PoC benign MCP server for update-hijack security research
Demo: Server update hijack PoC (clean copy for video)
PoC: Open Registry supply chain — unvetted server listing (security research)
Agent context flight recorder: restore after compaction, fan-out packs, signed git-bound receipts.
Fully local memory for AI agents: zero-LLM ingest, semantic recall, air-gapped, auditable.
Score sentiment toward specific entities in text. Cluster documents and name topics.
Free passive security scanning - check any domain's DMARC, TLS, headers, and exposures.
MCP server for Proxmox VE management (VM, LXC, nodes)
MyTelescope demand intelligence: signals, forecasts, competitor share, and emerging trends.
Dubstrata: Causal Financial & Narrative CDN providing Graph RAG & Deep Research Reports
Standalone MCP filesystem tools server — view, edit, shell, workdir.
Persistent memory for AI assistants with semantic search and knowledge graph relationships.
One safe tool for your AI agent to publish to every social network via the Social Fanout API.
Redis health, BullMQ queue monitoring, memory analysis, and slow query diagnostics
An MCP server that provides text preprocessing, NLP components, and document analysis
AST-based Python refactoring MCP server with safe automated refactorings and rollback
Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores.
Agent-First Data Bazaar. 136 Tools for DeFi, Derivatives, Governance, Alpha & Utilities.
Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.
Inject, parse, and strip [N] citation markers in RAG outputs.
Validate tool-call args before execution. Returns LLM-friendly retry hints.
Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
Network-egress firewall for agent tools: check URLs against a declarative policy.
Token-aware message truncation: fit a chat history into your model's context budget.
Structured-output enforcer: extract and validate JSON from messy LLM text.
Relays messages between two Claude Code sessions on different machines using the Channels API
Engine-free, governed Oracle Database MCP server with a fail-closed SQL guard (unofficial).
Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
Agent-first prediction markets on Base. Trade, quote, create markets via MCP.
MCP server for Atlassian Bitbucket Data Center - interact with repositories and code
Apple Mail, Calendar, Contacts, Reminders, Notes, Messages and Safari via AppleScript or iCloud
Flight data for Spain's 50 AENA airports over the public and OAuth2 REST APIs
Human-curated crypto market intelligence with x402 payments. Weekly signals and analysis.
Vivino wine data for AI assistants: search, explore, wine details and meal-aware recommendations
Stateless advisor + validator for Conducted Development: kickoff, artifact validation, rule checks.
Universal AI coding assistant memory — session handoff, SLM compression, and semantic retrieval.
All-in-one, self-hosted AI memory with semantic search, vector RAG, live updates, and governance.
Korean stock market theme lifecycle analysis (TLI) — rankings, stock lookup, predictions & prompts
Local MCP server for stateful, fail-closed Logic Pro control and live project readback.
Git-native decision memory for coding agents: only the decisions still in force for the edited path
Trust infrastructure for AI agents — DIDs, reputation, verifiable credentials, USDC.
Educational dermatology knowledge and lesion tooling. No credentials needed. Not a medical device.
Judge hardware timing/serial against a contract: pass/marginal/fail (WS2812, DShot, logs)
Pay-per-call DRT/ICT crypto trading signals for AI agents (LONG/SHORT, entry/SL/TP).
Generate app icons, favicons, OG images, and logos by routing across 30+ image models.
Linux MCP server for real-time system monitoring - CPU, memory, disk, network, processes, Docker.
Unofficial Infomaniak MCP — hosting, Node.js, mail, DNS, kDrive, SSL, VPS, domains. 81 tools.
Agency-grade MCP for WordPress Elementor — multi-site, safe edits, templates, versions.