F
licenseNot graded
qualityC
maintenanceConverts any MCP server into simple HTTP endpoints, enabling AI agents that only support HTTP (like ChatGPT Custom GPT or web_fetch) to use MCP tools.
-
deer-flow-mcp
by axsapronov
Related Servers
Alternatives to deer-flow-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceExposes local Flowise chatflows as MCP tools, enabling listing and running chatflows from any MCP client.211 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables remote MCP access to tools for URL-to-markdown conversion, web and image search, academic search, embeddings, reranking, classification, deduplication, and PDF extraction.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables 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.2MIT
- AlicenseBqualityCmaintenanceExposes your LLMGraph workflow deployments as MCP tools, allowing AI assistants to invoke them via natural language.127 npmMIT
- FlicenseNot gradedqualityCmaintenanceA remote MCP server deployed on Cloudflare Workers without authentication. Enables connecting MCP tools from AI Playground or Claude Desktop.-
TDQS
A4.1/5.0
Scored across 11 tools
Disambiguation4/5
Most tools target distinct lifecycle stages, but deerflow_run_status, deerflow_run_progress, and deerflow_wait_activity all revolve around checking run state and overlap in returned data (status, counters, activity). The descriptions do provide clear usage guidance, distinguishing polling, detailed progress, and blocking waits, so confusion is limited but possible. deerflow_research and deerflow_chat also both start runs, though the fresh-thread deep-research vs. continuation-chat distinction is clear.
Naming Consistency5/5
Every tool uses the same deerflow_ prefix and snake_case, with predictable action-oriented names like get_report, list_threads, cancel_run, and wait_activity. The only minor variation is research/chat lacking an explicit object noun, but the pattern remains overwhelmingly consistent and readable.
Tool Count5/5
Eleven tools is well within the ideal 3-15 range and maps tightly to the deep-research lifecycle: starting runs, monitoring them, retrieving reports/artifacts, listing threads/models, and cancelling work. Each tool has a clear role, and no tool feels redundant or trivial.
Completeness4/5
The lifecycle is well covered: start research/chat, monitor status/progress/wait, cancel, fetch reports, list/get artifacts, and list threads/models. Minor gaps include no operation to delete threads/artifacts or fetch full details for a single thread beyond list output, but agents can work around these in most workflows.
Maintenance
ActivityMaintained
ResponsivenessNo issues