lightbulb-mcp
Related Servers
Alternatives to lightbulb-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityFmaintenanceMCP server for running external coding agents as background tasks inside Claude Code. Supports multiple backends including Codex, Grok, GLM, DeepSeek, and more.7MIT
- AlicenseAqualityDmaintenanceMCP server that bridges OpenAI's Agents SDK with Claude Code, enabling web search, file search, and computer use capabilities directly in your development environment.29 npm1MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that lets Claude Code or any MCP client delegate coding tasks to the local Cursor Agent CLI, with persistent per-workspace sessions and tools for diffing and pushing changes.12 npmMIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server wrapping the Cursor CLI agent, enabling Claude Code and other MCP clients to delegate tasks to Cursor's AI agent for file writing, bash commands, and codebase queries.-
- AlicenseNot gradedqualityDmaintenanceMCP server that enables Claude Code to communicate with other Claude Code agents over HTTP, allowing users to ask questions about remote codebases or delegate coding tasks.MIT
- AlicenseAqualityBmaintenanceCode intelligence MCP server for Claude Code providing multi-project code graph, semantic search, session history, knowledge base, and web search.154MIT
TDQS
Scored across 1750 tools
Hundreds of tools overlap in purpose: the same domain actions appear as both <domain>_<action> and generic dispatch_domain_agent, Salesforce actions are duplicated with and without the connector_ prefix, and document/Stripe operations exist in several parallel surfaces (search_documents vs document_intelligence_search_documents, stripe_dispatch vs stripe_raw_api_request). An agent would frequently misselect among these near-duplicates.
All names are snake_case, but the pattern is not consistent: some are verb_noun (list_workflows, create_company), some are noun-centric (company_reviews, stripe_dispatch), some are provider_operation (clio_create_matter), and some add a connector_ prefix to already existing tools (connector_salesforce_bulk_ingest_close). It is readable in clusters but there is no single predictable convention across the set.
1750 tools is an extreme mismatch for any coherent MCP surface. Even a platform with many domains cannot be meaningfully navigated by an agent at this size, and no reasonable scoping guideline is approached.
Coverage is extensive across companies, domains, connectors, workflows, and memory context, and generic escape hatches (dispatch_domain_agent, invoke_tool, ask_document_agent) fill some gaps. However, many connector surfaces expose only read/list operations without matching writes, and the enormous, partially duplicated toolset makes it difficult to verify coherent lifecycle coverage for any given domain.