Enables read-only access to Percona Monitoring and Management 2.x through PromQL metric queries and Query Analytics, so clients can list monitored databases, surface the slowest queries, inspect query details, and run validated SELECT queries against QAN's ClickHouse data. TLS verification, input validation, and Viewer-role tokens keep access strictly observational.

Voxel editor with an MCP server: build and edit MagicaVoxel .vox models, add bones and animation clips, run Rhai generator scripts, path-trace PNG previews, and export glTF.

Enables AI assistants to query and analyze self-hosted real-estate public-records data through 20 read-only MCP tools, including property search, foreclosure and distress signals, comps, market context, and optional license-gated deal scoring.

Enables AI assistants to inspect and query a TPC-H sales warehouse through read-only, allowlisted catalog tools and schema resources, with ad-hoc SQL disabled by default. It enforces strict arguments and input-free errors, while a differential attack suite verifies that query protections hold across MCP transports.

Enables governed, AI-safe access to traveler data through three typed tools, enforcing consent, PII removal, provenance, and audit at the MCP boundary.

Connects AI assistants to Apple Mail, Calendar, and Contacts on a Mac, enabling local search, message reading, contact lookup, and optionally sending email or creating calendar events with guarded confirmation.

Enables Claude and other MCP clients to search finn.no and create, manage, and publish Torget ads from photos — preparing images (EXIF/GPS stripping, resize, HEIC), writing titles and Norwegian descriptions, suggesting category and market price, checking for duplicates, and publishing only after explicit confirmation. Read-only search, listing details, saved-search diffs, and management of your own ads are also supported through a locally stored logged-in session.

Turns a Frappe site into a remote MCP server that AI clients such as Claude can sign in to with OAuth and use curated, task-level tools registered by installed apps. Every call runs as the signed-in user with that user's permissions, with schema-checked arguments and rollback on failure.

Turns a HAR capture of an undocumented web system into an MCP server whose tools automatically handle hidden CSRF tokens, ETags, and rotating nonces, with write actions gated behind confirmation and exercised only against a sandbox. Verified tools are shipped alongside an honest report of the actions that could not be automated and still need a human.

Enables querying a Chatwoot support inbox in plain language—finding conversations, contacts, and conversations needing attention—and, after explicit confirmation, adding private notes or updating assignments, labels, and status without sending customer messages.

Enables plain-language queries about a support desk, ticket and customer investigation, and safe, confirmation-gated ticket assignment and internal notes.

Enables asking in plain language about a Proxmox VE cluster's guests, backups, snapshots and resource pressure, and starting, cleanly shutting down or rebooting VMs and containers or taking snapshots from the same chat. Every change requires a one-time confirmation code, and no tool can delete a guest, restore a backup or roll back a snapshot.

Enables AI assistants to read Lanhu requirements and design handoffs, extract pages, annotations, screenshots, design parameters, and image assets, and share team knowledge through a collaborative message board.

Enables MCP-compatible AI clients to run passive OSINT investigation tools for domains, IPs, emails, usernames, breaches, DNS, WHOIS, and reputation checks through natural-language tool calls. It exposes 16 passive tools by default, plus graph and batch helpers, with additional active tools available when explicitly enabled.

Enables reading, searching, organizing, archiving, and drafting email and calendar events in a locally running classic desktop Outlook via COM, with attachment saving and safety boundaries that prevent sending or deleting mail.

Enables local macOS clients to retrieve video metadata, timestamped transcripts, and still frames from Loom share links or IDs through three read-only stdio tools.

Enables an AI assistant to convert PDF and EPUB chess books into faithful PGN by reading pages and diagrams, validating moves with python-chess, preserving variations and commentary, and reporting verifiable issues.

Enables querying FAOSTAT statistics through read-only tools whose results are row- and size-capped, with a note on how to see the remainder. Every response carries release metadata such as source, endpoint, retrieved_at, published_at, and vintage.

Enables AI clients to control AutoCAD 2027 on macOS in real time through a live GUI bridge and to process drawings headlessly with AcCoreConsole and ezdxf, including drawing and editing geometry, managing layers and blocks, inspecting entities, and exporting DWG, DXF, PDF, or PNG files.

Enables searching, retrieving, summarizing, and comparing official central-bank time series, with resource and prompt access for generating reports and evaluating answers against memory-only responses.

Enables Claude Code and Codex to write, update, and retrieve durable long-term memories that survive session boundaries and context compaction. All recall runs locally against a single SQLite file using hybrid BM25, embedding, and recency ranking cut to an explicit token budget, with no cloud dependency.

Enables MCP-compatible AI clients to search and view CRM customers, deals, contracts, tasks, calendars, and outbound jobs, and to propose opt-in write actions that require human approval in the CRM.

Enables Claude to work with a corporate mailbox over IMAP/SMTP — listing, searching, reading, sending, forwarding, replying, handling attachments, and moving messages between folders — alongside calendar browsing and event creation/editing over CalDAV. Authentication needs only a single external app password, with no developer-console registration or admin approval.

Enables MCP clients to discover NVIDIA, AMD, and Intel GPUs, monitor utilization, memory, temperature, power, clocks, and processes, retain bounded local history, and estimate whether AI models fit available VRAM before loading them.