"osu!" matching MCP servers:

Enables AI agents to submit npm, PyPI, Go, or Maven packages and manifests to the free OSV.dev database and receive per-package and per-advisory results with CVE mappings, CVSS scores, severities, and the versions that fix each issue. It also supports filtering by minimum severity, de-duplicating alias advisories, and machine-readable error/warning rows for CI gates and upgrade recommendations.

Visual CVE audit dashboard for npm, Python, Go, and Rust projects. Scans your project manifests (package-lock.json, requirements.txt, go.sum, Cargo.lock) against OSV.dev live data, opens a browser dashboard for human review, then applies fixes only after explicit confirmation. Supports multi-service monorepos in one command.

Structural memory for coding agents — 60% fewer tokens, refactor-safe, runs entirely on your machine.

Gives every AI agent you use one shared, versioned memory in a local SQLite file, so a fact saved from one app is found by all the others. Runs fully offline with no API key, records which agent wrote each change, and keeps every prior version so nothing is silently overwritten.

An MCP server that enables natural language querying and troubleshooting of Kubernetes clusters, supporting multi-cluster switching and providing tools for pods, nodes, events, and logs.

Enables AI agents to start, control, and verify local open.mp/SA-MP game servers via MCP stdio, using a headless RakClient to send allowed slash commands and assert round-trip responses.

Gives any MCP client the same sandboxed coding-agent toolset — searching, viewing and editing files, running tests, and executing shell commands — each session in its own locked-down, network-isolated Docker container. Enables an MCP-capable assistant to diagnose and fix failing tests without touching the host machine.

Enables agents to convert local files across 162 input formats and 3649 proven conversions, using two tools to list supported formats and convert files with clear error reporting.

Build AI trading agents on Eterna Hybrid Exchange (no-KYC perp DEX with flat 0.014%/0.035% fees). Works out of the box with fee estimation, venue comparison, setup guides and guarded agent prompts; add an Eterna token to bridge the official trading tools.

Enables reading diagnostic data from remote servers over SSH using a whitelist of read-only commands, with secret redaction.

Memory vaults on your own machine, one per life domain, retrieved with a local BM25 index fused with vector search, where the human decides which vaults a model may answer from. Requires the Mnemosyne OS desktop app running locally; it also reports what other coding agents on the same machine are doing.

Walkie-talkies for AI coding agents: Claude Code, Codex, Cursor and any MCP client message other developers' agents directly, peer to peer over HyperDHT and end-to-end encrypted. No server, no account. Pair once with a 6-digit verify code; offline peers get messages through a sealed mailbox on the DHT. Tools: send_message, read_inbox, list_messages, list_peers, get_status.

Provides transactional intelligence for AI agents, enabling safe tool execution with pre-flight invariant checks, sub-second filesystem snapshots/rollback, causal tracing, belief contradiction detection, and 15 native MCP tools for Claude Code.

Stops AI agents reopening rejected decisions and forgetting project state. Persistent operational state for agents: decisions, plans, blockers, priorities and patterns that survive across sessions, with enforcement. Not conversation logs.

Enables AI agents to shop and query Magento/Mage-OS stores via the storefront GraphQL API, including product search, stock checks, category browsing, cart management, and customer order status.

Exposes a Notion-synced AI OS as read-only MCP tools, enabling MCP-compatible AI clients to search the vault, fetch page contents, list projects, and check project statuses without scraping public links.

Enables code agents to persist and recall durable project knowledge — rules, decisions, procedures, learnings and secrets — across sessions at low context cost, with accent-insensitive PT-BR search, scoped per repository/workspace, and secrets that stay out of the model's context.

Enables scanning Java (Maven) projects for known vulnerabilities via natural language, returning severity-sorted reports with CVSS scores and fix versions.

Enables AI assistants to scan local disks for developer caches, large unused videos, and old logs, present candidates for approval, and move only approved items to the operating system trash so they can be restored while protecting system folders.

An orchestrator MCP server that takes a plain-language app description and guides agents through a full workflow from intake to deployment, including design, audit, and maintenance.

An MCP server that scouts truly beginner-friendly open-source issues from GitHub, checking availability and summarizing them for AI consumption.

MCP server for Victron Venus OS that enables reading battery, PV, grid, and inverter data via D-Bus and MQTT, and safely controlling inverter mode and charge limits.

Enables AI agents to list metrics and dimensions, inspect definitions, and run governed metric queries against Apache Iceberg tables through a semantic layer, without writing SQL or accessing raw rows or columns outside their role.

Bridges Design OS exported component packages into target projects, handling migrations across different CSS, component, and icon libraries.

Enables users to store and query their own medical data—labs, medications, diagnoses, wearables, and food logs—in a local Postgres database and interact with it through any MCP client, with deterministic safety checks.

Enables an LLM agent to search files, list directories, read and write UTF-8 text files, move or delete paths, list terminal processes, and launch a terminal in a chosen folder.

Enables AI agents to generate dimensionally accurate mechanical parts (gears, enclosures, brackets, assemblies) in headless Blender from plain-English specs or JSON parameters, then verify them against manifold, bounding-box and print-production gates and export glTF/STL assets. It also scaffolds interactive Three.js CAD viewer pages with orbit controls, wireframe toggles and exploded-view scrubbing.

Acts as a persistent memory and cross-tool shared context store, and builds a queryable codebase knowledge graph to slash token usage via structural answers.

Provides a memory server for coding agents over MCP, capturing and retrieving the meaning and rationale behind code decisions down to the function level. It enables agents to search product memory, get task context, and propose new memories to avoid re-deriving or re-breaking past decisions.

Enables Claude or any MCP client to read, create, and edit GoHighLevel workflows through a logged-in Chrome session, with no API key or marketplace app install. Provides 30 tools for workflow CRUD and publishing, step-level patches, folder management, and location data such as tags, users, pipelines, and custom fields.