Arch
Related Servers
Alternatives to Arch
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceAn MCP-native agentic platform orchestrating planner/executor/critic agents over hybrid RAG with three-tier memory, budget enforcement, safety guardrails, and full observability. It exposes all capabilities as MCP tools, enabling natural-language control of document ingestion, retrieval-augmented generation, and multi-step AI workflows.MIT
- AlicenseNot gradedqualityBmaintenanceEnables running durable, traceable AI agents via LangGraph through a universal MCP interface, integrating with Hatchet for orchestration, logging, and retries. Provides tools for knowledge management (ingestion, RAG) and Kubernetes operations (diagnosis, auto-fix).MIT
- AlicenseNot gradedqualityDmaintenanceProvides AI agents with operational customer context, including typed revenue objects, persistent state, scoped tools, and human-in-the-loop handoffs through MCP, REST, and CLI.012Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables autonomous orchestration of vector search, knowledge graph queries, and web crawling through a single MCP interface, providing agentic RAG capabilities for AI assistants.8MIT
- AlicenseAqualityAmaintenanceEnables MCP clients to manage and orchestrate autonomous agents, budgets, and multi-agent workflows within the OpenMesha agentic operating system.91Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides unified AI agent observability including tracing, cost tracking, performance monitoring, anomaly detection, and audit trails via MCP.31 npmMIT
TDQS
Scored across 45 tools
Many tools have distinct purposes, but there is notable overlap: debug_diagnose_transcript is an alias for debug_why_transcript_failed, and several debug_* tools (traces, session_history, get_current_state) have overlapping scopes. An agent could misselect between debug_analyze_session and debug_diagnose, or between debug_session and debug_list_active_sessions.
Naming uses clear prefixes (debug_, platform_, agent_) that group tools by domain, but there are deviations: agent_tables lacks a prefix, platform_project_builder and platform_project_builder_operations are confusingly similar, and some tools like debug_harness_logs use debug_ despite being evaluation-related. The pattern is readable but not fully uniform.
With 45 tools, the surface is heavily oversized for even a comprehensive platform. The count exceeds the 25+ threshold that indicates bloat, and many tools expose multiple actions internally (e.g., agent_tables has 13 actions, platform_workflows has 9), making the actual surface much larger than the tool count suggests.
The tool set covers an impressively broad domain: debugging sessions, project lifecycle, agents, versions, deployments, evals, and package validation. There are minor redundancies (the alias tool) and some potential gaps (e.g., no explicit tool for managing users/permissions beyond workspaces), but overall the surface appears complete for the stated Arch platform purpose.