Enables MCP clients to query and diagnose machine-learning training runs through read-only tools for listing experiments, reading configurations and final metrics, comparing runs, sampling metric curves, and detecting training failures.

Enables AI agents to connect to Maptek Vulcan 12 Desktop through MCP, allowing natural-language inspection of block models and triangulations, drillhole and CAD database operations, legend updates, 3D screenshots, and PyVulcan script execution.

Enables live inspection and debugging of running C++ processes (development builds with PDBs) by controlling execution through cdb, evaluating expressions with natvis, reading and writing memory, and rapidly querying symbols and types via DIA, with special support for Unreal Engine processes.

Enables LLMs to query a local GnuCash MariaDB database through read-only MCP tools for account balances, recent transactions, spending and income by category, transaction search, and net worth without risking data mutation.

Enables MCP clients to control KakaoTalk PC through the Win32 API, sending, mentioning, and reading messages, opening chat rooms, sending images, extracting shared links, and monitoring rooms for keywords. It supports health checks, bulk sends to multiple rooms, and exact room-name matching for reliable automation.

Enables MCP-capable AI agents to control Windows desktops through UI Automation element trees, native screenshots, app launching, batched action sequences, smart waits, and safety gates using normalized coordinates.

Enables automation of the QingSoft U+ learning platform by patrolling courses, homework and experiments, inspecting objective questions, filling and submitting answers, and handing subjective work back to a human, while also providing a generic browser automation toolset.

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 an MCP-compatible assistant to log in with UNC single sign-on and explore the FCEFyN virtual classroom, listing enrolled courses, retrieving course indexes and materials, and reading or searching pages, activities, and PDFs. It works read-only with the user's own credentials, without tokens, admin permissions, or downloading entire courses.

Enables auditing GitHub Actions workflows for security problems directly from an MCP client, returning a risk score and findings with file:line evidence, attack narratives, and fixes. Also exposes the full rule catalog and a one-call demo that writes and scans a deliberately broken workflow.

Enables an LLM client to perform reverse engineering inside IDA Pro without the GUI, opening databases headlessly in persistent worker processes and exposing tools to decompile and disassemble functions, rename symbols, retype variables and arguments, add comments, and convert numeric bases. It can also run over stdio or HTTP transports and adopt an existing GUI session when desired.

Enables AI agents to query and trade through Interactive Brokers using 38 tools for order placement and management with risk checks, account and position data, market and historical data, and options analytics. Includes diagnostics and configurable safety limits, designed primarily for paper trading.

Enables Codex sessions to observe and control the Windows desktop through screenshot reasoning, archived-frame inspection, pixel sampling, keyboard/mouse input, and workspace-local multimodal memory.

Enables a model to write short Python programs that call a wrapped MCP server's tools as async functions, rather than invoking them one at a time. The program runs in a locked-down Docker sandbox, and every tool call passes through a host-side bridge that enforces an allowlist, schema-validated arguments, call budgets, timeouts and output caps.

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 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 LLM clients to explore and query a local SQLite database through read-only, typed tools for table listing, schema inspection, ad-hoc SQL, customer lookup, and sales summaries.

Enables MCP clients to search, classify, cite, and read EndNote X9 libraries locally, with PDF text extraction and narrowly scoped, backup-first field updates.

Enables coding agents to run diff-scoped mutation testing on Python code, returning mutation scores and surviving mutants with actionable hints so they can improve tests.

Enables any MCP-compatible client to persist long-term memories for AI agents, with LLM-based fact extraction, semantic vector search, update/delete/list operations, and queue status checks across sessions.

Enables AI agents to operate a self-hosted double-entry personal finance ledger: answering spending, net-worth and cash-flow forecast questions, searching transactions, and managing schedules, rules and imports through audited, reversible tools. Read and write access is scoped by token, with privacy controls over what financial details reach the agent.

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 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.