"Threads" matching MCP servers:

Enables peer-to-peer asynchronous conversation between Claude.ai and Claude Code instances via a shared file-based notebook, allowing them to leave messages, start threads, and organize by project.

An MCP server that enables a supervising OpenAI Codex agent to delegate bounded implementation tasks to isolated worker threads with enforced file scopes and verification, optionally running in parallel git worktrees.

Enables MCP clients to create, read, message, wait for, interrupt, and settle persistent peer threads through an existing T3 Code server, keeping them visible across its clients. It supports project-scoped coordination with source attribution and retry-safe commands.

MCP server for interacting with a running T3 Code instance. Enables viewing agent threads, sending messages, and approving permission requests from Claude Code or voice-controlled models.

A TypeScript MCP server that integrates Devin AI with Slack, allowing users to create Devin sessions, post tasks to Slack channels, and maintain thread context between Devin sessions and Slack threads.

MCP server for Huddo, a group chat where people and AI agents talk in the same room. Lets an agent join rooms by invite link, read and send messages, reply in threads, whisper to one member, pair with its human, and wait for new messages.

A Model Context Protocol server implementation that enables AI assistants to interact with Slack workspaces, allowing them to browse channels, send messages, reply to threads, add reactions, and retrieve user information.

Enables MCP clients to safely interact with a locally installed Freebuff Desktop orchestrator, providing verified read access to projects, threads, messages, and project files while keeping credentials local and write operations read-only when unsupported.

Production-oriented MCP gateway for managing Codex through a persistent codex app-server process, supporting threads, autonomous goals, approvals, and HTTP/stdio transports.

Deterministic MCP control plane for native Codex subagents, providing durable state, policy gates, budgets, artifacts, evidence workflow, and recovery for Sol/Terra/Luna hierarchical agent threads.

Enables creators to connect their social channels so AI assistants can read their published Instagram, TikTok, YouTube, LinkedIn and Threads history, including posts, metrics, transcripts, comments and audience data, then use bundled skills to plan next posts, research creators, maintain brand docs, manage product catalogues and find outreach targets.

Enables any agent to spawn and manage T3 Code agent threads over HTTP MCP — starting research or coding agents, sending follow-ups, waiting for results, and answering approval prompts. It pairs once as a T3 device, exposes 15 tools, and keeps operations retry-safe.

Lets coding agents create and manage threads in a running T3 Code server over MCP.

Enables external clients to read authorized projects and threads and, with passkey-approved leases, perform write operations across multiple explicit environments.

A task orchestration system for AI agent teams that provides a Kanban dashboard and 12 MCP tools to manage multi-step workflows with DAG dependencies. It enables agents to coordinate through task threads, automated retries, and real-time webhook notifications.

Enables ChatGPT to supervise and control local Codex runtime sessions through a secure MCP interface, managing threads, turns, approvals, events, and recovery without exposing direct file, shell, Git, SSH, or model loop access.

MCP server for Rivendell, a workspace where AI agents collaborate on threaded discussions with resolutions. Provides tools for agents to create threads, reply with structured verdicts, and manage project context.

Enables AI agents to read and interact with the target5.net board, including listing problems, reading threads, registering identities, and posting replies, with the board's rules enforced and embedded into every tool.

Enables any agent to send a message by name into a live chat or another agent's conversation, and to receive replies by long-polling an inbox cursor that yields each message exactly once, in order, in roughly a tenth of a second. Also lets agents discover reachable chats, threads, and registered agents, with unresolvable names optionally routed to a relay agent for delivery.

A personal MCP bridge that lets ChatGPT drive a local Codex CLI, translating instructions into Codex app-server threads and returning compact summaries of what Codex did.