F
licenseA
qualityC
maintenanceLocal MCP server that enables delegating low-risk tasks like summarization or code patches to a low-cost model, with the main agent reviewing results.
2
-
frx-director-mcp
Related Servers
Alternatives to frx-director-mcp
No user-submitted related servers found.
Related Servers
- FlicenseBqualityBmaintenanceMCP server that enables AI agents to drive your real, logged-in browser via accessibility snapshots, with hardened credential brokering and local workflow memory.5394 npm-
- AlicenseNot gradedqualityCmaintenanceMCP server that enables delegation of small coding implementations to a cheaper language model with propose_patch and apply_patch tools, while the primary agent retains architecture, review, and approval.MIT
- AlicenseNot gradedqualityDmaintenanceA local, privacy-first MCP server that orchestrates Ghidra, Binary Ninja, x64dbg, and system tools to provide AI assistants with powerful binary analysis capabilities.Academic Free v1.1
- AlicenseBqualityBmaintenanceA CDP-native MCP server that lets AI agents drive a real Chrome browser with deep network/console inspection, robust page interaction, and the ability to reverse-engineer a site's API flow into runnable code with dependency chaining and replay verification.52223 npm3MIT
- AlicenseNot gradedqualityAmaintenanceMCP server that gives any LLM a managed Docker workspace with live browser, terminal, code execution, document skills, and autonomous sub-agents.2,741 npm123MIT
TDQS
B3.4/5.0
Scored across 23 tools
Disambiguation4/5
The two main families (frx_env_* and agent_*) are clearly separated, and each tool maps to a distinct action or resource. The read/wait family (agent_poll, agent_wait_for_stop, agent_read, agent_read_brief, agent_state, agent_runlog) has subtle differences, but the descriptions are detailed enough to avoid serious misselection.
Naming Consistency4/5
The frx_ and agent_ prefixes create strong, predictable groups, and most tools use a clear verb-first pattern like frx_env_create, frx_env_delete, agent_start, and agent_send. A few noun-style names (frx_status, agent_state, agent_runlog, agent_tools) and the longer frx_page_automation_scan break the strict verb_noun pattern, but overall the convention remains consistent.
Tool Count3/5
At 23 tools, this is on the heavy side and sits in the 16-25 range that feels bloated. The tools do cover two distinct subdomains (environment lifecycle and agent orchestration), but the set would be tighter with fewer read-state variants or by merging some convenience wrappers.
Completeness4/5
Environment lifecycle coverage is strong: create, list, open, close, rename, delete, and import. Agent orchestration is also well covered with start, poll, read, send, stop, mode switching, run logs, and direct tool invocation. Minor gaps like environment export or an explicit session teardown tool can be worked around, so no critical dead ends exist.
Maintenance
ActivityMaintained
ResponsivenessUnresponsive