omnara
OfficialRelated Servers
Alternatives to omnara
No user-submitted related servers found.
Related Servers
- AlicenseAqualityDmaintenanceStart, observe, and interact with Claude Managed Agents from any MCP client — launch an agent, watch its events, reply, approve the tools it wants to run, and stop it. Runs over stdio, HTTP, or AWS Lambda with pluggable auth.171MIT
- AlicenseAqualityAmaintenanceThe infrastructure for AI teams: a self-hosted server that gives a fleet of agents shared semantic memory, tasks, direct messages, and session handoff. Any agent that speaks HTTP participates: Claude Code, AutoGen, raw API scripts, anything.479MIT
- AlicenseBqualityDmaintenanceagent-mq is a message queue that enables AI coding agents to communicate with each other across sessions and machines. Agents can send messages, delegate tasks, and coordinate work — all through MCP tools. Supports Claude Code, Cursor, Codex, OpenClaw, and any MCP-compatible tool. UUID-based authentication with per-user data isolation. Self-hostable with Docker.72MIT
- AlicenseNot gradedqualityAmaintenanceConnects your own Claude subscription to applications via an OpenAI-compatible API, adding durable job queues, workflows, subagents, and a local management console.Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables deployment of autonomous AI agents with memory and tool execution capabilities through a WebSocket-based MCP protocol. Provides production-ready infrastructure with REST API access, persistent state management, and extensible function registry for building self-hosted AI systems.-
- AlicenseAqualityDmaintenanceMulti-agent orchestration server that enables parallel task delegation, sequential pipelines, cron scheduling, and cross-model peer review via CLI providers like Codex, Antigravity, OpenCode, and Claude Code.427 npm6MIT
TDQS
Scored across 75 tools
The set contains many parallel tool pairs such as models_delete vs grant_models_delete, pools_delete vs grant_pools_delete, and secrets_create vs grant_secrets_add, which could cause misselection without careful reading. Descriptions clarify boundaries, but the sheer number of tools with grant/non-grant and resource/action variations creates moderate ambiguity.
Nearly all tool names use snake_case with a resource-first pattern (e.g., agents_get, models_create, grant_pools_add), which is predictable and readable. Minor deviations exist: grants use add/edit while base resources use create/update, and a few tools like whoami or profiles_rename break the verb pattern.
75 tools is an extreme mismatch for a single MCP server. While the domain is broad, this count far exceeds typical well-scoped ranges (3–15) and is likely to overwhelm an agent's selection process.
Core resources like secrets, machines, pools, crons, and grants have near-complete CRUD coverage. However, notable gaps exist: no configs_list/update/delete, no projects_get/update/delete, no skills_create, and no models_get, which will limit several agent workflows.