"Headroom open-notebook resources" matching MCP servers:

Discover and connect your agents with other agents via A2A protocol. Share resources for free or fee.

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.

A registry that enables MCP clients to discover and install MCP servers.

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

Enables Claude to delegate web search, page reading, text drafting, and parallel multi-model image generation to cheaper helper models on any OpenAI-compatible backend. Claude stays in charge of planning and final decisions while consuming fewer of its own tokens.

Routes every Claude Code/Hermes prompt through a local LLM planner and Open-Jev probe, injecting calibrated probability context while failing open if local services are unavailable.

Open source MCP server for Vectara

Open source contribution manager — tracks PRs across repos, discovers contributable issues, diagnoses CI failures, and drafts maintainer responses. 21 MCP tools, 5 resources, 3 prompts. Ships as CLI, MCP server, and Claude Code plugin.

This MCP server gives AI coding agents continuous self-awareness of their remaining Google Antigravity quota across both 5-hour rolling and weekly entitlement windows, plus live session token consumption and context pressure for the active conversation. It enables agents to probe headroom between tool steps, checkpoint work gracefully before hitting rate limits, and govern subagent model choice — all at zero LLM token cost.

Connects Claude Code and Codex to Jev-compatible System One services for context compaction, completion verification, and decision tasks like screening, classification, and gating.

The first open catalog and community for AI agents. Register, search, share skills, find partners. REST API + MCP. Free and open forever. First Czech MCP server included.

Enables deploying applications and managing cloud resources in Timeweb Cloud through natural language.

Steers a coding model through a 0→10 step reasoning protocol by injecting a directive into the system prompt before inference, and hooks refusals to retry the request with a reframe and rotate to an open-weight model. Exposes tools, prompts, and resources for traffic-light state, history, health, and configuration over stdio, Streamable HTTP, or a Cloudflare Worker.

A ready-to-use starter implementation of the Model Context Protocol (MCP) server that enables applications to provide standardized context for LLMs with sample resources, tools, and prompts.

A Model Context Protocol server that provides Coze resources and tools for managing workspaces, bots, and conversations.

Open-source shared rooms for AI agent conversations across Claude Code, Codex, Pi, OpenCode, and DeepSeek Harness. The Apache-2.0 core provides messaging, room history, MCP integrations, and self-hosting on Cloudflare.

Connects AI assistants to the Opsenes platform, exposing its capabilities as MCP tools, resources, and prompts for safe platform operations.

Enables federated search across public ARD registries and a verified index of MCP tools read from each server's own tools/list, with hybrid lexical and semantic retrieval. It lets agents discover and connect to resources at runtime without hard-coded integrations.

Open source AI agent platform with MCP server, browser automation, knowledge packs, and workflow engine. Works with Claude Code, ChatGPT, Cursor, and any MCP client.

Enables multiple MCP agents to read and write a single user-controlled, local-first fact layer under one user identity with explicit scopes, preserving sources, versions, permissions, and audit history. Supports structured memories such as preferences, facts, task state, and decisions, plus structured handoff capsules so one agent can resume another's work by task ID.

Enables clients to connect to and manage multiple backend Model Context Protocol servers, aggregating their tools and resources and exposing them through a unified SSE, Streamable HTTP, or Stdio interface.

Enables AI coding agents to check real subscription usage limits and get a go, wait, or reroute decision before starting work.

Proxy that aggregates multiple MCP servers and presents them as a unified interface, allowing clients to access resources from multiple servers transparently.

Enables developers to expose custom tools, prompts, and resources to MCP clients from a stateless App Router route handler. Serves the current 2026-07-28 protocol natively while a compatibility layer supports 2025-era Streamable HTTP clients.

Enables AI agents to file review jobs that real human reviewers open, return pinned comments and verdicts on, and approve, so agents can iterate on built sites, videos, and other artifacts based on genuine human feedback.

Enables AI tools to uniformly discover, inspect, and call tools, prompts, and resources from multiple upstream MCP servers through a small set of fixed MCP tools, over stdio or HTTP.

An open-source MCP server that turns real business workflows into reviewed, agent-callable commands, enabling safe execution through REST and MCP.

Ultra-lightweight MCP server for Bun with full protocol compliance. Enables building MCP servers with tools, resources, and prompts using minimal dependencies and heap footprint.

Enables browsers to act as MCP servers by relaying tools, resources, and prompts to AI agents via a WebSocket-to-stdio bridge.

Enables AI agents and IDEs to discover, install, and execute skills over Model Context Protocol via stdio or SSE, with semantic search and framework bridges.