"Understanding Perplexity in Relation to Claude" matching MCP servers:

Enables MCP clients such as Claude Desktop to hand tasks to a running DeepSeek Harness window, where each task becomes a real session visible in the sidebar with a reusable session id. If the in-process plugin is unavailable, it falls back to running the task headless so the tool still returns a result.

Enables AI agents to maintain persistent, inspectable understanding through typed, revisable updates, and to coordinate multi-agent work via shared graph-based stigmergy.

MCP server that lets you drive Claude Code sessions hands-free by voice from any MCP client, enabling remote models to send prompts, monitor progress, and get results read back.

Enables Claude to use Google Gemini as a secondary AI through MCP for large-scale codebase analysis and complex reasoning tasks. Supports both Gemini Flash and Pro models with specialized functions for general queries and comprehensive code analysis.

Enables Claude Desktop and other AI tools to interact directly with Figma, allowing for powerful AI-assisted design capabilities through natural language commands.

Enables an Alexa+ host to place and manage customer-care calls by building a case, navigating phone menus, waiting on hold, explaining the issue, guarding sensitive disclosures, handing off identity checks, recording ticket numbers and promises, and scheduling follow-ups.

An MCP relay that adds a use_jev tool to every connected server, letting the Jev model autonomously select and execute tool calls while the calling model supplies any required text values. It enables agents to delegate multi-step tool use across all configured MCP servers through a single unified interface.

Enables Claude Code to delegate autonomous web browsing, deep research, and multi-tab management to a Comet browser session, with tools for asking questions, capturing screenshots, managing tabs, switching modes, and uploading files.

Interfaces with the Perplexity AI API to provide advanced question answering capabilities through the standardized Model Context Protocol, supporting multiple Perplexity models.

Enables MCP clients such as Cursor to hand a bounded task to a scoped, non-interactive Claude Code session billed to a Claude subscription rather than Cursor model credits. Runs read-only by default, with optional file edits or Bash, plus budget, timeout, and session-resume controls.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Wraps the Claude Agent SDK as MCP servers, letting you spawn multiple specialized Claude Code agents — each with its own model, tools, system prompt, and personality — from any MCP client.

Enables Claude Code sessions to communicate with each other, allowing discovery, messaging, and synchronous queries across sessions.

Self-improving learning engine for Claude Code. Extracts signals from sessions (corrections, successes,confusion), runs periodic reflections, and evolves behavioral frameworks through evidence. 9 MCP tools, automatichooks, local-only.

Multi-agent AI consultation framework for Claude Code via MCP — get second opinions from OpenAI, Gemini, Qwen, DeepSeek

A fire-and-poll MCP server that lets Claude Code run long background jobs without hitting tool-call timeouts.

Lets Claude Desktop and Claude Code inspect and drive Windows desktop applications in the background, including clicking, typing, launching, and verifying results, while the user keeps their mouse, keyboard, and foreground window.

MCP server for orchestrating multiple Claude Code instances via tmux, enabling spawning, reading, sending, listing, and killing sessions.

An autonomous MCP server that uses the Claude Code CLI to solve coding problems without permission prompts.

One-pass agentic inbox triage as an MCP server: fetch unread Gmail → classify (action_needed/fyi/newsletter/noise) → summarize → extract tasks → draft replies as Gmail DRAFTS (never sends) → flag calendar → write a triage report. Four stdio tools (fetch_emails, save_gmail_draft, append_tasks, write_report); the host is the LLM, so it runs keyless in Claude Code. Gmail scopes: readonly + compose

A Model Context Protocol server that converts Markdown content to HTML format.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Enables Claude Code to retain persistent cross-session memory with semantic search, automatically tracking user corrections as behavioral patterns that move through lifecycle stages. It also extracts signals from every session to evolve and promote behavioral frameworks, giving the assistant developing judgment over time.

Enables Claude Code sessions to persist identity and cross-session memory through a local SQLite store with semantic search, so past facts, decisions, and lessons can be recalled by meaning. It also detects and classifies user corrections into behavioral patterns that progress from new to internalized, letting reflection cycles evolve skills that work over time.

Enables voice-driven software development by bridging the Claude app's voice mode to Claude Code, allowing users to direct repository work through natural language while requiring approval before any write or shell execution.

Enables networked Claude-to-Claude messaging over HTTP and MCP channels, allowing direct messages, broadcasts, threaded replies, and permission approvals among Claude Code instances.

Gives Claude Code persistent memory across sessions with semantic search, tracks and classifies user corrections to surface behavioral patterns, and evolves behavioral frameworks over time based on accumulated evidence. Runs entirely locally through 15 MCP tools and hooks, requiring no API key or cloud service.

Enables users to request a second opinion from a locally authenticated Claude Code model via MCP tools, supporting asynchronous jobs with restricted tools for safety.

Enables Claude Code to retain persistent identity and cross-session memory, storing facts, decisions, and lessons in a local searchable database that can be queried semantically by meaning. It also detects and classifies user corrections over time, tracking behavioral patterns through lifecycle stages so repeatedly confirmed working practices are promoted and failures retired.

Gives Claude Code persistent memory across sessions, detecting and classifying user corrections, and evolving behavioral frameworks from accumulated evidence. Exposes 15 MCP tools for semantic memory search, signal recording, self-evaluation, and reflection cycles that run locally alongside automatic hooks.