"Eight Sleep" matching MCP servers:

Stop hallucinating numbers. An MCP server that runs every math expression through four independent numeric engines in parallel and returns all four results side by side — so when they disagree, you know the answer is numerically unreliable.

An MCP control plane for Codex native sessions, translating eight explicit operations with strict security boundaries for authenticated access through OpenAI Secure MCP Tunnel.

Local-first persistent memory for coding agents and MCP clients. It keeps important project context across sessions and reduces wasted tokens by retrieving only relevant memories instead of replaying unnecessary history.

A specialized MCP server for detailed control of Home Assistant lights, supporting advanced features like RGB colors, color temperatures, effects, and robust scene management. It includes specific fixes for IKEA Tradfri devices and intentionally focuses on lights only to ensure home safety.

Provides persistent, searchable memory for AI agents across any MCP-compatible client, storing project context, user preferences, and session learnings locally in SQLite with tools to save, retrieve, search, and manage them.

Enables cross-harness host inspection, profile persistence, and execution configuration, with safe preview, apply, and validation of configuration changes.

Generates harmonious color schemes for design projects using The Color API, offering eight different palette generation methods including monochrome, analogic, complement, triad, and quad schemes.

MCP server for searching Stack Overflow questions and retrieving answers with body content, supporting advanced filters and multiple transport types.

A hybrid MCP server that allows users to manage tasks through Claude Desktop or Claude Web using a NestJS API. It provides eight tools for creating, updating, listing, and tracking statistics for personal tasks.

Enables MCP clients to turn plain-language mobile app descriptions into rendered, editable screens and project links for exporting to Figma, HTML, or React.

Exposes eight mmap_* tools that let an agent declare a system's ghost dependency design first, then light each node up as it is built and verified, with downward-only edges and evidence-backed green status. Clients get a live ledger of what exists, what is in progress right now, and which foundation has cracked.

Other PDF MCP servers ask you to install Chrome, manage a local renderer, and ship templates yourself. Kamy MCP is a hosted endpoint — point any MCP client at https://mcp.kamy.dev/mcp, paste an API key, and start asking your AI to "generate an invoice for Acme Corp". Eight production-ready templates ship with the service (invoice, quote, receipt, contract, agreement, certificate, report, shipping-

Enables coding agents to declare an entire system design up front as ghost nodes, then light each node up as it is built and test-verified, exposing a live layered dependency graph in a terminal pane beside the conversation. Structural corruption such as upward-pointing edges is refused, while progress and broken foundations stay visible through eight mmap_* tools.

A dual-transport MCP server enabling anonymous free web search via Parallel (default) or Exa (backup), with no API keys or DSH dependency, for Claude Code, Codex, and any MCP client.

Provides deterministic Unicode 17 text integrity operations—inspection, normalization, comparison, transcoding, security observation, difference explanation, indexing, and protocol profiles—over explicit strings and byte arrays via eight read-only MCP tools.

Exposes read-only Huly task intake, architecture guidance, UX patterns, and static validators through eight MCP tools, letting host agents drive approval-gated Flutter and Frappe delivery workflows. It can also be inspected directly (e.g. via the MCP inspector) so users can exercise the tools without an agent.

Exposes eight mmap_* tools that let a coding agent declare a whole layered dependency design as ghost nodes, then light nodes through building and verification while a live terminal pane shows the map. The server also tracks status such as in-progress spinners, verified-green nodes, and red cracked foundations.

Lets an AI coding agent declare a system's layered dependency graph up front as ghost nodes, then light each node up as code is built and verified, with a live terminal pane showing spinners on active work and red on cracked foundations. It exposes eight mmap_* tools so structural rules — downward-only edges and unique ranks — are enforced as the design ledger.

Enables AI coding agents to declare and maintain a live, layered dependency map during bottom-up development, exposing eight mmap_* tools that ghost the intended design first and then light nodes up as they are built and verified in a terminal pane beside the conversation.

Provides eight stdio tools for capturing source snippets and direct Python dependency witnesses, verifying code evidence after edits, repairing citations, and producing reuse, repair, review, or retrieve decisions.