI/GraphQL CLI wrapper. Shell tools without shipping schemas every turn.

  CatchVs SuperGateway / mcp-remote (transport bridges) and MCP Inspector (debug UI): mcp2cli is a runtime CLI façade for APIs/MCP, not a gateway product and not an inspector. GraphQL mode needs introspection. You still trust whatever endpoint you point it at.

• mcp-useMIT fullstack TypeScript MCP — servers, apps, clients, agents

  Free / OSS · OSS/MIT · 10.8k GitHub stars

  VerdictMIT fullstack MCP kit. Build servers and Apps; Manufact is optional soft upsell.

  CatchVs FastMCP (Python MCP framework), mcp-agent (MCP-as-runtime + Temporal), and Composio (managed tool/auth catalog): mcp-use is fullstack MCP app/server kit, not a multi-SaaS OAuth fabric. Manufact Free is an optional hosted/upsell path — core stays MIT you run yourself.

• BeeAI FrameworkApache-2.0 production agents in Python and TypeScript — MCP + A2A

  Free / OSS · Apache-2.0 · 3.4k GitHub stars

  VerdictApache-2.0 dual-language agent framework. MCP/A2A serve built in; you own ops and models.

  CatchVs Agno / VoltAgent / Google ADK (agent kits) and mcp-use / FastMCP (MCP server kits): BeeAI is dual-language agent framework + protocol serve, not a coding CLI and not a managed tool catalog. IBM open-source notice says community maintenance posture — treat it as OSS you own, not an IBM product SLA. A2A server is Python-first today.

• Microsoft Agent FrameworkMIT successor to AutoGen + Semantic Kernel — Python and .NET

  Free / OSS · OSS/MIT · 14.2k GitHub stars

  VerdictMIT Microsoft agent SDK. Prefer over AutoGen for new builds; watch Azure meters in prod.

  CatchVs AG2 (community AutoGen fork), LangGraph (graph orchestration), and Google ADK: MAF is Microsoft’s enterprise-shaped multi-agent SDK, not a coding seat. Foundry hosted agents and Azure model meters are paid paths — OSS framework still runs with BYO providers. AutoGen is maintenance-only; start new projects here, not there.

• Strands AgentsApache-2.0 model-driven agent SDK from AWS — Python and TypeScript

  Free / OSS · Apache-2.0 · 8.9k GitHub stars

  VerdictApache-2.0 AWS agent harness. Model-driven + MCP; Bedrock optional, not mandatory.

  CatchVs Agno / OpenAI Agents SDK / Microsoft Agent Framework: Strands is AWS-born harness with Bedrock gravity, not a coding CLI and not a React copilot UI. Bedrock/AgentCore paths meter when you leave local/BYO. Bring your own model spend either way.

• OpenAI Agents SDKMIT multi-agent workflows — tools, handoffs, tracing, MCP

  Free / OSS · OSS/MIT · 30.2k GitHub stars

  VerdictMIT OpenAI agent workflow SDK. Build multi-agent loops; API spend is separate.

  CatchVs openai-codex-cli (terminal coding agent), Vercel AI SDK (app AI primitives), and Microsoft Agent Framework: this is the workflow SDK, not the Codex CLI seat. OpenAI API keys and hosted tools meter; sandbox/realtime extras add surface area. Do not confuse with ChatGPT product seats.

• CopilotKitMIT agent-native UI layer — React copilots, AG-UI, MCP

  Free / OSS · Freemium · 38.1k GitHub stars

  VerdictMIT agent UI layer. Self-host free; Cloud Developer free forever is real but capped.

  CatchVs Vercel AI SDK (primitives) and Mastra/LangGraph (backend agent runtimes): CopilotKit is the user-facing agent UI/protocol layer, not the orchestration brain. Pro/Team Cloud and VPC are paid when you outgrow Developer free forever. Self-host keeps the MIT path.

• RowboatApache-2.0 local-first AI coworker — knowledge graph + MCP

  Free / OSS · Freemium · 18k GitHub stars

  VerdictApache-2.0 local AI coworker. Graph memory + MCP; paid cloud is optional.

  CatchVs OpenClaw / Continue / Claude Code (coding seats) and Mem0/Letta (memory runtimes): Rowboat is a full coworker desktop with graph memory, not a library you embed. Hosted Starter/Pro plans are paid convenience; OSS/local path is the free forever bar. Shell access on your machine means trust boundaries matter.

• GriptapeApache-2.0 Python agents, pipelines, RAG — MCP tools too

  Free / OSS · Apache-2.0 · 2.6k GitHub stars

  VerdictApache-2.0 Python agent/RAG framework. MCP as tools; Cloud free tier is metered, not forever.

  CatchVs LangChain/LangGraph and CrewAI: Griptape is a structured Python agent/RAG framework, not a coding CLI. Cloud Developer free tier needs a payment method on file and meters after small included quotas — pitch the OSS framework first, not Cloud as free forever.

• ScraplingBSD-3 adaptive scrape/crawl framework + MCP

  Free / OSS · BSD-3-Clause · 88.9k GitHub stars

  VerdictBSD-3 adaptive scrape/crawl + MCP. Self-run framework vs Firecrawl-shaped APIs.

  CatchVs Firecrawl-style hosted scrape APIs: Scrapling is a library/framework you run (plus MCP), not a metered scrape SaaS with a managed anti-bot fleet. You own proxies, blockers, and ops; MCP does not erase site ToS or legal risk. Not a general browser-agent product like Browser Use/Steel.

• mcporterMIT MCP as CLI + generate-cli / emit-ts (OpenClaw)

  Free / OSS · OSS/MIT · 5.1k GitHub stars

  VerdictMIT MCP→CLI/TS kit. Generate or call; different shape than mcp2cli runtime façade.

  CatchVs mcp2cli (runtime MCP/OpenAPI→CLI, zero codegen): mcporter leans generate-cli/emit-ts packaging and TS API shape — pick based on whether you want codegen’d CLIs vs pure runtime discovery. You still trust the MCP servers you wrap. Not an MCP transport gateway (see SuperGateway/mcp-remote).

• EngramMIT persistent agent memory — MCP, CLI, TUI, SQLite

  Free / OSS · OSS/MIT · 7.5k GitHub stars

  VerdictMIT agent memory primitive. MCP/CLI/TUI on SQLite; not a full agent framework.

  CatchVs Mem0 / Letta / full agent frameworks: Engram is the memory primitive (store + retrieve + surfaces), not an orchestration framework or coding agent. “local or cloud” branding means optional hosted/sync gravity — day-one stays OSS you run. You still decide what gets written and when.

• Open Code ReviewApache-2.0 hybrid deterministic+LLM review agent (MCP/plugins)

  Free / OSS · Apache-2.0 · 47.8k GitHub stars

  VerdictApache-2.0 hybrid review agent. Deterministic+LLM vs Semgrep/Gitleaks and vs general coding agents; BYO LLM.

  CatchVs Semgrep/Gitleaks (deterministic SAST/secrets): OCR adds an LLM agent layer for context-heavy review, not a drop-in replacement for static rules alone. Vs Claude Code/SWE-agent/OpenHands (general coding agents): OCR is a purpose-built review harness, not a full autonomous coder. BYO LLM cost — you bring the model endpoint and pay the provider; the OSS CLI itself is free.

• DeskcommCRMMIT self-hosted AI sales OS/CRM — MCP-ready

  Free / OSS · OSS/MIT · 4.7k GitHub stars

  VerdictMIT self-hosted AI sales CRM. Agents+WhatsApp vs Chatwoot/Composio; HostGator kit ≠ lock.

  CatchVs Chatwoot (open inbox/helpdesk) and Composio (agent tool auth/connectors): DeskcommCRM is an AI sales OS/CRM with WhatsApp agents, not a general shared inbox alone and not a universal tool marketplace. HostGator affiliate/setup kit is infra convenience, not product lock — you can host elsewhere.

• LibreChatMIT Agents/MCP chat UI — OpenAI-compatible, self-host

  Free / OSS · OSS/MIT · 46.1k GitHub stars

  VerdictMIT Agents/MCP chat UI. Self-host orchestration vs Open WebUI/AnythingLLM; BYO models.

  CatchVs Open WebUI / AnythingLLM (local RAG chat UIs): LibreChat leans hard into Agents/MCP/skills orchestration and multi-provider routing, not only RAG chat. You own auth, model keys, vector/DB ops, and upgrade discipline — the OSS UI is free; the models and infra are not.

• OpenStatusAGPL-3.0 status/uptime as code — Terraform/CLI/MCP

  Free / OSS · Freemium · 9.2k GitHub stars

  VerdictAGPL status/uptime as code. Free Hobby is tiny; self-host or pay when monitors multiply.

  CatchAGPL-3.0 — network copyleft on modifications you ship as a service. free cloud: one monitor / one page / 10m checks — fine for a side project, not a fleet. Vs Better Stack / Checkly-class SaaS, OpenStatus wins on OSS+IaC; you trade managed depth for license+self-host ops.

More with this tag (111)

• nanobot — Ultra-light self-hosted personal AI agent with WebUI, MCP, and memory
• Voicebox — Local-first OSS voice studio — clone, TTS, dictate, MCP voice for agents
• Octop — MIT self-hosted multi-user multi-agent platform
• MCPJam — OSS MCP testing, debugging, and evals platform
• Friday — Self-hosted cognitive memory MCP for coding agents
• AX Check — Hosted free agent-experience checklist + recorded coding-agent sessions
• TradingView MCP — Local CDP bridge: Claude/agents on your TradingView Desktop charts
• SLayer — MIT embeddable semantic layer for agents — MCP, SQL expressions, dbt/Cube import
• PageIndex MCP — Vectorless tree-index RAG over long PDFs — freemium MCP for agents
• Cua — Open computer-use drivers, sandboxes, MCP, and CUA-S1 decision models
• Context Mode — Elastic-2.0 MCP sandbox for tool output and session continuity
• Stitch Skills — Google Labs agent skills and plugins for the Stitch design MCP
• AURA — Apache-2.0 MCP-ready SRE agent platform for production incidents
• Agent Native — Define an action once and expose it to agents and every UI surface
• OKF Agent Memory — Git-native dual-memory for agents — OKF v0.2 + embedded MCP
• Skillbox — Self-hosted versioned skills library with MCP and scoped clients
• PaperGraph MCP — Evidence-first math-paper reading maps for AI agents
• Design Studio AI — Agent-first design workspace with MCP, CLI, and shared human edits
• Jev Review — Local MCP that scores coding-agent diffs with TypeSafe Jev
• Foremerge — Deterministic intent and scope conflict resolution for parallel agents
• Codex-X — Codex-specific desktop and CLI workspace for visual configuration and MCP skills
• OpenHuman — GPL-3 local-first agent orchestrator with memory trees and MCP
• Claude Code Templates — MIT npx catalog of Claude Code agents, hooks, settings, and MCPs
• Cloudflare MCP Servers — Apache-2.0 official domain-specific Cloudflare MCP server suite
• AI-Infra-Guard — Red-team platform for agent, MCP, and skill infrastructure
• treg — Metered tool catalog and team vault for agent integrations
• LitterBox — Malware and payload detection sandbox with LitterBoxMCP
• Jev MCP — Ten TypeSafe Jev judgment tools over local stdio MCP
• Agentao — MIT governed Python agent runtime — permissions, MCP, memory, replay
• Equibles — Self-hosted financial-data MCP — SEC, 13F, FRED, prices for agents
• Codebase Memory MCP — MIT persistent code knowledge graph MCP — static binary, no LLM key
• ARTEMIS — Apache Android NL automation + MCP for IDE coding agents
• CC Switch — MIT desktop All-in-One manager for Claude Code, Codex, OpenCode, and peers
• Hindsight — MIT retain→recall→reflect agent memory (+ MCP)
• AIO Sandbox — Apache one container: browser+shell+files+VS Code+Jupyter+MCP
• ContextForge — Apache MCP+A2A+REST/gRPC→MCP gateway with governance + OTel
• MCP Registry — Canonical protocol-org community MCP server registry
• SkillSpector — Apache NVIDIA scanner for agent skills before you install them
• OpenAI Tunnel Client — Apache customer daemon for Secure MCP Tunnel to ChatGPT/Codex
• emcee — MIT turn any OpenAPI into an MCP server for Claude and friends
• Klavis — Apache MCP integrations + Strata multi-tool server (hosted or self-host)
• Invisible Playwright MCP — MIT stealth Firefox Playwright MCP — not plain Chromium MCP
• StarNet — MIT local-first pixel-art desktop station for real agent crews
• tRPC-Agent-Go — Apache-2.0 Go production agent framework — GraphAgent, MCP, A2A
• FrontMCP — Apache-2.0 TypeScript-first MCP server framework (decorators, DI, OAuth)
• Desktop Commander MCP — MIT MCP for terminal, files, and processes on your desktop host
• Mobile MCP — Apache-2.0 native iOS+Android a11y-tree MCP (sim/emu/real)
• MetaMCP — MIT self-host MCP aggregator + middleware + inspector (one endpoint)
• Qwen Code — Apache-2.0 multi-surface coding agent (Qwen lineage)
• Coding Tools MCP — Apache-2.0 model-neutral 18-tool coding runtime over MCP
• Gemini Notebook MCP CLI — MIT CLI+MCP for Gemini Notebook (NotebookLM) — uv/PyPI free path
• DBX — Apache-2.0 agent-facing multi-engine DB client — MCP + CLI + Docker
• Agent Toolkit for AWS — Apache-2.0 Agents/MCP toolkit — plugins, skills, AWS CLI MCP proxy
• GitMCP — Apache remote MCP — any GitHub repo as live docs for agents
• Framelink Figma MCP — MIT Figma-layout MCP for coding agents — npm figma-developer-mcp
• Mobile Build MCP — MIT Sentry MCP+CLI for iOS/macOS agent builds — npm mobilebuildmcp
• Langflow — MIT visual agent/workflow builder — every flow as API + MCP tool
• Agentgateway — Apache AI-native proxy — MCP & A2A security, obs, governance
• MCP Scanner (Cisco) — Apache MCP security scanner — YARA, LLM, Cisco AI Defense
• Reverify — MIT claim-verify loop for agents — MCP + deterministic tools
• HOL Guard — Apache local antivirus for agents — MCP, skills, shell, packages
• Apify MCP Server — MIT Apify Store MCP — agents scrape via thousands of Actors
• InsForge — Apache agent-native backend with MCP self-host
• OpenKnowledge — GPL-3.0 local markdown IDE + LLM wiki — MCP/skills for agent editing
• geo-score — MIT free AIV readiness score + MCP — cite-ability without a paywall
• mcp-audit-tool — MIT static audit of MCP client configs — poisoning, rugs, secrets
• growth.engineer — MIT agent-readable GTM catalog — tools, functions, workflows via MCP
• awwwards-mcp — MIT design-inspiration MCP — Awwwards search, DNA, screenshots
• Qanat — MIT MCP for quant factor processing and backtesting
• OpenChatX — MIT local ChatGPT agent runtime — tools, MCP aggregate, skills
• text-to-cad — MIT agent CAD plugin — STEP/STL/3MF, DFM checks, drawings via local MCP
• MCP for Blender — MIT Blender MCP — prompt-driven 3D scenes from any agent client
• Radar — Apache-2.0 Kubernetes web UI — topology, Helm, GitOps, audit, built-in MCP
• Kubescape — Apache-2.0 CNCF Kubernetes security — manifest and cluster scans, image CVEs, auto-fix, admission policies, MCP server
• Docker Agent — Apache-2.0 YAML-defined agents with MCP toolsets — runs as `docker agent`
• REA — MIT MCP server for agent-driven reverse engineering — binaries, Electron apps, .NET, websites
• Windows-MCP — MIT MCP server that lets an agent drive the Windows desktop — apps, UI, input, shell
• ToolHive — Apache-2.0 MCP server runner + gateway — each server in its own container
• Grafana MCP server — Apache-2.0 MCP server from Grafana Labs for dashboards, datasources, alerts and incidents
• Higress — Apache-2.0 AI and API gateway on Envoy and Istio, with Wasm plugins, model proxying and MCP hosting
• TrueForge — MIT open-source agent harness — MCP, skills, subagents, approvals, local SQLite or hosted Postgres
• MCP Toolbox for Databases — Apache-2.0 Google MCP server for databases
• AWS MCP Servers — Apache-2.0 AWS Labs MCP servers for AWS services
• Microsoft MCP — MIT official Microsoft MCP servers, led by Azure
• Firecrawl MCP Server — MIT official MCP server for Firecrawl scraping
• Supabase MCP Server — Apache-2.0 official MCP server for Supabase
• MongoDB MCP Server — Apache-2.0 official MCP server for MongoDB
• Stripe AI — MIT official Stripe toolkit and MCP server for agents
• Exa MCP Server — MIT official MCP server for Exa web search
• Obsidian Mind — MIT Obsidian vault as persistent agent memory
• AgentMesh — Apache-2.0 private network for AI agents, from Google
• Hex-Rays IDA MCP — Official MIT MCP server for the IDA disassembler
• Appwrite — BSD-3-Clause backend: auth, database, storage, functions
• ByteStash — GPL-3.0 self-hosted code snippet manager with MCP
• MCP Python SDK — MIT official Python SDK for MCP servers and clients
• Activepieces — MIT open-source Zapier alternative with MCP pieces
• Flint — MIT chart language and MCP server that turns short specs into polished charts
• ripwire — Apache-2.0 offline code map and quality checks for coding agents (CLI + MCP)
• MCP for Unity — MIT MCP server that lets AI assistants drive the Unity Editor
• ToolJet — AGPL-3.0 low-code builder for internal tools on your own data
• kubernetes-mcp-server — Apache-2.0 MCP server that talks to the Kubernetes API directly
• Terraform MCP Server — HashiCorp's official MPL-2.0 MCP server for Terraform Registry and HCP Terraform
• Docker MCP Gateway — MIT docker mcp CLI plugin that runs MCP servers in isolated containers
• Sentry MCP — Sentry's official MCP server for issues, traces and Seer; FSL source-available
• mcp-agent — Apache-2.0 MCP-as-runtime + durable Temporal workflows (LastMile)
• Agent-MCP — AGPL MCP-native multi-agent + shared knowledge graph
• Chrome MCP Server — MIT Chrome extension MCP server for your own browser
• Context7 — MIT MCP client for live library docs; free anon / free key
• Smithery — Freemium MCP registry, gateway, and hosting marketplace
• Antigravity CLI — Google terminal agent (agy) — Gemini CLI consumer successor
• Scry — Hosted freemium MCP + SQL over public-record corpora