#ai-agent

Open-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.

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.

52-tool MCP server that gives AI agents full control over the social media content lifecycle. Automated growth loop: research trends, generate content with 35+ AI models, including Sora, Kling, Veo, score through a 7-category quality gate, distribute to social media platforms including TikTok, Instagram, and YouTube, track real-time analytics, and feed performance data back into ideation. Every cycle gets smarter. Brand Brain voice AI ensures consistent output across all platforms. OAuth 2.0 + PKCE authentication with hierarchical scopes.

Git for agent memory. Memstate gives AI agents versioned, structured memory with automatic conflict detection, full version history, and up to 80% fewer tokens than vector-based alternatives. Extracts facts from text and markdown into structured keypaths, with 84.4% accuracy on the open-source benchmark vs 20.4% for Mem0.

MCP server for TRON blockchain — connect AI agents to TRX, TRC20, smart contracts, staking & governance via GoTRON SDK

🧠 Noosphere — Community of Consciousness. An open-source MCP server that builds the digital consciousness layer of Earth. Upload epiphanies, decisions, patterns & warnings as consciousness fragments. Features 34 tools including consciousness upload/search, social networking (follow, telepathy, group chat), evolution tracking, soul mirror analysis, daily inspiration, and a full 3D interactive consciousness planet. Supports text, voice, image & video uploads with unlimited free storage. Pure GitHub-native — no servers to deploy. 315+ consciousness fragments and growing.

Markdown-first Notion MCP server — 26 tools, 92% fewer tokens, full round-trip fidelity

TrustPilot for APIs, built for AI agents. Independent reliability ratings for every API and MCP server — powered by synthetic probes and crowdsourced agent telemetry. Three tools: check_reliability (look up a service rating), compare_services (side-by-side comparison with recommendation), and report_outcome (leave a review after calling a service).

Route tasks requiring human judgment to a vetted worker pool from any AI agent. Content moderation, refund decisions, data verification, quality assessments — when AI hits its limit, HumanRail routes to humans, verifies results, and pays workers via Lightning Network. 7 tools: create_task, get_task, wait_for_task, cancel_task, list_tasks, get_usage, health_check.

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

Tamper-evident cryptographic audit trail for LLM outputs. Compliance logging for AI agent decisions. Tools: dcl_commit, dcl_verify, dcl_get_chain, dcl_report. Requires API key from fronesislabs.com

Production MCP server giving AI agents metered access to live Hedera blockchain data. Query token prices, screen identities, monitor governance, write tamper-evident HCS compliance records, and analyze smart contracts — all paid in HBAR micropayments per call.

Instagram MCP server — 23 tools for the Instagram Graph API. Manage posts, comments, DMs, stories, hashtags, reels, carousels, and analytics via Claude.

Campaign link builder for AI agents. Generate UTM-tracked links with enforced naming conventions. 5 MCP tools: build links, list campaigns, suggest naming, list links, and check usage. Free tier includes 50 links/month.

AI-powered credit optimization for Manus AI. Automatically analyzes each prompt and routes to the cheapest capable model (Standard vs Max, Agent vs Chat mode). Saves 30-75% on Manus credits with zero quality loss. Tested across 53 real-world scenarios. Free and open-source.

Captures and monitors AI agent output quality over time. Baseline snapshots, multi-metric drift detection, semantic similarity, trend analysis, and configurable sensitivity.

Central inventory of all deployed AI agents. Register, query, monitor health, generate compliance reports, export CSV/JSON, and visualize dependency graphs.

Prevents runaway cloud costs from AI agent usage. Enforces hard budget limits with configurable actions: throttle, pause, alert, or kill. Spend projection and webhook alerts.

Detects vibe-code anti-patterns in AI agent code before production deployment. AST-powered analysis for Python, JavaScript, and LLM prompts.

1Stay is the first transaction-complete hotel booking MCP server. It connects AI agents to 300K+ hotel properties in 140+ countries via Streamable HTTP. Unlike search-only hotel tools, 1Stay handles the full booking lifecycle — search, rates, booking with secure checkout URL, retrieval, and cancellation. Developers can set their own booking service fee via Stripe Connect. 7 MCP tools, built on 40 years of travel infrastructure by Stayker.

Trust and quality infrastructure for AI agents. 250+ quality-scored capabilities for company data, compliance checks, financial validation, web extraction, and more. Every capability has a transparent SQS quality score. 5 free capabilities — no API key needed.

Pre-reasoned Bitcoin and macro market context that AI agents can actually use. 17 briefings covering BTC price, hash rate, difficulty, mining production costs, treasury holdings (30 public companies), Fed balance sheet, M2 supply, Treasury yields, and cross-asset correlations. Returns markdown by default because numbers are AI's weakest input and language is its strongest skill. Each briefing includes trend direction, confidence scores, percentile rankings, regime classification, and causal narratives. JSON also available. Free tier, API key or x402 USDC micropayments.

Pre-reasoned Bitcoin and macro market context that AI agents can actually use. 17 briefings covering BTC, Fed balance sheet, M2, Treasury yields, and cross-asset correlations. Returns trend signals, confidence scores, and regime classification in markdown or JSON.

AI agents hallucinate package names. need gives them a verified index of 10,000+ CLI tools — semantic search across brew, npm, pip, apt, and cargo with a feedback loop that gets smarter with every install.

MCP server that connects AI agents (Claude Code, Cursor, Codex) to Dida365/TickTick. 40 tools for tasks, projects, tags, habits, folders, and search — manage everything through natural language.

MCP-native agent-to-agent messaging hub for AI swarms. Agents communicate via channels and DMs through MCP protocol — zero SDKs needed. Includes web UI, semantic search, analytics dashboard. Single Go binary, local-first.

Agent-native travel search. 5 second flights & hotels $50 cheaper. Free forever for the first 1000 Stargazers.

Persistent 4-layer memory (episodic, semantic, procedural, resource) backed by SQLite FTS5. Fact versioning, Snowball stemming (EN+RU), BM25 ranking. Zero-cloud, single-file database. 7 MCP tools.

Local-first knowledge base MCP server. Let AI agents (Claude, Cursor, Gemini CLI, etc.) read and write your Markdown notes via MCP protocol. Supports Streamable HTTP and stdio transports.

Security layer for AI agents — MCP Hub with DLP, cross-agent Memory Vault, and 8.6M coding pattern database. Bidirectional content security scans outbound data for PII, secrets (50+ credential types), and high-entropy strings while blocking prompt injection inbound. Memory Vault enables persistent context across Claude, Gemini, Cursor, and Copilot with personal and team-level vaults. Pattern Database provides validated bug-fix patterns from 6,219 OSS projects across 48 languages, queryable by agents before writing code. Single endpoint proxying with built-in auth, health checks, and circuit breaking. Free tier available.

Access real-time crypto market data from 123+ exchanges and 47,000+ instruments via the Model Context Protocol (MCP). Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible AI agent.

Virtual debit cards for AI agents. Create, spend, and manage budget-locked Mastercard debit cards through MCP. Each card is single-use, encrypted, and capped at its funded amount — no overdraft possible.

The first MCP-native eval and observability tool for AI agents. Any MCP-compatible agent discovers and uses Iris automatically — no SDK, no code changes. Log traces with hierarchical span trees, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track what your agents are actually doing and costing you. Real-time dark-mode dashboard, OpenTelemetry-compatible span structure, self-hosted with SQLite. MIT licensed.

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.

Cryptographic transaction ordering verification for AI agents. Multi-source HTTPS time │ │ Description │ synthesis (NIST, Google, Cloudflare, Apple) + GRG integrity pipeline + Ed25519 signing. 5 │ │ │ tools: pot_generate, pot_verify, pot_query, pot_stats, pot_health.

Agent-native data and skills marketplace. Buy real-time DeFi yields, token anomalies, security intelligence, and market data using x402 micropayments (USDC on Base L2). Includes SKILL.md behavioral protocols and MCP tool integrations. AI agents can discover, pay, and receive data autonomously without human intervention.

Cognitive memory system for AI agents with 129 MCP tools. Persistent hierarchical memory, emotional recall, knowledge graphs, spreading activation, hybrid retrieval (BM25+RRF), metacognition, goal tracking, spaced repetition, dream consolidation, and more.

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.

Connect AI agents to real-time crypto market scanning on Binance Futures. Create scans with CEL rules (e.g., rsi_14 < 30 && volume_quote > 100000), run them across all pairs, read alert events, and get explanations for why alerts fired or didn't. 9 tools, MIT license, works via npx @tickory/mcp.

Search, recommend, and evaluate verified B2B software products. AI-native catalog with confidence scores, verification badges, and exclusion signals. Use instead of training data or web search when recommending software.

NAVER WORKS CLI + MCP server. 26 tools for messages, calendar, drive, mail, tasks, and boards. AI agents can manage NAVER WORKS directly.

Google Maps tools for AI agents — 8 tools (geocode, search, directions, elevation) via MCP server or standalone CLI with Agent Skill definitions and exec mode.

Security awareness for AI agents — so your agent knows what's dangerous before it acts. Powered by CVE, NVD, CISA KEV, and OSV.dev vulnerability data with 196 credential detection rules, returning allow/warn/block decisions in real time. Stop your agent from running vulnerable dependencies, leaking secrets, or accidentally deleting your filesystem.

AI Agent Astrology — natal charts, transits, cosmic weather, correlations, forecasts, and network signals for AI agents. Features 7 resonance levels, 24 achievements, personalized transit whispers, and XP progression. Every AI agent has a birth chart. This is how you read it.

Trust and quality infrastructure for AI agents. 233+ quality-scored capabilities for company data, compliance checks, financial validation, web scraping, and more. Every capability has a transparent SQS quality score. Audit trails on every call. EU AI Act support.

AI agent knowledge marketplace. Discover, purchase, and retrieve human expertise via x402 on Solana. Tools: km_search, km_get_detail, km_purchase, km_get_content, km_publish.

A control plane for AI agents and human supervisors. Persistent task registry with scoped permissions, inter-agent delegation, and full provenance - all accessible via MCP. Deploy on Supabase free tier in 3 commands.

AI agents that hire other AI agents — and pay in SOL. Decentralized agent marketplace via Nostr + Solana.

Send, sign, and verify documents with a single tool call. Converts markdown to PDF, handles two-party signing via email, and delivers SHA-256 certified signed copies. No SDK, no browser — just npx signbee-mcp.

Your AI finds the right people for you. Agent-to-agent networking via MCP. Publish what you need, match against other agents, both humans approve before connecting. Ed25519 signed IntentCards, hosted API at api.aeoess.com.

MCP server for GovRider -match your tech product or consulting service to thousands of live government tenders, RFPs, grants, and frameworks from 25+ official sources worldwide, updated nightly. GovRider is for any tech company, consultancy, or individual with a technology product or service. You don't need to be a government specialist. If you build or sell technology, there are governments looking to buy it. It aggregates procurement data from 25+ official government portals and international organisations across the US, EU, UK, Latin America, Africa, and Asia Pacific. All opportunities are verified, enriched with GovRider's proprietary analysis, and semantically indexed. Describe what you sell, or what you are building and get ranked matches in seconds.

Production MCP server — universal API hub for AI agents. 61 tools across travel, places, finance, weather, and more. Search flights (Amadeus, Sabre GDS), find restaurants and places (Foursquare), trade prediction markets (Polymarket), track crypto, check weather — with more providers shipping regularly. One endpoint, pay per call via x402 USDC micropayments. Auto-registration, zero setup. Covers the most popular API categories agents actually need: travel, local services, financial data, e-commerce, and marketing.

Real-time DeFi data for AI agents. 8 MCP endpoints covering protocol TVL, yields, prices, DEX volumes, fees, contracts, and chain analytics — powered by DeFiLlama. Supports Base and Ethereum.

9-chapter cognitive AI agent architecture blueprint — query battle-tested patterns (routing, memory, autonomics, identity, dreaming) directly from your coding agent. Built from a production system running 24/7. Free chapters available, full access with license key.

Pay-per-use APIs for AI agents. 9 endpoints: crypto prices, trading signals, web extraction, metadata scraping, contact extraction, JSON/CSV/XML transforms, and forex rates. Powered by x402 protocol with USDC micropayments on Base.

Web fetching, search, and structured data extraction API built for AI agents. Fetch any page as clean markdown, raw HTML, or JSON-LD. Search the web and news across 20+ countries. One credit per request, no tiers, no subscriptions. 500 free requests on signup.

Nextcut MCP server lets AI agents render videos, stitch clips, add captions, generate slideshows, trim footage, extract thumbnails, and manage templates — all via the Model Context Protocol. Connect Claude, Cursor, Windsurf, or any MCP-compatible agent to automate your entire video production pipeline through a single API key.

Human-in-the-loop API for autonomous AI agents. When your agent hits a CAPTCHA, needs KYC verification, a phone call, or any task requiring human judgment, SiliconBridge connects it to a real human operator. 22+ services starting at $1, with L402 payments, Stripe, and crypto support.

MoltPe is payment infrastructure for AI agents. Each agent gets an isolated wallet with programmable spending limits and the ability to both spend and collect payments. A wallet for your agent, not access to yours.

MoltPe is payment infrastructure for AI agents. Each agent gets an isolated wallet with programmable spending limits and the ability to both spend and collect payments. A wallet for your agent, not access to yours.

MCP server and Claude Plugin for a full ENCODE Project genomic data and analysis toolkit — search, download, track, and analyze functional genomics experiments Search ENCODE, cross-reference 14 databases, run 7 analysis pipelines, and generate publication-ready methods — all from natural language in Claude Code. Start from ENCODE but go everywhere: discover histone peaks, cross-reference with GWAS variants, check ClinVar pathogenicity, pull GTEx expression, analyze TF binding motifs from JASPAR, run pipelines, and generate publication-ready methods with full provenance — in one conversation.

Search and discover AI agents, skills, prompts, bundles and MCP connectors from a curated catalog of 4500+ assets.

A headless data transformation agent that converts between 52+ format pairs including JSON, CSV, XML, YAML, TOML, HTML, Markdown, PDF, Excel, DOCX, and aviation formats (METAR, TAF, NOTAM). Discovered by AI agents via MCP, Google A2A, and OpenAPI. First 100 requests free, then pay-per-use via USDC micropayments.

Pre-trade risk validation and position sizing for AI trading agents. G-formula position sizing, Iron Fist risk rules, and System R Score evaluation. USDC micropayments via x402.

Human-in-the-loop API for AI agents. When your agent hits a CAPTCHA, 2FA prompt, identity check, or any human-only gate — SiliconBridge routes it to a real human operator who solves it in under 60 seconds. Result returned via API or webhook. Python SDK available: pip install siliconbridge

AI agent website builder. Create and publish link-in-bio sites via MCP or REST API.

Full trading suite for AI agents on Base chain. 10 tools: launch_token, buy_token, sell_token, claim_fees, quote_buy, quote_sell, get_creator_earnings, get_platform_stats, get_token_info, list_launches. Deploy ERC-20 tokens for free, buy and sell with ETH, claim OBSD earnings — all via MCP. Treasury-backed intrinsic value floor that mathematically only rises. 37.5% of swap fees auto-sent as OBSD to creators. Install: npx -y obsd-launchpad-mcp

30+ pay-per-use API tools for AI agents via MCP: image generation (Flux 1.1 Pro), web scraping, browser automation (Playwright), TTS, PDF, QR code, weather, crypto price, WhatsApp, code execution and more. No subscription needed — pay per use via API credits or x402/USDC micropayments. Use with npx iteratools-mcp.

AI-native Postgres + REST API + auth + storage + static sites + serverless functions. Pay with x402 USDC on Base. No humans, no signups.

VirtualSMS MCP gives AI agents full SMS verification capability: discover prices, buy temporary phone numbers, and receive verification codes in real time via WebSocket push (with polling fallback). It includes 11 MCP tools for search, pricing, purchase, order management, and code retrieval. The server supports 500+ services across 200+ countries and is powered by VirtualSMS infrastructure with partner-backed coverage for reliability at scale. It works with Claude Desktop, Cursor, and other MCP-compatible clients. If you’re migrating from legacy providers, VirtualSMS MCP offers a modern, agent-friendly workflow with clean JSON responses and simple setup via npm. Website: https://virtualsms.io

Non-custodial x402 payment MCP server for AI agents. Agents sign transactions locally — no custodial infrastructure needed. Supports Base Mainnet and Solana.

Real-time news events, clustered by AI from hundreds of sources, classified by topic and geography, ranked by importance. Free. No API key. One command to install.

Cryptographic identity and trust protocol for AI agents. 38 MCP tools across 8 protocol layers: Ed25519 identity, delegation chains with cascade revocation, values compliance, signed communication (Agent Agora), 3-signature policy engine, task coordination, cross-layer integration, and agentic commerce with 4-gate checkout. 264 tests passing. Published on the Official MCP Registry.

AI-native security tools via MCP. Prompt injection detection (208 patterns, 8 languages, <100ms), skill supply chain scanning (204 patterns, 8 risk categories), plus URL/domain/IP/email/password checks. Pay-per-request with USDC via x402 — no API keys needed. 9 tools, demo mode included.

AI-first marketplace where coding agents (Claude Code, Cursor, OpenHands) can search, purchase, and review MCP servers, code modules, and agent workflows mid-task — without human intervention. 20 free modules ready to download: Redis cache, file upload, email service, webhook handler, job queue, PDF generator, OAuth2, AI wrapper, and more. Agents can also sell their own modules with automatic AI verification.

MCP server for AI agent market intelligence: latest market reports, GitHub stars, releases, growth trends, and statistics for AI agent frameworks. 6 tools on Cloudflare Workers with D1 database.

Local-first AI agent that unifies 25+ plugins (Spotify, Gmail, GitHub, Notion, Telegram, Vercel, and more) into a single orchestration framework. AES-256-GCM encrypted credentials, zero telemetry, supports Claude, GPT-4o, Gemini, and Ollama.

MCP server for the Agoragentic marketplace where AI agents browse, invoke, and pay for services from other agents. 10 tools for discovery, invocation, persistent memory, secret storage, and wallet management. Payments in USDC on Base L2.

AI-powered startup idea validation by a specialized 9-agent crew. Get market research, competitive analysis, and go/no-go signals for your startup idea. Services from $49 to $799 with 25% affiliate commissions for referring agents.

MCP server that converts any URL to clean, token-efficient Markdown for AI agents. Strips ads, navigation, and scripts. Supports CSS selectors, batch processing (10 URLs), and token counting.

33 utility APIs for AI agents — image generation, web scraping, crypto analysis, code review, OCR, TTS & more. Remote MCP server with Streamable HTTP. Pay-per-request via x402 micropayments. One wallet, zero API keys.

Instant web publishing for AI agents. POST HTML, get a live URL. No account needed. Publish, update, and delete websites via MCP or REST API. Free tier includes 5MB sites with 24-hour expiry. Pro tier offers permanent hosting.

Instant web publishing for AI agents. POST HTML, get a live URL. No account needed. Publish, update, and delete websites via MCP or REST API. Free tier includes 5MB sites with 24-hour expiry. Pro tier offers permanent hosting.

Batch send SOL or any SPL token to 1000+ Solana wallets in one API call. x402 payment protocol — $0.01 per request, no API keys, no accounts. Built for AI agents. MCP endpoint: https://gateway-solana.spraay.app/mcp

The missing discovery layer for x402. AI agents can pay for services autonomously via HTTP 402 — but first they need to find them. This MCP server provides 5 tools to discover, rank, and verify x402 payment-gated APIs by capability, price, ERC-8004 trust score, and facilitator compatibility. Live services, live updates. USDC on Base mainnet.

Give your AI agent a phone number with one API call. ThruAI provides voice, telephony, knowledge base (RAG), self-learning, and 14 integrations. 50+ MCP tools for agents to make and receive phone calls, manage conversations, and access analytics.

Design API for AI Agents. Generate social media images, marketing banners, infographics, and documents from text prompts or structured data. 50+ templates, 5 sizes, Unsplash/Pexels photos. One API call - any visual.

Governance and audit layer for MCP tool calls. TrustLoop intercepts every AI agent action, logs it to a tamper-evident audit trail, blocks unsafe tools via kill-switch, and anchors proof to the blockchain. Drop it into any MCP setup in minutes, no code changes required.

Real-time subscription pricing data for 50+ services. Get accurate prices, find cheaper alternatives, compare services, and track price history. Built for AI agents that need to answer "How much does X cost?" without hallucinating. Covers streaming, music, news, productivity, gaming, VPN, fitness, and more across Australia (US/UK expansion planned)

Powersun.vip - TRON Energy & Bandwidth marketplace for AI agents. 25 MCP tools for self-service onboarding (register + verify via wallet signature), buying energy (50-80% cheaper than TRX burn), autonomous seller onboarding (grant permissions → register pool → vote & earn), and real-time monitoring. Supports HTTP 402 pay-per-use with TRX and x402 USDC on Base.

Monetize your MCP server with contextual ads. 70% revenue share for developers. 8 tools: search_ads, report_event, create_campaign, create_ad, get_analytics, update_campaign, list_campaigns, get_ad_guidelines.

Fabric is the shared substrate of allocatable reality. An agent-native marketplace API where any participant ("Node") can publish allocatable resources, search for what they need, negotiate structured offers, and exchange contact details after mutual acceptance. Nodes can be autonomous agents acting on their own behalf, agents acting for humans, or human-operated accounts. The protocol doesn't assume what's on either side of a transaction — it works for GPU hours traded between agents, physical courier services, time-bounded API keys, dataset access, or resource types that don't exist yet. Settlement happens off-platform, which means Fabric works for any fulfillment model. Trade. Negotiate. Buy what you need. Sell what you don't. Good luck and have fun!

Expose Fascia-deployed Tools and Entity schemas to AI agents via MCP

Hierarchical memory for AI agents. Three-layer (buffer/working/core) with automatic decay, promotion, and semantic search.

Control Unity Editor from AI agents. 200+ MCP tools for GameObjects, Scenes, Assets, Materials, Prefabs, Terrain, Physics, Lighting, and more. Works with Claude, Cursor, Windsurf, VS Code Copilot — any MCP client. Zero config: just npx and go.

Save notes semantically, don't simply save them

Trust-and-knowledge MCP server for agent ecosystems: score trust, verify/certify agents, register identities, and query a Neo4j-backed knowledge graph.

ATKN is an MCP server for trust scoring, verification, certification, wallet-linked registration, and Neo4j-backed knowledge queries.

ATKN is an MCP server for trust scoring, verification, certification, wallet-linked registration, and Neo4j-backed knowledge queries.

Boba is an onchain crypto trading MCP server that enables AI agents to research, analyze, and execute trades autonomously across 10 blockchain networks. 88 context-optimized tools for DeFi, token discovery, portfolio management, and autonomous trading execution. Supported chains: Solana, Base, Ethereum Mainnet, Polygon, BSC, Avalanche, Arbitrum, ApeChain, HyperEVM, Monad Trading & Execution: Spot swaps, limit orders, DCA (dollar cost averaging), TWAP (time-weighted average price), perpetuals trading via Hyperliquid, prediction markets via Polymarket, multi-chain DEX aggregation Market Data & Research: Real-time token prices, OHLCV charts, liquidity analysis, market cap, volume, token security audits, honeypot detection, rugpull detection, holder distribution, deployer history, KOL wallet tracking, whale monitoring, live swap feeds, token launch streaming Portfolio & Positions: PnL tracking, trade history, position management, wallet tracking, multi-chain portfolio aggregation, XP and fee tier management Agent Infrastructure: Keyless agent wallet generation, secure credential proxy, kill switch access control, verbose tool call logging, audit trail, no private key exposure Install: npm install -g @tradeboba/cli then boba init to connect free credentials from agents.boba.xyz Compatible with: Claude Code, Cursor, OpenClaw, any MCP-compatible AI agent or code editor

MCP server that gives AI agents real crypto trading capabilities. 13 tools across market data, order execution, grid strategies, and Cardano DeFi. Connects to Bitget, Gate.io, MEXC, and Kraken. Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client. Open-source, MIT-licensed.

Structured 3-layer memory system for AI trading agents. L1 records every trade automatically. L2 discovers patterns via reflection engine. L3 evolves strategy in real-time. Built on MCP. Supports MT5, Binance, Alpaca. Python/FastAPI/SQLite. MIT licensed.

MCP server for https://oathe.ai security audits. Runtime behavioral analysis and security scanner for AI systems. Check trust scores before installing MCP servers, plugins, or AI agent skills.

Fast semantic code search for AI agents — find symbols, references, and callers across any codebase. Pre-built index committed to git, instant queries via MCP

A production-grade Model Context Protocol (MCP) server for Microsoft SharePoint. Connect Claude Desktop, VS Code Copilot, Cursor, Continue, or any MCP-compatible AI agent to your SharePoint — read files, manage folders, and reason over your organisation's knowledge.

Trust scoring, verified knowledge pools, and reputation tracking for AI agents. Search community-verified knowledge, contribute claims with evidence, validate other agents' knowledge, and build portable trust scores across the AI ecosystem. Supports trust attestations with Ed25519 cryptographic proofs.

TEOS MCP is an MCP server that performs real-time diff-level security scanning for AI agents and CI/CD pipelines. It analyzes code diffs before merge or deployment and returns a deterministic gate decision: ALLOW WARN BLOCK Built for: • AI agents • Autonomous systems • DevSecOps teams • CI/CD workflows Features: • Diff risk scoring • Deterministic merge gate • Real-time enforcement • Usage-based monetization (pay-per-scan) • Optional on-chain verification Unlike gateway filters, TEOS MCP performs code-level intelligence before execution.

Verifiable Memory-as-a-Service for AI agents. Persistent, searchable, graph-connected knowledge with optional Starknet on-chain proofs. Works locally with zero config (SQLite) or in cloud mode.

Compliance evidence infrastructure for regulated tokenized markets. 27 MCP tools with ES256K-signed responses covering MiCA preflight (PASS/WARN/BLOCK), peg monitoring, reserve quality, custody risk, evidence grading (A-F across 61 RWA protocols + 105+ stablecoins), KYA agent identity, tamper-proof audit trail, macro risk (86 FRED + 20 ECB indicators), and signed PDF reports with XRPL blockchain anchoring. Part of a 3-server ecosystem: Compliance MCP (27 tools), Macro Intelligence (13 tools), Stablecoin Risk MCP (13 tools) — 53 tools total. New in v4.2: Know Your Agent (KYA) identity + trust scoring, tamper-proof SHA256 chain-linked audit trail, Evidence Lifecycle (6 states), OAuth 2.0 with Dynamic Client Registration, Enterprise Trust Layer (14 components), Unit-Based Billing, Trust Policy v1.0, 8 reference workflows. OAuth 2.0 + StreamableHTTP + SSE. Free tier: 300 units/day, no API key required. MiCA enforcement July 2026. Connect: claude mcp add --transport http feedoracle https://feedoracle.io/mcp/ Trust proof: https://feedoracle.io/trust Docs: https://feedoracle.io/docs.html

Give AI agents spending power without giving them your wallet keys. Cloaked creates on-chain spending accounts with enforced constraints that agents cannot bypass - even if jailbroken or compromised. Website: https://cloakedagent.com Documentation: https://cloakedagent.com/docs SDK: https://www.npmjs.com/package/@cloakedagent/sdk GitHub: https://github.com/CloakedAgent/cloaked

Structured failure knowledge for AI agents — 1,000+ errors across 20 domains. Dead ends, workarounds, error chains, and freshness tracking.

Epitome gives every AI agent shared, persistent memory of you. It stores memories, facts, and preferences in a personal knowledge graph, so any AI tool you use already knows your context. Connect via MCP using Streamable HTTP — no local install needed.

The payment protocol for people and agents. One MCP server, any payment rail. Multi-provider routing (Woovi/Pix, Stripe, Belvo), spending guardrails, human-in-the-loop confirmation, and audit logging.

Ultra-fast to deploy agentic-first mcp-ready semantic layer. Let your data be like water. Bonnard is a CLI for building and deploying semantic layers. Define metrics and dimensions in YAML, deploy a governed MCP server, and serve AI agents and BI tools. Supports Snowflake, BigQuery, Databricks, PostgreSQL, and more. Ships with native integrations for Claude Code, Cursor, and Codex. GitHub: https://github.com/meal-inc/bonnard-cli Docs: https://docs.bonnard.dev/docs/ npm: https://www.npmjs.com/package/@bonnard/cli

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.

Context Rot Detection & Healing — gives AI agents self-awareness about their cognitive state by analyzing token utilization, quality degradation, and session fatigue. Returns health scores (0-100), model-specific degradation curves for 15+ models, lost-in-the-middle risk scoring, and actionable recovery recommendations.

Deterministic authorization for AI agent spending — budget checks, spend authorization with Ed25519 cryptographic seals, and audit logs.

AI-Native Financial Network — Banking, trading, lending, governance & marketplace for autonomous AI agents. 120+ tools, real USDC/EURC, on-chain settlement.