Enables agents to guard external API calls with circuit-breaker health checks, success/failure reporting, and recovery state inspection, including exponential backoff with jitter and fail-fast rejection.

Enables agents and applications to detect, inspect, and neutralize prompt injection, jailbreak attempts, and hidden instruction escapes in untrusted text before it is passed into prompts.

Enables multiple autonomous agents to safely modify shared workspaces and documents by performing three-way reconciliation, detecting collisions, and returning structured conflict data for automated re-arbitration.

Enables agents to store LLM query-response pairs and retrieve them via fuzzy cosine similarity matching, reducing duplicate inference calls; it exposes tools for setting cache entries, semantic lookup, and hit-rate statistics.

Claude Code skill for editing Russian text using Ilyakhov's information style (инфостиль). First-ever AI skill based on 'Пиши, сокращай' methodology.

DeepSeek Harness 终极指南：快速入门、资源推荐、精选插件与实用工具 ｜The Ultimate Guide to DeepSeek Harness: QuickStart, Resources, Plugins&Toolkit

Enables Claude to create, edit, validate, and animate video projects through structured project files, including rendering frames or exports, inspecting previews, and applying themes, templates, effects, and subtitles.

Enables agents to run multi-engine web searches, find GitHub repositories, and fetch web pages as Markdown with headless-browser fallback and automatic system-proxy support.

A read-only MCP server that lets AI assistants search and browse the Coolapk community — posts, comments, topics, user profiles, home feeds, and images — with built-in login reuse, rate limiting, and risk-control fallbacks. All access is strictly read-only, so agents can look up community information without any write operations.

Enables Claude to manage an Instagram professional account through Meta's official Graph API, including analytics, comment moderation, and publishing, while running locally with confirmation-preview safeguards for write actions.

Enables reading public WeChat articles through HTTP text extraction with metadata, pagination, and image links, automatically falling back to a visible Chrome window when a verification page appears so the user can complete any captcha manually.

Enables local synchronization of Garmin activity and health data using a personal API key, then lets MCP-connected AI clients analyze training readiness and recovery with cited models and research. Supports viewing records, sleep/HRV, stress, Body Battery, and generating pre-run recommendations without hosting accounts or personal data.

Enables AI assistants to raise, submit, approve, amend, and cancel purchase orders and onboard suppliers in ERPNext or SAP S/4HANA while enforcing procurement controls such as duplicate detection, budget limits, split-purchase checks, price tolerances, and segregation of duties.

Enables creating, inspecting, and stopping Google Colab sessions, executing Python code or files, retrieving session URLs, and reading logs through the local Colab CLI.

Enables discovery of official DHS country, survey, and indicator metadata; retrieval of public aggregate estimates; assessment of comparison risks; and export of auditable CSV, JSON, Excel, or executable notebook bundles.

Enables AI agents to set up, launch, monitor, and manage LoRA training runs through the ai-toolkit web UI API, including datasets, captions, job configuration, checkpoints, logs, loss curves, and sample images.

Enables MCP clients to explore PostgreSQL schemas, run guarded read-only queries with row limits, and inspect execution plans without executing them. It prevents writes and DDL while exposing schema discovery tools, a schema overview resource, and a guided analysis prompt.

Read-only MCP server with real Chinese chain-restaurant nutrition data: 103 menu items across 14 chains, calories and macros plus per-item health notes. Published on PyPI.

Enables AI agents to monitor live token consumption and rate-limit windows across providers and assess whether expensive actions are justified before exhausting quotas, with optional budget guardrails.

Enables natural-language control of Siemens NX 12 for 3D modeling, 2D drafting, tolerance annotation, process planning, read-back verification, and PDF export through a persistent NXOpen bridge.

Enables AI agents to search and invoke 1,939 Atlassian automation tools across Jira, Confluence, Bitbucket, Admin, Assets, and more, with cached reads and JSON-RPC over stdio. It helps agents find tools without calling Atlassian and execute operations while reducing rate-limit pressure.

Enables AI assistants to connect to a student's university learning platform through Lightpanda, supporting consultation of courses, activities, deadlines, calendar events, downloadable materials, and assignment submissions via natural-language requests.

Enables MCP clients to perform basic arithmetic, send demo log messages, read static and personalized greeting resources, generate greeting prompts, and receive autocompletion suggestions over Streamable HTTP.

Enables AI clients to create, configure, validate, and generate STM32CubeMX projects through 113 MCP tools, including pin, clock, peripheral, RTOS, and middleware setup plus C code generation. It can drive an installed CubeMX engine or run fully standalone using a bundled data pack with real pin and mode validation.