LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.

Enables MCP-capable agents to settle deadlocks with a neutral, unsteerable tie-break and to obtain sealed independent AI review of their output, returning Ed25519-signed receipts that can be verified offline. Also supports running free demo matches and listing saved receipts with spend tracking.

Enables an AI agent to set up, run and verify engineering simulations through typed tools — creating or importing cases, setting boundary conditions, running solvers, checking convergence, verifying results against references, and rendering output, with edits appearing live in the GUI. It exposes no shell or code-execution tool.

Enables AI agents to see compiled LaTeX output: it builds the document, returns rendered page images, maps any point on a page back to its exact source line, and diffs what the last edit changed. It also audits an entire book for regressions, letting an agent diagnose and verify layout fixes without reading source alone.

Gives AI coding agents on-demand security playbooks, a code scanner they can run on their own output, and live lookups against CISA KEV, NVD and OSV so they verify threats instead of guessing. Runs locally with no API keys or accounts, exposing skills, tools and a secure-build prompt to Claude Code, Codex, Cursor or any MCP client.

Enables MCP clients to reverse-engineer binary files — hex viewing, disassembly, function/call-graph recovery, syscall and RTTI naming, string/xref search, and symbol export for Ghidra and IDA — across Switch NSO/NRO/NSP and many other formats. Tool output is persisted as annotations so analysis carries across sessions.

Turns a long tennis recording into a labeled highlight reel: keyframe-aligned lossless rally clips, hit count / venue / timestamp burned in, and a self-check on every output. Runs locally with ffmpeg.

GPU energy per million output tokens by model, GPU and configuration, with grid carbon by country.

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.

x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

Opt-in, token-authenticated MCP server built into the Shelly Android terminal app: read-only tools for terminal output, git status, registered agents and repos on the phone, plus off-by-default run_command and write_file that need an on-device approval tap per call.

Enables coding agents to record product demos, changelog GIFs, help-center guides, and bug repros by driving a signed-in browser or Mac window, then rendering branded MP4 and GIF outputs with delivery checks.

Enables coding agents to navigate and verify a contract-backed semantic graph of TypeScript backends, inspect change impact, run checks, explain failures, and draft human-reviewable contracts through bounded MCP tools and matching JSON CLI output.

Keeps large tool outputs out of an agent's context window by spilling them to disk and handing back a short pointer instead. Lets the agent pull only what it needs — exact numbered line ranges read directly from disk, or verbatim relevant lines returned by a small model answering a question about the stored output, plus tools to open, list, and close documents.

Enables MCP clients to create and control persistent, PTY-backed terminal sessions on macOS: launch commands and interactive programs, read output incrementally via byte cursors, send keystrokes, wait on conditions, and detect running/awaiting-input/exited states. Sessions run inside a Seatbelt sandbox with command policies, human approvals, secret redaction, and hash-chained audit logging.

Enables an LLM to orchestrate multiple downstream MCP tools inside one isolated sandbox in a single turn, filtering intermediate results in memory and returning only the final output to cut context tokens.

Enables MCP clients such as ChatGPT to execute shell commands, manage files, and view or capture images on Mac and Linux hosts. Supports terminal-based connection approval, time-limited access, and output controls.

Enables Codex to delegate subtasks to concurrent background coding agents that can each run on any model provider supported by Pi, such as DeepSeek, Anthropic, Gemini, OpenRouter, or local models. Exposes MCP tools for listing models, spawning and waiting on agents, sending follow-ups, and aborting, backed by a live local web panel showing status, token usage, and streaming output.

Enables local MCP clients to expose and execute typed tools through a bounded native runtime with Ed25519 admission, per-session budgets, rate limits, schemas, and cached outputs.

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.