glm-orchestrator
Related Servers
Alternatives to glm-orchestrator
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceEnables MCP clients to connect to LLM/API services using the Model Context Protocol, providing real-time interaction and tool access. Also offers RESTful API endpoints via FastAPI for programmatic integration with existing systems.Apache 2.0
- FlicenseNot gradedqualityDmaintenanceLocal MCP server that exposes fixed tools for GPT, Claude, and Gemini while routing to any OpenAI-compatible chat completions backend with independent configuration per target.1-
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to use llama.cpp models via MCP protocol by bridging MCP requests to an OpenAI-compatible API.-

Local AI MCPofficial
AlicenseAqualityAmaintenanceUnified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.1646 npmCreative Commons Attribution Non Commercial No Derivatives 4.0 International- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that bridges MCP clients with local LLM services, enabling seamless integration with MCP-compatible applications through standard tools like chat completion, model listing, and health checks.-
- FlicenseCqualityDmaintenanceEnables MCP clients to interact with local LLMs via LM Studio, supporting dynamic chat, vision, RAG, file interaction, and model orchestration.28-
TDQS
Scored across 20 tools
Most tools are clearly separated by resource and action (plan, memory, git, skills, GLM runs). The only mild ambiguity is among glm_status, glm_result, and glm_wait, but their descriptions make the distinction reasonably explicit.
The snake_case verb_noun pattern is dominant and recognizable across all tool groups. Minor deviations like glm_models (noun-only) and the skills_list vs skill_read singular/plural mismatch prevent a perfect score.
Twenty tools is on the heavy side for a single server, even though the grouping into GLM lifecycle, memory, plan, git, and skills makes the set navigable. It falls into the 16–25 range where the tool count starts to feel like a burden rather than a curated surface.
Core workflows are well covered: GLM runs have create/status/result/cancel/wait/list/apply, memory has full lifecycle, skills are readable, and plan/git basics exist. Minor gaps include no plan editing/removal and no git diff/log, but these are workable or intentionally left to the user.