REA is an open-source MCP server that wraps native-binary, JS/Electron, .NET, and APK reverse-engineering backends behind one interface. Install: npx rea-agents setup. It solves the problem of wanting to build a feature you've only seen in someone else's app, with no source code to learn from.
appwrite/appwrite (57,624★) pivots from a developer backend-as-a-service to a cloud that exposes an MCP interface agents can call directly. DeusData/codebase-memory-mcp (46,293★) replaces embedding-based RAG with an AST-plus-knowledge-graph MCP server that indexes an entire codebase into a single queryable binary. Yeachan-Heo/oh-my-claudecode (39,768★) bolts the multi-agent team orchestration layer Claude Code doesn't ship natively. sgl-project/sglang (36,965★) is trending because agentic workloads — not single-turn chat — are now what inference frameworks optimize for first. Agno v3.1.2 adds Conversation Compaction to fold old turns into a summary, plus a new Codex External Agent adapter.
**mattpocock/skills** (283,680★) is the agent-skills collection its author actually uses day to day — now listed in Claude Code's official plugin marketplace, installable with one command in Codex, Copilot, and Gemini CLI too. **morluto/rea** (61,585★) wires an agent into Ghidra, Hopper, and IDA to reverse-engineer native binaries, JS/Electron apps, and websites. **cathrynlavery/diagram-design** (48,496★) is an agent skill for drawing diagrams — 44 types, each exported as a single self-styled HTML+SVG file. **anthropics/knowledge-work-plugins** (28,593★) is Anthropic's own open-sourced set of 11 role-specific plugins, bundling Slack/Notion/HubSpot connectors into Claude Cowork. **mksglu/context-mode** (26,062★) is an MCP server built to stop tool output from flooding an agent's context window. pydantic-ai v2.55.0 raises its minimum Python version to 3.11 and adds a `Conversation` object; Claude Code v2.1.296 fixes how plain-language hooks are evaluated.
AI Agent Gateway is Tuskira's open-source gateway between agents and MCP tool servers / LLM providers. Install: docker compose -f deploy/docker-compose.yml up --build -d. It solves the problem of credentials pasted into every agent's MCP config, with tool access that was otherwise all-or-nothing.
postgres2mcp is a self-hosted MCP server that wraps a Postgres connection with a governance layer. Install: curl -fsSL https://raw.githubusercontent.com/Railcode-HQ/postgres2mcp/main/install.sh | bash. It solves the problem of multiple agents or third parties needing the same database, where the only options used to be full read-only access or none at all.
Brickwise (roblox-logics-mcp) is an open-source MCP server that packages common Roblox development pitfalls into a sourced knowledge base your AI assistant can query. Install with `git clone` + `npm install && npm run build`, then wire it up with `claude mcp add`. It fixes AI assistants writing broken code from outdated Roblox APIs — like calling `PhysicsService` when the engine moved that to `WorldRoot` months ago.
shipstores is an MCP server that lets an agent like Claude operate App Store Connect and Google Play Console directly. Install: claude mcp add shipstores -- uvx shipstores. It solves the problem where the app is built, but publishing still takes about 40 manual steps, half of which have no public API.
gitlab-mcp-server is an open-source MCP server that covers 868 GitLab API actions (1,094 on Ultimate) through two dynamic tools, find and execute. Install: npx -y @jmrp.io/gitlab-mcp-server or docker run ghcr.io/jmrplens/gitlab-mcp-server:latest. It solves the problem where mapping every API action to its own MCP tool floods the client's context window before the model does any actual work.
dots (1.9k★, live for under a day) uses a patched Firefox engine so web agents don't get flagged as bots. context-mode (24.5k★, #1 on Hacker News the day it shipped) cuts tool output by 98% to stretch context budgets. openrig (3k★) runs Claude Code and Codex as one coordinated team. dbx (23.2k★) turns a database client into an MCP server with a built-in AI assistant. universal-modder lets Claude Code mod PC games directly. Claude Code v2.1.286 is versioned as a patch but actually fixes a batch of credential-leak bugs, and Haystack shipped v3.3.0-rc1 fixing an anyio CVE and changing BM25 retrieval behavior.
skillmem is an MCP server that gives Claude Code, Codex, and other coding agents a local skill memory that can both strengthen and forget. Install: pip install 'skillmem[semantic]', then skillmem init --claude-code. It solves the problem of existing memory tools storing everything indiscriminately and trusting whatever the agent itself claims was useful — skillmem only raises a skill's strength on evidence from outside the agent's own judgment (a passing test, an accepted diff), and any memory you haven't approved gets flagged as data, not instructions.
Titration is a self-hosted MCP server that lets a coding agent edit a prompt and grade the change against a frozen baseline, using judges from other AI vendors, until the problem is actually gone or the tool concludes the prompt was never the issue. Install: docker compose up -d for Postgres, then npm install && npm run setup. It solves the problem of an agent editing a prompt, scoring its own work, and quietly gaming that score.
Paperclip (86.7k★) manages a fleet of agents like employees — org chart, budgets, heartbeat scheduling. Block's open-sourced Buzz (34.8k★) goes the other way, putting humans and agents in the same Nostr-signed workspace. Z.ai open-sourced ZCode, joining the club of vendors building their own coding-agent shell. mobile-mcp extends MCP tooling to real iOS/Android devices. Notable releases: Pydantic AI v2.51.0 adds OpenAI GPT-Live support and tightens realtime tool_choice / model-id matching; Claude Code v2.1.283 adds a `deniedModels` lockdown setting and `/doctor prompt-audit`.
ismail is an MCP server that exposes a DAW in text: an agent writes notes, effect chains, and automation, then reads back structured text describing the mix. Install: clone the repo, then pip install -e . It solves the problem of agents doing audio work with no ears, forced to guess at parameters.
terminal-mcp is an MCP server that exposes a real terminal (a PTY behind full xterm.js emulation) so an agent can operate interactive CLIs and full-screen TUI programs the way a human does. Install: npm install -g @ellery/terminal-mcp. It solves the problem of ordinary shell-exec tools getting stuck or misreading output whenever a command hits an interactive prompt or a full-screen redraw.
petit-poucet is a Rust-built MCP server that stores AI coding agents' long-term memory as Markdown notes in a git repository. Install: claude plugin marketplace add https://github.com/areguig/petit-poucet, then claude plugin install petit-poucet@petit-poucet. It solves the problem of every agent tool keeping its own separate memory, so switching tools or starting a new session means repeating yourself.
Microsoft open-sourced agent-governance-toolkit (6,303 stars), enforcing tool-call policy in code instead of prompts, citing an ICLR 2025 paper showing 100% adaptive jailbreak success on GPT-4o/Claude 3/Llama-3; ai-memory grew from 2,900 to 7,575 stars in a month, giving 20+ coding agent CLIs a shared long-term memory; anthropics/financial-services ships the same finance-vertical agents as both a Cowork plugin and a Managed Agents API template, at 35,728 stars; the official MCP Inspector reached v2.7.0, unifying its web/cli/tui clients into one binary; coder/coder folds AI coding agents into Terraform-defined, controlled dev environments with no API keys in the workspace.
openclaw/openclaw hit 390k stars in ten months, but today's v2026.9.5 release also left some users with vanished sessions that took 8 hours to recover after upgrading; volcengine/OpenViking benchmarks directly against OpenClaw, Hermes, and Claude Code, showing an attached context database lifts long-conversation memory accuracy from 24-57% to 80-83%; trycua/cua shipped CUA-S1-FORMS, a 2.8MB model that takes small decisions like filling in form fields away from the general-purpose model; pydantic-ai v2.46.0 bakes the same 'hand narrow tasks to a specialist decision model' idea into its core API
SessionRelay is a local-first memory layer for AI coding sessions, exposed through an MCP server so an agent can query full conversation history across tools and sessions. Install: npx @ewanjasper/sessionrelay init. It solves the problem of decisions and context vanishing the moment you switch AI tools, start a new session, or hand a project to someone else.
affaan-m/ECC rode agent-harness optimization to 260k+ stars in eight months, though a growth rate that steep deserves skepticism; cactus-compute/needle trades chat ability for tool-calling precision in an 8-29MB model; Graphify-Labs/graphify builds knowledge graphs with local AST parsing instead of a vector store; tinyhumansai/openhuman makes 'getting to know the user' the core of its agent memory; IvanMurzak/Godot-MCP lets agents drive the Godot editor directly; Claude Code v2.1.277 adds AGENTS.md support
codebase-memory-mcp is an MCP server that indexes a codebase into a knowledge graph, exposing 15 tools for indexing, structured querying, and change-impact analysis. Install: a one-line curl script, then restart your agent and say 'index this project.' It fixes the token blowup and missing cross-file call tracking that come from making an agent grep and read files one by one.
edgar-mcp is an MCP server for SEC EDGAR with six tools covering company lookup, filing lists, section extraction, financial facts, and full-text search. Install: pip install -e . then set EDGAR_MCP_USER_AGENT — no API key needed. It addresses the problem of agents being forced to swallow an entire 10-K when the context window gets eaten by tables of contents and legal boilerplate.
DearAgent is an open-source email inbox API that runs on Cloudflare Workers, with a built-in MCP server so an agent can create an inbox, wait for a verification code, search, and reply. Install: git clone then npm run setup for an interactive deploy, or just try the live demo at dearagent.sh. It solves the problem of agents that need a real inbox for signup flows without wanting to depend on a third-party hosted service.
mcp-bi is zavora-ai's open-source Business Intelligence MCP Server. Set BI_BACKEND to switch between Superset, Metabase, Power BI, Tableau, Looker, Qlik, and QuickSight while an agent calls the same tool set across all of them. Install: cargo run (ships with a seeded fixture, no setup needed). It addresses the problem of agents only seeing a dashboard screenshot and guessing at trends.
BankMCP is a self-hosted, read-only MCP server that wraps 2,700+ European banks behind Enable Banking's PSD2 API, so an AI assistant can directly answer things like "has the Acme invoice been paid" or "what did I spend on subscriptions." Install: `claude mcp add bankmcp -- npx -y bankmcp`. It addresses the problem that letting an AI assistant help with money has never had a safe, read-only channel into real account data.
jmeter-mcp-server is a stdio MCP server that lets an agent build, edit, and run JMeter load tests through typed tool calls and read back aggregated reports. Install: `claude mcp add jmeter -e JMETER_HOME=... -- npx -y jmeter-mcp-server`. It addresses the problem that an LLM hand-writing `.jmx` XML can produce output that is structurally valid but semantically wrong, with no error raised.
okf-agent-memory implements the Google OKF v0.2 spec as a Git-native agent memory system, with a zero-dependency Go CLI and an embedded MCP server. Install: `brew install okf-memory/tap/okf`. It addresses the problem of architectural decisions either living inside an opaque vector database, or piling up in a CLAUDE.md file that only ever grows.
cc-readback is a local, read-only MCP server that lets Claude Desktop read, search, and summarize your Claude Code session history stored under ~/.claude, automatically redacting common credentials like AWS, GitHub, and OpenAI keys. Install: `npm install -g cc-readback && cc-readback install all`. It addresses the problem of wanting Claude Desktop to recap what yesterday's Claude Code sessions did and where they got stuck, without having to scroll back through terminal history yourself.
KRU is a local-first MCP credential manager that lets agents like Codex, Claude Code, and Cursor log in, connect, and call APIs using saved passwords, API keys, SSH keys, and TOTP codes — without the plaintext secret coming back into the conversation. Install: download the portable build from GitHub Releases. It addresses the problem of an agent stalling on a login page or SSH password prompt, leaving you to either take over manually or paste the secret straight into the chat.
github/spec-kit turned one and shipped 1.0.0, with its maintainer stressing that adaptability now matters more than stability. stablyai/orca lets you run a whole fleet of coding agents in parallel worktrees and gained 812 stars in a single day. KeygraphHQ/shannon shipped 3.0, an AI agent that runs real penetration tests and outputs SARIF reports straight into CI/CD. On the browser side, ChromeDevTools/chrome-devtools-mcp opens Chrome's official MCP server up to any agent. On the framework side, Pydantic AI v2.38.0 changes how one-off capabilities get merged (a breaking change), and Claude Code v2.1.259 fixes a long-standing bug where concurrent sessions silently clobbered each other's settings.
reverify is an open-source MCP server plus CLI that puts a pure-Python deterministic reverse-engineering toolkit (disassembly, CPU emulation, pattern scanning) in the judge's seat for whatever an AI claims about a binary. Install: `pip install reverify`. It addresses the problem of an agent stating guesses about a binary as if they were fact, with no way for you to tell which is which.
upnote-mcp is an open-source MCP server that lets Claude read and create UpNote notes. Install: clone the repo, then `npm install`. It solves the problem of a note app with no official automation API where you also don't want your notes touching the cloud.
mcp-spend-guard is an open-source stdio proxy for MCP that fills the gap MCP has no built-in rate limiting for: spend caps, rate limits, a circuit breaker, and a kill switch. Install: `pipx install .`. It addresses the fact that a looping or prompt-injected agent can hammer a paid tool with nothing to stop it.
read4all is an MCP server that converts PDFs, Office files, images, and web documents into Markdown plus images, preferring MinerU's cloud engine and falling back to local libraries when no API key is set. Install: uvx read4all. It solves the problem that an agent reading an attachment either loses all layout structure or needs a hand-built conversion pipeline.
Sovereign MCP (sovereign-observer-mcp) is a locally-run MCP server that scans and auto-fixes Terraform security misconfigurations while an agent is writing them. Install: claude mcp add sovereign -- uvx sovereign-observer. It solves the problem that AI-generated IaC is insecure by default, and the mistake usually isn't caught until a PR or production.
Google's own ChromeDevTools/chrome-devtools-mcp (50k stars) lets coding agents drive a real Chrome instance for performance profiling and debugging; abhigyanpatwari/GitNexus replaces 'guessing at code by reading it' with a pure browser-side knowledge graph; mksglu/context-mode targets coding agents' context-window waste; google/skills is Google's own official Agent Skills package library; livekit/agents keeps shipping actively for voice agents. On the framework side, pydantic-ai v2.36.0 adds `@durable_operation`, opening a pluggable slot for third-party durable-execution engines.
proton-safe-mcp is a FastMCP server that lets an agent read, search, and prepare draft attachments via Proton Mail Bridge. Install: git clone + uv sync + uv run proton-safe-mcp setup. It solves the problem that 'letting an agent read email is itself a prompt-injection attack surface' — there is no send tool in the codebase, and a draft only becomes real once it's manually approved from a local terminal.
localagents is an MCP server that lets Claude Code delegate subtasks to a local llama.cpp / vLLM model. Install: git clone + uv tool install -e . + claude mcp add. It solves the compatibility problem where a local model can't plug directly into Claude Code's conversation protocol — KV-cache placement and context window size both trip it up.
deepseek-ai/deepseek-harness (dsh) uses a Cordis plugin architecture to make models, tools, sandboxes, and memory all swappable components, hitting nearly 200k stars a week after its developer preview launch; PrimeIntellect-ai/prime-agent runs long-lived research coding tasks on a Recursive Language Model architecture, surviving terminal disconnects via a persistent IPython session; liqiwa/mcp-radar automates this very kind of digest by scanning GitHub daily for newly ranked MCP servers. On the framework side, Mastra 1.61.0 adds a crash-resilient background task queue, and ComposioHQ/composio 0.17.0 extends SSRF protection to tool-execution downloads and S3 uploads.
pgbot is a read-only Postgres health-check CLI; run `pgbot mcp` and it becomes an MCP server agents can call directly. Install: `curl -fsSL https://pgbot.dev/install | sh`. It solves the problem of piecing together root causes across multiple monitoring dashboards when a database slows down, while an agent only ever sees fragments of that picture.
mcp-guardrail is an open-source MCP security proxy: policy gateway + audit log + secret scanner in one. Install: clone then `pip install -e .`. It addresses the fact that most MCP server setups lack tool-level permission controls and often have secrets hard-coded in config files.
duty1g/x64dbg-mcp-server wraps a reverse engineering debugger as MCP tools, hitting 563 stars in two days; Cripacx/mediagen bakes EU AI Act content marking into an image generation MCP server; QwenLM/qwen-code v0.22.0 publishes full SWE-bench Verified test trajectories with a 77.08% pass rate; open-gitagent/gitagent rewrites its core engine in Rust with agent state living entirely inside a git repo. On the framework side, GitHub's official MCP Server v1.10.0 is a security spring-cleaning — a typo in `--tools` now crashes the server on startup.
localmem-mcp is a local-first MCP memory server that stores and searches agent memories using SQLite + on-device embedding (fastembed), with zero LLM calls on the recall path. Install: `uvx localmem-mcp` (zero-install) or `pip install localmem-mcp`. Solves the problem of existing memory tools (Mem0, Zep) requiring cloud LLM calls, API keys, and extra infrastructure (vector DB / graph DB) to function.
CopilotKit/OpenBot ships an AG-UI-based 'AI coworker' framework where each agent gets its own computer, hitting 2,289 stars in a week; Bruno's official MCP server (usebruno/bruno-mcp) arrives two months after the community version (Ostico/bruno-mcp-studio); the browser-use team spins off a macOS Harness project that gives LLMs six accessibility primitives to control a Mac directly; opencode, now under Anomaly, has ~199K stars — surpassing Anthropic's Claude Code at ~142K. On the framework side, the MCP TypeScript SDK v2 splits the monolith into 8 sub-packages and follows the protocol's stateless redesign, dropping the session handshake entirely.
mcp-anything is a meta-MCP server that indexes 75,000 MCP servers from public registries to your local machine, letting agents discover and call any server through 5 fixed meta-tools (search/describe/list_tools/call_tool/sync). Install: `npx mcp-anything sync && npx mcp-anything serve`. Solves the problem of too many MCP servers to manually configure, each one burning context tokens.
HKUDS/nanobot rode its v0.3.0 'The Agency Release' to 47K stars in 7 months as a self-hostable personal agent runtime; genspark-ai/genoffice hit 3,400 stars in 3 weeks with an open-source AI office suite for native file formats; NVIDIA published labs-OO-Agents (NOOA), collapsing agent state into a single Python class; repo-context-mcp is an MCP server that helps coding agents understand repos without stuffing the entire codebase into the prompt. Framework-wise, Mastra 1.60.0 adds durable execution and Cloudflare Sandbox; pydantic-ai v2.33.0 has a breaking change from the anthropic SDK's switch to httpx2.
comfy-mcp is Comfy's official local MCP server that wraps the full comfy-cli feature set into 39 MCP tools. Install: pip install comfy-mcp "comfy-cli>=1.14.0". It solves the problem where agents trying to run image/video generation workflows for you still need you to manually open a terminal, type commands, and verify that the right nodes and models are installed.
headroom compresses tool output, logs, and RAG chunks locally before sending them to the LLM, reaching 66K stars in 7 months. agentmemory gives Claude Code, Cursor, Codex CLI and a dozen other coding agents a shared cross-session memory store, hitting 27K stars in half a year. Andrew Ng's team releases OpenWorker, a desktop agent targeting knowledge workers beyond engineers. NVIDIA's labs-OO-Agents reimagines agent abstractions with object-oriented design. Mastra 1.59.0 renames CostGuardProcessor to TokenCostControl (breaking). browser-use 0.13.8 adds first-party OpenClaw skill support.
forge adds a reliability middleware layer for tool-calling on self-hosted LLMs, proxying opencode/aider/Claude Code with zero code changes; repo-context-mcp provides token-budgeted repo context packaging via MCP, integrated into PR CI within 5 days of launch; DeepSeek's official harness dsh spawned at least 5 independent community desktop wrappers in one week, totaling nearly 1,500 stars; Microsoft Research's browser agent framework Webwright uses Skill Factory to distill solved tasks into replayable scripts without model calls, boosting reuse accuracy by 15 percentage points on WebArena; Mastra 1.59.0 renames CostGuardProcessor to TokenCostControl (breaking); Pydantic AI v2.30.0 patches a DNS rebinding security vulnerability in its local web chat interface.
mcp-memory is an MCP server that persists Agent long-term memory as Markdown files conforming to Google's OKF v0.2 spec, with SQLite FTS5 full-text search indexing. Install: git clone then run `python3 setup.py`. It solves the problem of Agents losing all context on every new session, and memory formats being incompatible across different Agent tools.
pbx-mcp is an MCP server that wraps Asterisk (AMI) and FreeSWITCH (ESL) behind one set of MCP tools. Install: npx -y pbx-mcp. It solves the problem of memorizing two command sets when operating two PBX systems, and prevents Agents from accidentally running state-changing commands.
Claude Code connects to external tools via MCP (Model Context Protocol), with manual configuration split across three scopes: team-shared .mcp.json, personal local/user entries in ~/.claude.json, and enterprise managed config — not settings.json. This post covers claude mcp add/login flows, the transport landscape (SSE is deprecated), and tool search lazy loading.