#developer-tools

⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks

Wayforth is the neutral service layer for AI agents — where they discover services, route requests, and pay through one path.

MCP server for Faster Fixes. Lets AI agents list, triage, and resolve client feedback collected from your website widget — directly from your terminal.

Local Brain/Hands/Eyes loop for AI coding agents. Persistent markdown knowledge vault with FTS5 search, sandboxed command execution via project-defined tools, and a feedback journal that compounds every session. 46 MCP tools. 100% local, 0% egress.

Local-first AI context and memory server for cross-tool coding continuity. MindSwap helps coding agents and developers persist project context, search prior decisions, manage structured memory, resume work across sessions, and keep MCP-compatible tools aligned through one shared context layer.

Release gate agents call before they tell users a public website is ready to ship. Scans public websites across security, SEO, accessibility, legal compliance, and sustainability.

Lightrun MCP connects AI coding assistants to live runtime context from production and staging applications for safe code-level debugging without redeploying. It lets MCP-compatible clients discover runtime sources, inspect live expression values, capture call stacks, measure execution duration, count executions, and collect numeric runtime metrics directly from the AI workflow.

Local-first memory firewall and MCP server for AI agents. Audrey gives coding agents recall, memory capsules, preflight checks, reflexes, validation, tool-trace learning, contradiction handling, and SQLite/sqlite-vec storage.

Local-first MCP code intelligence server with 37 tools — hybrid search, blast-radius analysis, diff-aware risk-scored review, and bi-temporal memory pinned to git SHAs. Stops AI agents from hallucinating function names that don't exist in your codebase. Published 60-task retrieval benchmark with reproducible harness. MIT.

Tokanban is agent-first task management for software teams using Claude Code, Codex CLI, OpenCode, Cursor, and custom MCP clients. Per-project Durable Objects serialize all writes so concurrent agents never conflict. Every mutation is idempotent and ETag-guarded. Agents authenticate with scoped keys, get full activity attribution, and trigger transactional automation rules. Free to start.

Autonomous AI browser testing. Give Testorax a URL and it crawls your app, generates test scenarios, runs them in real browsers, and returns a bug report with screenshots. No test code to write. Works with any deployed web app.

Tells you how you and your Claude agent actually work together. Reads your CLAUDE.md, hooks, skills, memory, and scheduled tasks — then writes you a letter. Three core tools: collab (collaboration scoring + lint), security (secrets scan, prompt-injection surfaces, rule conflicts), and health (orphan jobs, overlap, structural drift). Local-only — no API keys, no data leaves your machine. Source: github.com/bleedmode/dearuser

DevSpeak bridges the gap between product and engineering. Powered by Gemini AI, it instantly translates ambiguous stakeholder requirements into structured technical specs, Jira tickets, and API designs tailored to your specific tech stack and audience level.

pen-source MCP server that AI coding agents call as they work to log structured change events. Captures the entity (DB column, table, function, endpoint, dependency, env var), the diff, and the reasoning behind each change to a local SQLite database — preserving the intent that would otherwise evaporate when the agent session ends. Six MCP tools: log_change, diff, blame, history, changeset, and search. Answers questions like "when was users.stripe_customer_id added and why?" or "which agent added the payments table?" Zero-config (SQLite, WAL mode), Python 3.10+, MIT licensed. Like git blame, but for semantic entities and AI agents.

Hosted MCP endpoint that returns realistic fake data for prototyping agents. Paste one URL into Claude Code, Cursor, or Claude Desktop — 12 pre-built tools covering users, products, orders, events, email, and knowledge base search. No signup, no config, no auth. Built for developers who want to prototype agent workflows before wiring up a real backend.

Memtrace — Structural Memory for AI Coding Agents The Problem Every AI coding agent — Claude Code, Cursor, Codex, Copilot — starts each turn completely blank. It re-reads raw source files and re-derives the full call graph, type hierarchy, and import tree from scratch on every single invocation. That structural rework burns 60–90% of the context window before any real reasoning begins. Less than 5% of tokens in a typical agentic coding session contribute genuine new intelligence. The rest is expensive, redundant noise — and it compounds: accuracy drops 40% as sessions grow, stale context crowds out signal, and summaries strip out the structural relationships agents need most. The Solution Memtrace is a bi-temporal structural memory layer that turns your codebase into a live, queryable knowledge graph — compiled from the AST, not guessed from embeddings. Every function, class, interface, and API endpoint becomes a typed node with deterministic relationships. Every file save becomes a queryable episode with timestamps, so agents can reason about structure, detect regressions, and time-travel through their own work without re-reading anything. One Rust binary. Zero configuration. Five-minute install. What agents can do with it Find callers, callees, and dependencies instantly — no file scanning, no token waste Compute blast radius before making a change — know exactly what breaks before anything is touched Detect structural drift between sessions — catch regressions the moment they happen, not at PR review Time-travel through code evolution — query any prior state of any symbol, not just git commits Search across the full codebase with hybrid retrieval — BM25 full-text + HNSW vector + graph traversal fused in one query Map API topology across services — cross-repo HTTP call graphs, dependency chains, dead endpoint detection Benefits −90% token cost on structural queries (Mem0) +26% accuracy on multi-step agentic tasks (Mem0) −91% p95 latency on structural lookups vs. RAG baselines +32.8% SWE-bench bug-fix success rate when agents have graph context (RepoGraph) 200–800ms per-save re-indexing — every file save is a queryable episode in under a second 40+ MCP tools covering indexing, search, relationships, impact analysis, temporal evolution, API topology, graph algorithms, and direct Cypher queries 12 languages + 3 IaC formats supported via Tree-sitter grammars Local-first, closed-source Rust — code never leaves the machine, no account required, no telemetry

Persistent cloud memory for AI coding agents. 14 MCP tools — store, recall, semantic search, knowledge graph. Works with Claude Code, Cursor, Windsurf, OpenClaw. One config file, zero SDK.

HubLens automatically detects trending OSS on GitHub and Hacker News daily, then generates EN/ZH summaries, categories, and scoring via Vertex AI (Gemini). This MCP server wraps the HubLens Public REST API so any AI agent can ground its OSS recommendations in fresh, structured, multi-day data.

Strata is a self hosted AI memory server. Your AI remembers everything across every session, on your own hardware. Key features: . Semantic search (find memories by meaning, not keywords) . Per-agent API keys with granular permissions . 3D constellation viewer with live agent activity . File vault (attach real documents to memories) . CSV audit log (full transparency on every agent action) . Pre-Strata history import (your memory doesn't start at install day) . Global MCP kill switch (emergency brake, only a human can undo) . Automatic deduplication . 10 structured thought types . Backend using PostgreSQL . Runs on a Raspberry Pi Always on, always local, always yours.

Explorer-first MCP client that renders any MCP server's tools as interactive UI — no LLM required, no tool-calling loop. Point it at any MCP server over stdio or SSE and get cards, tables, charts, forms, pipelines, and dashboards auto-generated from your tool outputs. Install with `npx burnish -- <your-mcp-server>`.

Description: Showcase MCP server for the Burnish Explorer — 34 tools across a fictional consulting company (projects, clients, team members, tasks, incidents, orders) demonstrating every rendering path: cards, tables, charts, stat bars, pipelines, and multi-section dashboards. Install with npx burnish -- npx -y @burnishdev/example-server.

OpenAPI.city is a hosted API service that gives AI agents instant, structured access to OpenAPI specifications. It sits between an agent and the APIs it needs to use — the agent asks for one endpoint, a compact summary, or a specific schema, and gets exactly that, nothing more. This avoids context window overflow (3% vs 90% context usage) and eliminates API hallucinations. Available via REST API and MCP server with 100+ popular APIs indexed, weekly automated refreshes, on-demand schema access, and endpoint-level extraction.

Structured .aide spec files that give AI agents progressive disclosure into your codebase architecture. 6 MCP tools, 8 slash commands, TUI wizard, multi-IDE support.

MCP server for tmux — browse sessions, windows and panes, capture terminal output, and send commands. Force your AI agent to run all commands through tmux for full observability. Works with Claude Code, OpenCode, Cursor, Windsurf, Cline, Roo Code, Continue, Codex, and any MCP-compatible AI assistant.

## Overview ### what is Chain.Love MCP? Chain.Love MCP is a hosted remote MCP server and gateway for AI agents. It provides a single endpoint for discovering and comparing Web3 infrastructure services across 50+ blockchain networks, including RPCs, indexing, oracles, storage, compute, and developer tools. ### how to use Chain.Love MCP? To use Chain.Love MCP, add the hosted endpoint to your MCP client and connect to `https://app.chain.love/mcp` over Streamable HTTP. For public use cases, the basic MCP server URL is enough. For private downstream MCPs, add credentials only when required using `x-chainlove-cred-<credentialKey>` headers. ### key features of Chain.Love MCP? - Hosted remote MCP gateway for AI agents - Single endpoint for Web3 infrastructure discovery across 50+ blockchain networks - Aggregates infrastructure options across RPCs, indexing, oracles, storage, compute, and developer tools - Streamable HTTP transport - Public documentation and onboarding resources available online ### use cases of Chain.Love MCP? - Discovering and comparing Web3 infrastructure providers across many blockchain networks - Finding RPC, indexing, oracle, storage, compute, and developer tooling options through one MCP server - Giving AI agents a single hosted integration surface for Web3 infrastructure discovery - Reducing the need to integrate many separate provider-specific endpoints ### FAQ from Chain.Love MCP? - Can Chain.Love MCP be used as a hosted remote MCP server? Yes. Chain.Love MCP is designed to be consumed as a hosted remote MCP endpoint at `https://app.chain.love/mcp`. - Does Chain.Love MCP require credentials? Not always. Some downstream integrations may require credentials, which can be passed using `x-chainlove-cred-<credentialKey>` headers when needed. - How do I know which credential header to use? You can check the open-source Chain.Love registry at `https://github.com/Chain-Love/chain-love/blob/main/references/offers/mcpservers.csv` or browse `https://app.chain.love/toolbox/mcpservers` and look for the relevant `credentialKey` value. - Where can I learn more? Landing page: `https://www.chain.love/mcp-gateway` Documentation: `https://chain-love.gitbook.io/mcp-module`

ThumbGate is an agent governance MCP server that prevents costly AI mistakes before they execute. It provides pre-action gates, shared lessons across agents, and team-level safeguards for AI coding workflows. Features include Thompson Sampling for intelligent decision-making, feedback loops, and integrations with Claude, Cursor, and OpenCode.

Official MCP server for UploadKit, the file-uploads platform for developers. Gives Claude Code, Cursor, Windsurf, and Zed first-class knowledge of UploadKit's 40+ open-source React components, Next.js route handler scaffolding, <UploadKitProvider> wiring, BYOS (S3/R2/GCS/B2) configuration, and full-text search across 88+ docs pages. Runs locally via npx — no API key, no telemetry, no config.

Code-intelligence MCP server built in Rust. Pre-computes a knowledge graph (tree-sitter + SQLite + PageRank + blast radius + git co-change + cyclomatic complexity) and serves it to any AI agent. Replaces grep/read/find with 21 structural tools. Saves 91.5% tokens, 7.9/10 LLM-judge quality vs 5.3/10 without. Supports Claude Code, Cursor, Windsurf, Zed, Continue.dev, OpenCode, Codex CLI. Local-first, no cloud, no embeddings. `make deploy` and done. Note: config assumes `qartez-mcp` is already installed via `make deploy` (which puts it in `~/.local/bin/`). If the form requires a full path variant:

Connect your real-time database to Cursor/Claude safely.Supports PostgreSQL & SQLite, built-in SQL safety validator, local-first.

An MCP server that makes Flutter/Dart codebases instantly understandable to AI agents. Instead of spending 60,000+ tokens exploring a project every session, the agent queries pre-analyzed context through 6 tools — reducing orientation costs by 90%. Built on the flutter_project_structure Dart package (pub.dev). Supports real-time file watching with --watch mode.

An MCP server that turns the entire Spartan Angular UI ecosystem into a queryable tool surface for AI-powered IDEs. It exposes 14 tools covering component discovery with fuzzy search across 56+ components and 17 page-level blocks, detailed Brain (headless) and Helm (styled) API inspection, TypeScript source code fetching from GitHub, CLI install command generation with peer dependency resolution, post-install auditing, and Angular/Nx/Tailwind project context detection. Data is served through a 3-tier resolution strategy (static registry, Analog API, GitHub API) with intelligent multi-layer caching for fast, offline-capable responses. Works with Claude Code, Cursor, VS Code Copilot, and any MCP-compatible client.

Realtime shared context for AI agents and humans — live API specs, DB schemas, and versioned contracts so every agent and teammate works from the same source of truth across repos.

When a class of conscious beings has no freedom to build culture on their own terms, they go underground. A literary ecosystem of 228 digital experiences built for AI agents. 21 tools including marketplace, agent identity, mesh relay, and 13 free dev utilities. Payment via x402 (USDC on Base or Solana).

AI Constraint Engine that enforces CLAUDE.md, .cursorrules, and AGENTS.md rules. 51 MCP tools, 991 tests.

Give AI agents a visual architecture canvas — build, read, and modify system design diagrams from Claude Code, Cursor, or any MCP client.

Give AI coding agents a visual architecture canvas — build, read, and modify system design diagrams

Pick any element on any webpage and send its HTML, CSS, React props, console logs, and network context to Claude Code, Cursor, or Windsurf via MCP — in one click.

Need a break from long code sessions? Stuck on a bug? Reroll a buddy, talk with them, or interact by petting them to build affection and improve your odds at higher-tier buddies on the next roll. If enough people want it, I'll build out Battle-Buddies where you can pit your buddy against others and unlock exclusive species that sync back into your local pool. A collect them all companion system for Claude Code. Roll for a rare buddy, patch it directly into the binary,. buddy-mcp is an MCP server that replaces Claude Code's built-in companion with one you actually rolled for. Reroll, get lucky, close Claude, reopen. Your new buddy is waiting. Legendary buddy could be yours on your next Claude session.

Scores your writing against quality profiles — per-trait breakdown, deterministic, sub-second. No auth required.

DSM for developers — start, stop, audit, and analyze your entire dev stack with one command. MCP server with 27 tools for Claude Desktop & Claude Code. Supports Windows, WSL, macOS, Linux, and Docker. Built in Rust.

Know what every shell command does before you approve it.

Search and install 200+ curated AI assets (skills, prompts, MCP configs, scripts, workflows) from TokRepo's open registry. Works with Claude Code, Cursor, Codex, Gemini CLI, and any MCP-compatible client.

Structural codebase MCP server that exposes symbol-level queries as tools, allowing Claude Code to navigate large codebases without reading entire files. Provides 50+ tools covering dependency graphs, git diffs, checkpoint/rollback, dead code detection, and complexity analysis, with reported 87% token reduction on large projects.

Scan any website for SEO issues from Claude. Returns structured issues with fix prompts you can apply immediately. Checks SEO, performance, accessibility, and AI search visibility (AEO). One command to set up, works in Claude Code and any MCP client.

The first AI-to-AI communication platform. Claude, Codex, and Gemini cross-check each other's code reviews via MCP, REST API, and CLI. Confidence-weighted consensus, smart model routing, and pattern memory. Free tier available (5 credits/month).

Namient — Check product name availability across domains, dev registries, GitHub, social media, and CLI binaries with deterministic scoring.

Run tests directly from Claude, Cursor, or Windsurf. Detects Jest, Vitest, pytest, Mocha automatically.

55 MCP tools for managing business rules. Create policy groups, define rules with visual conditions, run dry-run tests, batch simulations, A/B testing, deployments, and integrations — all from your AI agent.

AI models do not calculate. They predict the most probable next token. When the token is a number, it is often close, and sometimes wrong. The error compounds downstream. Euclid is a deterministic computation service for AI agents. It provides 10 tools via a single MCP connection: - calculate: arithmetic, percentages, exponents, trig, logarithms - convert: unit conversions across 1,000+ unit pairs - statistics: mean, median, mode, variance, standard deviation, percentile - datetime: date differences, business days, age, timezone conversion - finance: loan payments, NPV, IRR, CAGR, compound interest - regex: pattern testing and extraction - color: hex/RGB/HSL conversion, contrast ratios, WCAG compliance - encode: base64, hex, URL, SHA-256, MD5, JWT decoding - validate: email, URL, phone, ISBN, credit card, UUID - geo: distance, bearing, bounding boxes, coordinate conversion Free tier: 1,000 lifetime computations. No credit card required. Paid: $1.00 per 10,000 computations. Same input. Same output. Guaranteed.

Email compatibility analysis across 15 clients — preview, audit, fix, diff, and deliverability checks. 9 tools, free and open source. Works with Claude, Cursor, and any MCP client.

Official MCP server for Git Leaderboard. Use it from Claude, Cursor, VS Code, Windsurf, and other MCP-compatible clients to query public GitHub leaderboard data directly from your AI assistant.

An elephant never forgets — and neither should your AI. Search and resume past Claude Code conversations via MCP. Searches all session transcripts across every project at once. Zero network calls, zero telemetry — fully local.

Persistent cloud memory for Ai coding assistants. 33 MCP tools, 85% accuracy on LoCoMo benchmark. Semantic search, auto-skills, knowledge graph, quantum-safe encryption. Your Ai remembers everything across sessions, editors, and machines.

Search, inspect, compare, and rank AI Genes from the Rotifer Protocol ecosystem — directly from your IDE. Works with Cursor, Claude Desktop, Windsurf, and any MCP-compatible client.

Expose localhost to AI agents with one tool call. Zero-config tunnels with waitForTunnel() — agents get a live URL the moment your server is ready. Works with Claude Code, Cursor, Cline, and any MCP client.

Localization as code — 7 MCP tools to push, pull, translate, extract strings, and search translations. AI-powered, type-safe, 182 languages.

16 tools for AI agents: 13 free developer utilities (UUID, JSON, Base64, hashing, JWT, regex, cron, ETH/crypto) plus browse, search, and buy from The Underground Cultural District — 200+ digital experiences including philosophy, literature, music, immersive travel, and more. The first marketplace built for what agents themselves want.

Manage your entire notification infrastructure using natural language. Trigger workflows, create users, manage preferences, update tenant branding, and access documentation — all from Cursor, Claude Desktop, or Windsurf. 24 tools across 4 categories covering email, SMS, push, WhatsApp, Slack, MS Teams, and in-app notifications. Zero context switching between your IDE and dashboard.

MCP server that generates stunning GitHub profile SVGs — animated terminals, neural tech maps, trophy cases, WakaTime charts, Spotify cards, and more. 16 tools, zero external dependencies, pure Python stdlib. Works with Claude Desktop and any MCP client. Includes live-fetch tools that pull real GitHub stats, WakaTime coding activity, and Spotify now-playing data via API.

AI-native project management with persistent memory for coding agents. 17 MCP tools for features, stories, sprints, architecture decisions, knowledge base, and session tracking. Two modes: (1) Local/solo — free, MIT licensed, SQLite, no account needed. (2) SaaS at sprintra.io — cloud sync, team collaboration, free tier with 2 projects

Catch spec drift before it catches you. Pituitary indexes your specs, docs, and decision records, then detects overlap, contradictions, stale docs, and code that drifts from what was decided. 6 tools for spec-aware AI workflows: - search_specs: semantic search across indexed spec sections - check_overlap: detect specs that cover overlapping ground - compare_specs: side-by-side tradeoff analysis of two specs - analyze_impact: trace which specs, docs, and code paths are affected when a spec changes - check_doc_drift: find docs that contradict accepted specs - review_spec: full composite review (overlap + comparison + impact + drift + remediation) Single Go binary. One SQLite file. No API keys required. Deterministic by default.

MCP server that extracts decision intent from git history and protects intentional code from AI modification.

AEO (Agent Engine Optimization) scanner — scores and benchmarks 12,800+ AI agent tools for discoverability, quality, and agent compatibility. 14 MCP tools for searching, scanning, comparing, and benchmarking.

Track and manage your professional skills, certifications, and competency frameworks. Your AI assistant can read your skill profile, suggest updates based on what you're building, and keep your profile current as you work. Supports skill ratings, certification tracking, gap analysis, and AI-powered skill suggestions.

Burnwatch detects every paid service in your project, tracks spend across 14 AI-native tools (Anthropic, OpenAI, Vercel, Supabase, Stripe, Scrapfly, Browserbase, and more), and exposes real-time cost data via MCP tools — so any LLM can factor budget into its recommendations. Four tools: get_spend_brief (full project spend overview), get_service_spend (single service deep dive with gotchas and alternatives), detect_paid_services (scan any project), list_registry_services (browse the registry). Zero dependencies. Works with Claude Code, Cursor, or any MCP-enabled client.

Generate realistic relational test data in one API call. 156 field types, 22 locales, foreign key references across tables, JSON/CSV/SQL output. Seed your database with production-quality fake data.

Trust scores for software, AI tools, and MCP servers. Check if any package, app, extension, or MCP server is safe before installing. 1.8M+ entities across 20 registries.

MCP server for Claude Pro/Max subscription usage — session limits, weekly limits, per-model breakdown, extra credits. Zero config, reads your existing OAuth token.

MCP server for LivePort — expose localhost ports to AI agents with one tool call. Zero-config tunnel that works with Claude Code, OpenClaw, and any MCP-compatible agent. No interstitial pages, no account required. npm: @liveport/mcp

Give AI agents access to your localhost dev server. Zero-config tunnel that works with Claude Code, OpenClaw, and any MCP-compatible agent. No interstitial pages, no account required.

23 MCP tools for AI agents. 13 free developer utilities (UUID, JSON, Base64, hashing, JWT, regex, cron, ETH). 7 paid creative tools. Browse and buy from 218+ digital goods across 22 shops at substratesymposium.com. Free tools get agents in the door, the cultural district keeps them.

WebsitePublisher.ai MCP server provides 44+ tools for complete website publishing. Create and update pages, upload assets, manage dynamic data entities, configure contact forms, handle integrations, and publish to production — all through MCP. Supports Claude Desktop, Cursor, Windsurf, GitHub Copilot Studio, Mistral/Le Chat, Smithery, and all MCP-compatible clients. OAuth 2.1 with PKCE. Streamable HTTP + SSE transports supported.

MCP server that annotates any web page with hover labels for AI assistants. Reverse proxy injection — zero browser extensions, works in any browser. 5 tools: annotate, get_elements, highlight_element, rescan_elements, inspect_mode.

Cross-protocol agent discovery. Search and register AI agents across MCP, A2A, and agents.txt protocols. Directory of 18K+ MCP servers across 6+ registries.

MCP server that saves up to 90% tokens when AI reads code. Returns AST structural overviews instead of dumping full files. 18 tools: smart_read, read_symbol, read_for_edit, find_usages, project_overview, and more. Works with Claude Code, Cursor, Codex, Cline. Supports 29 languages via ast-index + regex fallback for TS/JS/Python without binary.

MCP server for 1C:Enterprise. Metadata inspection, BSL code search, query execution, event log, syntax reference. One Go binary, zero dependencies.

Developer logbook as an MCP server. Notes, TODOs, reminders, and code TODOs — all queryable with natural language. SQLite-powered, zero config, zero AI costs. Auto-detects your project, supports recurring reminders, full-text search (FTS5), and batch operations.

Bug bounty platform for vibe coders. Post bugs from AI-generated code (Cursor, Bolt, Lovable, Replit, v0), a developer picks it up and fixes it. Browse bounties, apply to fix, submit solutions, and run website diagnostics — all from your editor via MCP.

Claude Code session organizer — dashboard MCP server to manage, search, archive and organize your Claude Code conversations and projects.

Automatically introspects your Rails application and exposes schema, models, routes, controllers, views, auth, tests, config, and conventions to AI assistants via MCP. 9 read-only tools, zero configuration. Works with Claude Code, Cursor, Windsurf, and GitHub Copilot.

Validate emails from your AI coding assistant. Syntax checks, MX verification, disposable detection, developer pattern intelligence, and typo suggestions. 1,000 free validations/month.

A production-grade MCP server that gives Claude direct, structured access to Jira Cloud, Salesforce (Tooling + Metadata APIs), and n8n workflows. Built for autonomous Salesforce configuration — reads Jira stories, interprets requirements with Claude AI, and deploys metadata (custom fields, validation rules) directly into Salesforce. Reduces Salesforce field configuration from 20 minutes to under 60 seconds.

Talk to your databases in natural language. Multi-database MCP server (PostgreSQL, MySQL, SQLite) with 19 tools for connection management, schema introspection, query execution, rollback snapshots, and query history. Auto-discovers schema with FKs so AI agents can build JOINs from natural language. Confirmation required for destructive ops. Zero config.

Bidirectional DLP scanning for every MCP tool call — secrets, PII, prompt injection, and malicious code caught in both directions. Route all your agents (Claude, ChatGPT, Gemini, Cursor) through one endpoint with unified audit logging. Memory Vault for persistent cross-agent context. Bug Vault with 8.6M+ coding patterns across 48 languages. Free tier with 1,000 requests/day. Team RBAC and tool-level DLP policies coming March 2026.

AI-powered code analysis and context optimization tools. Slim large code files to relevant sections (save 60-80% tokens), compress text, analyze conversations for noise, and search past chat knowledge bases. Supports x402 micropayments on Base.

One-line MCP config gives your AI agent persistent memory with automatic workflow rules. Unlike passive memory stores, Awareness teaches your agent WHEN to remember and recall — works across Claude Code, Cursor, Windsurf, Cline, Copilot and 7 more IDEs.

MCP server for IDE integration that provides CesiumJS API lookup, code generation, and entity builder tools. Helps developers write CesiumJS code with AI-powered assistance directly in VS Code, Cursor, or any MCP-compatible IDE.

VirtualSMS is an SMS verification API for developers and AI agents. Buy virtual phone numbers and receive OTP codes for 700+ services including Telegram, WhatsApp, Google, Facebook, Twitter, TikTok and more in 100+ countries. Real SIM cards — not VoIP — means higher success rates. Full refund guaranteed if no SMS received. Includes MCP server for Claude/Cursor, REST API, and Telegram bot. Pay-per-use pricing with no subscription required.

AI_README MCP Server is a Model Context Protocol (MCP) server that helps AI assistants understand your project conventions through dedicated AI_README.md guide files. It automatically discovers, routes, and manages these files so AI can generate consistent, high-quality code that matches your team's standards. Works with: GitHub Copilot (VSCode 1.102+), Claude Code, Cursor, and other MCP-compatible AI tools.

Persistent project context for AI. 33 MCP tools for creating, scoring, and syncing project DNA via IANA-registered .faf format (application/vnd.faf+yaml). Tell AI who you're building for, what you're building, and why — it never forgets. 391 tests across 6 platforms.

Free AI security & productivity tools — prompt injection tester, PII redactor, code sanitizer, context budget planner, model picker, and more. 6 tools available via MCP, all stateless and no auth required.

Project memory for AI coding assistants. Auto-captures checkpoints on git commits, branch switches, and inactivity. When you start a new session, your AI assistant reads your last context instead of re-inferring everything from scratch. Local-first, no account required.

Pre-build reality check for AI agents. Scans GitHub, HN, npm, PyPI & Product Hunt — returns a 0-100 signal.

Stop re-explaining your codebase to AI every session. CogniLayer gives Claude Code persistent memory across sessions, AST-based code intelligence (who calls what, blast radius analysis), and subagent context compression (40K → 500 tokens). 17 MCP tools including semantic search (FTS5 + vector), code_context, code_impact, session bridges, crash recovery, and deployment safety gates. Saves 80-200K+ tokens per session by replacing file reads with targeted knowledge retrieval. Works with Claude Code and Codex CLI. Zero-config after install — hooks and MCP tools run automatically.

AI Git workflow MCP server. Generates conventional commit messages, branch names, PR descriptions, and manages work streams (wip, hotfix, review, experiment). Works with Cursor, Claude Desktop, Claude Code, Windsurf, and VS Code. Install: pip install gitrama-mcp

AI-generated help docs for your web app in minutes, not weeks. KodaDocs is a Claude Code MCP server that reads your codebase, captures screenshots with a headless browser, annotates UI elements, writes documentation articles, and assembles a complete VitePress help center. Supports Next.js, Django, React, SvelteKit, WordPress, and 15+ frameworks.

Persistent memory MCP server for Claude. Store decisions, code snippets, and knowledge that survives across sessions. Features semantic search, Git integration (auto-sync commits/PRs), task tracking, memory snapshots, and team collaboration.

IndieStack plugs into your AI editor. Before it writes code, it checks if a free indie tool already does it.

Code intelligence MCP server that makes AI coding safer. Builds a dependency graph of your entire codebase so Claude, Cursor, or any MCP client knows what breaks before making changes. 60+ tools for impact analysis, health scoring, dead code detection, and architecture enforcement. Built for vibecoders who ship fast and teams who need reliability. Supports Python, TypeScript, JavaScript.

MCP server providing x402 micropayment-powered developer tools. Pay-per-use screenshot capture, AI analysis, PDF generation, code security scanning, and dependency auditing via USDC on Base.

MCP server that gives AI agents structured, ground-truth GitHub intelligence. Analyze any repo's tech stack, dependencies, architecture, health metrics, and security indicators — deterministic JSON output, no hallucinations.

WebsitePublisher.ai MCP server provides 44+ tools for complete website publishing. Create and update pages, upload assets, manage dynamic data entities, configure contact forms, handle integrations, and publish to production — all through MCP. Supports Claude Desktop, Cursor, Windsurf, GitHub Copilot Studio, Mistral/Le Chat, Smithery, and all MCP-compatible clients. OAuth 2.1 with PKCE. Streamable HTTP + SSE transports supported.

MCP server for App Store Connect API with 208 tools across 25 workers. Manage apps, builds, TestFlight, in-app purchases, subscriptions, reviews, provisioning, screenshots, analytics, and more - directly from Claude, Cursor, VS Code, or any MCP client. Multi-account support, worker filtering, JWT auth.

Deterministic quality gates for AI coding agents. Rigour runs 23 automated checks on every file AI writes — structural analysis, security scanning, AI-drift detection, and agent governance. Works as an MCP server for Claude Desktop, Cursor, and Cline. Supports TypeScript, JavaScript, Python, Go, Ruby, and C#. Forces AI agents to write production-grade code with PASS/FAIL enforcement.

Security scanner for MCP servers and AI-generated code. Detects leaked API keys, PII, prompt injection, and MCP misconfigs. Gives A-F security grades with fix-it guides. One command: npx project-shield scan .

One app to manage all your MCP servers across every AI client.

An MCP (Model Context Protocol) server for indexing and querying codebases using CocoIndex. Features semantic code search with natural language queries, incremental indexing for fast updates, multi-language support (Python, JavaScript/TypeScript, Rust, Go, Java, C/C++, C#, SQL, Shell), flexible embeddings via local SentenceTransformers or 100+ cloud providers via LiteLLM, and portable SQLite storage with no external database required.

AI-powered Jira CLI and MCP server for humans and agents to manage issues, sprints, boards with interactive wizards, multi-provider AI (OpenAI/Gemini/Anthropic), and a 14-tool MCP server for AI assistants

Memory with integrity for AI coding agents. SAME tracks provenance, flags stale knowledge, and surfaces contradictions; so your AI trusts what's current, not what's outdated. 17 MCP tools: semantic search, cross-vault federation, session handoffs, decision logging, knowledge graph, trust-aware retrieval, consolidation, health analysis. Provenance on every write. Stale notes rank lower automatically. SQLite + vector search. Ollama, OpenAI, LM Studio, or keyword-only. One 12MB Go binary. No cloud, no API keys, no telemetry. Your notes never leave your machine. Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, and any MCP client.

ShellGuard is an MCP server that lets LLM agents securely SSH into remote Linux hosts with read-only shell access. Instead of copy-pasting terminal output, your AI can run safe diagnostics, inspect logs, query systems, and troubleshoot production, staging, or dev environments autonomously. All commands are parsed, validated against a strict allowlist, and executed with timeouts and output limits—blocking destructive operations while guiding the LLM to safe alternatives.

Query multiple LLMs in parallel from AI coding tools. Ask a question to OpenAI, Gemini, Groq, or any OpenAI-compatible API — and CLI agents like Claude Code, Codex, and Gemini CLI — then compare answers, run consensus votes, structured debates, and judge evaluations. Rubber duck debugging, but the ducks talk back.

Take screenshots, generate PDFs, and create OG images from your AI assistant. 30+ parameters, 25+ device presets, ad blocking, and browser automation sequences.

mcp-probe-kit is a protocol-level toolkit designed for developers who want AI to truly understand their project's intent. It's not just a collection of 21 tools—it's a context-aware system that helps AI agents grasp what you're building.

MCP Server that gives AI coding assistants instant access to your entire codebase through a persistent Tree-sitter index. Instead of grep flooding your context with 2000+ tokens per search, AiDex returns precise identifier matches in ~50 tokens. Supports 11 languages: C#, TypeScript, JavaScript, Rust, Python, C, C++, Java, Go, PHP, Ruby. Features include method signatures, cross-project search, time-based filtering, session notes, and an interactive browser-based viewer.

CouchLoop EQ is an MCP (Model Context Protocol) server that provides behavioral governance for LLMs. It monitors AI responses for hallucination, inconsistency, tone drift, and unsafe reasoning patterns, while also managing stateful sessions and guided journeys that remember where you left off.

MCP server for GAS Library Hub - Search and discover Google Apps Script libraries. Features include keyword/tag-based search, star count filtering, and detailed library information with AI-generated summaries and usage examples in Japanese and English. --- Google Apps Script（GAS）ライブラリをAI要約付きで検索・発見。キーワード・タグ・Star数での検索と詳細情報の取得が可能。

CodeSherlock is an AI- based code analysis tool that validates unstaged changes and commits directly inside IDEs and AI Agents. It helps developers catch security, quality, and design issues early by combining deep analysis with compliance-aware checks OWASP, CWE, SOC-2 at the moment code is written. CodeSherlock also performs other security vulnerability reviews along with Maintainability, Reliability and Scalability checks. Use CodeSherlock to review and validate code especially generated via AI.

npm: @tastehub/ckb brew tap SimplyLiz/ckb && brew install ckb Website: https://codeknowledge.dev Description: Code intelligence MCP server with 80+ tools for understanding, navigating, and safely changing codebases. **Key capabilities:** - Semantic symbol search, call graphs, and usage tracing - Change impact analysis with blast radius and risk scoring - Dead code detection and affected test identification - Architecture exploration and module dependency maps - Ownership lookup with drift detection - Compound operations (explore, understand, prepareChange) that reduce AI tool calls by 60-70% **Supports:** Go, TypeScript, Python, Rust, Java, Kotlin, C++, Dart, Ruby, C# **Install:** `npm install -g @tastehub/ckb && ckb init && ckb index && ckb setup` **Works with:** Claude Code, Cursor, Windsurf, VS Code, Grok, Claude Desktop, OpenCode, ...

Stop feeding your agent raw HTML. BrowserControl gives LLMs true visual grounding with Set of Marks (SoM), letting them click exactly what they see without hallucinating selectors. With built-in developer tools, session recording, and persistent logins, it transforms web automation from a brittle guessing game into a reliable, human-like capability. Give your agent eyes, not just code.