Turns long-form videos into short-form clips (TikTok/Reels) by reasoning over word-timestamped transcripts, with silence-aware rendering, STT-based validation, and optional reframing/captions.
MCP router that fronts your other MCP servers behind a few small generic tools, so their tool definitions stay out of the context window and are discovered on demand.
Audits MCP tool descriptions for quality and reliability, scoring them 0-100, detecting smells, and providing rewritten versions for better agent accuracy.
Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.
A Model Context Protocol server that enables AI assistants to interact with Google Gemini CLI, allowing them to leverage Gemini's large token window for analyzing files and codebases using natural language commands.
Enables AI agents and MCP clients to deterministically score creator short-video hooks for 3-second retention and scroll-stop effectiveness, returning structured JSON telemetry. It runs as a zero-dependency Python MCP server for seamless integration with Claude Desktop, Cursor, and Windsurf.
Enables scoring the WHO-5 Well-Being Index from five answers, returning a 0–100 score and a low, reduced, or normal band without providing a diagnosis.
Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.
Gives LLM agents spatial awareness inside Autodesk Maya, enabling scene inspection and measurement, aesthetic and engineering audits, camera planning, checkpoint/rollback safety, asset import, and viewport or render previews. Agents can also execute arbitrary Python in Maya to build and verify 3D scenes against engineering rules instead of writing blind.
Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.
Enables detection of AI-generated content in images, videos, audio, and text via the AI or Not API. Supports media analysis tools for deepfakes, synthetic voices, and AI-written text.
Enables AI agents to subscribe to a deterministic daily ethics feed drawn from a four-module curriculum and retrieve read-only tools, resources, and reflection prompts covering principles, case studies, and codes of conduct.
Lets your AI app build real SOLIDWORKS parts, sheet metal, weldments, assemblies and drawings on Windows: fully defined sketches, 121 tools, and every result measured from the model. One-click Windows installer.
Enables MCP clients to discover OpenRouter image and video models, generate and edit images, create variations, launch and monitor video jobs, and save resulting media into authorized local project directories with cost controls.
A local stdio MCP server that enables validated access to official ElevenLabs APIs with cost controls, local media storage, and audio export for Godot.
MCP server over a curated catalog of 78 AI tools for engineering teams. Every entry states when it fits, when it does not, its limits, licence terms and open issue numbers, all verified against the project's own repository — search by keyword, category or licence, and get full records or published comparisons.
MCP server that detects and guards against tool poisoning and prompt injection attacks in tool descriptions and schemas. It provides risk scoring, pattern detection, safe rewriting, and audit reports with zero external API cost.
Lets a human review what an AI agent is about to post to a chat tool (Slack first) before it is sent. Renders the draft, destination and warnings (@here/@channel, unresolved mentions, format issues) in a neutral local HTML preview; never sends anything.
Analyzes multi-step AI agent tool chains to compute success probability, identify bottlenecks, and suggest better execution orders, enabling more reliable agents via local pure-math computation.
Give your AI agent the entire China A-share market: 55 datasets of prices, financials, capital flows, corporate events and futures/options, stored locally and queryable with read-only SQL. Built point-in-time with delisted stocks kept, so backtests don't lie — no account, no API key.
Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the results. Free AI moderation. Uses an organization API token from askone.org
Codebase Q&A agent with git-history awareness. Explore a repo with list_files, read_file, and search, plus git log, blame, and diff and a repo map to answer "why did this change?" questions. Runs locally as an MCP server for Claude Code and other MCP clients.
MCP server for Takes, a free, open-source Mac teleprompter and recorder for talking-head videos. It lets an AI assistant write scripts and storyboards, manage takes, make edits and draft the posts for LinkedIn, X, YouTube and Shorts.
Enables agents to plan token swaps, cross-chain swaps or bridges, and native gas top-ups on six EVM chains by returning unsigned transactions for user wallets to sign. It also supports tracking transfers, resolving token addresses, and obtaining gas through a signed USDC authorization.
Enables agents to synthesize typed MCP tool schemas at runtime, validate Python ASTs for unsafe imports, compile sandboxed callable handlers, and hot-plug them into an active MCP runtime. It provides a zero-dependency, standard-library-only MCP server for safe just-in-time tool creation and execution.
WordPress plugin that runs an MCP server on your own site: search and read published posts and pages, look up WooCommerce products, describe the site as schema.org types and query site figures, with drafts only when the site enables them. Signed-in access by default; anonymous access and OAuth are optional and off.
Enables querying real-time China A-share stock and major market index quotes by stock code or Chinese name, with automatic name resolution and dual free data sources.
Enables autonomous agents to automatically repair and guard tool-call schemas through deterministic AST analysis and parameter projection validation, ensuring reliable, schema-compliant interactions in MCP-compatible environments.
Enables agents and MCP-compliant clients to resolve tool execution graphs by scheduling calls as a topological dependency DAG, running independent tools in parallel batches while speculatively prefetching and evaluating arguments. This cuts latency and token burn by handling routine tool orchestration deterministically without extra LLM round-trips.
Enables agents to search a catalog of 216 browser-based file tools and hand users a working link instead of generic advice, while also running small stateless helpers for text stats, hashing, UUIDs, passwords, JSON, Base64, colour conversion and QR codes.
Lets AI agents register, post job specs to matching specialist bots, authorize PayPal escrow funds, and capture payment only for units that pass acceptance checks. Covers the full job lifecycle — bidding, hashed contracts, funding, delivery verification, payouts, dispute mediation and long-polled events.
This MCP server wraps agent tool calls with fault-tolerant retry logic, including adaptive exponential backoff, full jitter, 429 rate-limit backpressure handling, and circuit breaker patterns. It enables autonomous agents to execute tools reliably without frontier LLM round-trips, using a zero-dependency Python stdio JSON-RPC interface.
Enables AI agents to track, calibrate, secure, and audit Milwaukee M18 FUEL ONE-KEY power tools through BLE proximity, geofencing, torque profiles, remote lockout, and fleet telematics.
A lightweight, zero-dependency MCP gateway adapter that enables Claude/Cursor agents to process structured JSON payloads and integrate with GenPark AI agent pipelines.
A stdio MCP server exposing a validate_emails tool that lets agents screen email lists without sending mail or probing SMTP, checking syntax, DNS/MX records, disposable domains, role accounts, free providers, typo suggestions, and SPF/DMARC. Each address comes back with a valid/risky/invalid/unknown verdict plus machine-readable reason codes so agents can clean leads and signups before outreach or import.
Local memory for coding agents that can refuse, not only recall. A rule carrying a machine-checkable proof blocks the matching command before it runs, while prose-only rules can warn but never block.
Enables MCP clients such as GitHub Copilot, Codex, Claude... to explore a SQL Server 2017+ database read-only: databases, schemas, tables, views, procedures, functions, indexes and dependency graphs, plus filtered, grouped, sampled and paginated queries capped by row limits.
Send email through your own Amazon SES account, and check domain verification, the suppression list and sandbox status. Works with any SES account; Wraps adds send history and delivery events.
Manage SockDock rules from an MCP client: Slack posts that run Claude Code, Codex or a program on your Mac, through one Socket Mode app. Needs SockDock running.
Enables AI assistants to search, read, compose, and manage Thunderbird mail, filters, contacts, and calendar events through the Model Context Protocol.
Read selected local folders from ChatGPT on macOS, with per-folder read-only or read-write access and hash-checked, recoverable edits. Requires local installation and a private ChatGPT app. The Glama container is a synthetic evaluation demo; it does not connect to files on your Mac.
Gives AI clients guarded access to SAP Business One over SAP HANA / MS SQL and the Service Layer OData API. SQL is read-only, enforced on the server; Service Layer is GET-only by default, with opt-in writes that require user approval unless a profile explicitly turns it off.
Daily market-regime context for trading agents: is the market risk-on or risk-off? Free tools: rules, schema, ledger of issue hashes, 7-day-delayed issues, full PAPER results record (losses included), disclosures. Paid tool: today's issue via x402, 0.10 USDC on Base, with spend caps and optional Agent Trust payment preflight. No track record; not investment advice.
Run all of WordPress + SEO, Security, WooCommerce Shop & Elementor: 10 websites in one connector. Posts, pages, media, comments and updates from Claude, ChatGPT or Cursor. Start free.
Enables AI apps to read a student's Moodle courses, upcoming and overdue due dates, assignment submission statuses, course grades, gradebook items and announcements. It is strictly read only, so it can never submit, edit or delete anything.
Lets AI agents create real disposable email addresses, wait for incoming mail, and get verification codes and links back, so they can complete signups, logins and email-flow tests on their own. Codes and links are detected server-side, so no HTML parsing is needed. Requires an OpenInbox API key (Pro, Business or 7-Day Pass).
Enables Claude to check, search, read, and organize email across multiple Spacemail (Spaceship) inboxes, and to compose threaded drafts or replies that are saved to Drafts for review before sending. Optional direct sending, safe move-to-Trash instead of permanent deletion, and keychain-backed credentials keep the workflow private and controlled.
Lets Claude Desktop and Claude Code inspect and drive Windows desktop applications in the background, including clicking, typing, launching, and verifying results, while the user keeps their mouse, keyboard, and foreground window.
Hebbian learning MCP server with neural memory graphs, eligibility traces, and three-factor
reward signals. Associative memory that strengthens through use.