"Sway" matching MCP servers:

Enables semantic search and interaction with Fuel Network documentation and Sway Language resources within AI-powered development environments. It provides high-quality technical context using a local vector database to assist with smart contract development and FuelVM queries.

Enables provider-neutral automation of dedicated Linux desktop applications across private X11, KWin/Wayland, headless Chromium, and explicitly enrolled Sway sessions through MCP. It supports input, screenshots, window targeting, cancellation, timeouts, and crash recovery while reporting each backend's limits.

An MCP server implementing the ROBINS-I V2 framework for risk-of-bias assessment in non-randomized studies, with deterministic algorithms and full provenance. It enables users to parse study documents, specify target trial results, answer signalling questions with evidence-bound quotes, and compute or override domain judgements.

Enables automated assessment of research manuscripts against the TARGET reporting guideline for target trial emulation, providing item-by-item scoring with evidence and provenance.

Enables aggregating multiple MCP servers behind a single HTTP/SSE endpoint, with Code Mode to reduce token usage and support for OAuth and sandboxed execution.

Enables hot-swapping llama.cpp models in a running Claude Code session via launchctl or systemd, preserving conversation context across model changes.

Enables users to compare a supplier invoice with its purchase order and accepted receipts by exact SKU, unit price, and billed quantity, surfacing mismatches even when totals agree. It returns per-SKU evidence and source values for each exception.

Lets LLMs play a local Slay the Spire 2 installation by exposing game state, action help, and 29 gameplay actions through STDIO tools, with waiting, wiki lookups, and profile inspection.

MCP server for text-to-speech using macOS say command, enabling speech synthesis, audio file generation, and voice management.

Enables retrieval and structural analysis of FDA regulations.gov dockets: searching dockets, pulling comments and attachments into a local cache, extracting sectioned guidance text, and computing section-aligned draft-versus-final guidance diffs. All results are deterministic and cache-first, with no model calls in the server.

Enables text-to-speech functionality on macOS using the say command, offering extensive control over speech parameters like voice, rate, volume, and pitch for a customizable auditory experience.

Enables LLM agents to create circuit schematics and diagrams in Microsoft Visio through MCP tools for managing documents, pages, stencils, shapes, wires, and exports, with measured pin geometry for accurate component connections.

Enables engineers and AI assistants to search source-backed hardware design guidelines, retrieve detailed conditions and limitations, and trace citations to original sources, all through a read-only offline interface.

Enables scanning repositories for TODO and FIXME markers while avoiding false positives in strings and URLs, then reports each marker’s age, author, and staleness using git blame and history. It also counts suppression signals, long functions, and commented-out code inside real comments.

Enables AI agents to safely run test suites over MCP, returning concise JUnit-based results, trimmed tracebacks, rerun-failed support, and flaky-test detection while handling timeouts, process cleanup, and bounded output.

Enables an AI agent to inspect and safely edit local .ics calendar files, query agendas, find free/busy slots, detect overlaps, and handle time zones, DST, and recurrence rules.

Enables AI agents to inspect and safely edit Excel workbooks by distinguishing formulas from cached values, previewing changes with dry runs, detecting what a save would lose, and refusing unsafe writes.

Enables developers and agents to determine what licenses a project's dependencies use and whether shipping is permitted, combining SPDX parsing, installed metadata, lockfile readers, a compatibility table, and a policy engine whose verdicts always carry reasons.

Enables an AI agent to run read-only SQL over local CSV, Parquet, and JSON files through MCP tools, with directory sandboxing, statement gating, timeouts, and query timeouts that keep access confined to permitted folders. Results are shaped for small context windows with row caps, truncation notices, and markdown/CSV/JSON output.

Enables an AI agent to inspect images, resize and compress them to size budgets, strip EXIF/GPS metadata, generate thumbnails, and safely batch-process files inside a directory sandbox.

Enables an AI agent to inspect which process is listening on a local port and safely plan, confirm, and verify termination of that process across platforms.

Enables an agent to mine a repository's git history and answer questions a new teammate would ask: which files are riskiest based on churn, recency and author breadth, who actually knows each file based on surviving lines, which files secretly change together, which directories depend on one person, and what recent commits mean for release notes. All analysis runs through a read-only server sandboxed to a single directory.

Enables AI agents to compress videos to target sizes, create GIFs, cut clips, and preview exact ffmpeg commands before execution, with safe subprocess handling, progress reporting, cancellation, and dry runs.

Enables an AI to risk-review Terraform and OpenTofu plan files over MCP stdio by summarizing plans, ranking dangerous changes, diffing resources with secrets masked, and comparing two plans without running Terraform.

Local-first Sui review and evidence layer for AI clients. It enables users to review and approve Sui transactions in their own wallet after AI requests, without the AI having signing authority.

Enables AI agents to inspect git working trees and history for exposed credentials without letting raw secrets reach the model, with false-positive filtering, baseline support, and remediation guidance.

Enables Solana swaps through ranked quotes, transaction building, broadcasting, and status tracking, with per-request payment in USDC via the x402 protocol using a local keypair.

Enables an AI to statically audit GitHub Actions workflow files, parsing YAML with accurate line numbers and reporting findings about on: key quirks, expression injection risks, unpinned actions, effective token permissions, and cron scheduling.

Enables an AI agent to analyze browser HAR exports, break down request timing, identify dominant phases and critical request chains, render ASCII waterfalls, and safely redact secrets before analysis.

Non-custodial Solana swap routing with best-price execution, flat 0.25% fee, and built-in on-chain scam checking for token safety.

Enables agents to create, read, update, and validate editable analog/RF circuit schematic projects (including a five-transistor OTA template), wiring and moving components by pin name, running topology checks, exporting SVG or SPICE/Spectre netlists and normalized JSON, and opening the browser editor with a project loaded. It also exposes the component library's exact pins and defaults so drawings stay netlist-correct.

Enables an AI to statically lint Dockerfiles and compose files without Docker by parsing their true structure, reporting line-numbered findings with concrete fixes, and analyzing cache order, .dockerignore matching, and safe fix previews as diffs.

Enables agents to lint OpenAPI specifications and detect breaking changes between two versions of an API, normalising Swagger 2.0 and OpenAPI 3.0/3.1 into a single model with safe $ref resolution. It exposes schema-walking and example-validation tools over stdio, classifying each change as breaking, potentially breaking, or safe based on request-versus-response variance.

Enables an AI agent to search a folder of markdown notes, follow links and backlinks, and safely rename notes while rewriting every link to them.

Enables AI-assisted gameplay for Slay the Spire by reading game state and providing strategy advice or automated actions via Claude Code.