Fcop
Coordination middleware for file-based multi-agent workflows. Exposes 45 tools across three tiers (L1/L2/L3) that implement the FCoP 3.2.5 protocol: directories as state machines (inbox, active, review, done, archive), filenames as routing headers (TASK/REPORT/ISSUE/REVIEW), and atomic os.rename() as the only sync primitive. The server provides init_project, create_custom_team, lifecycle transitions, and event history commands. Reach for this when you want multiple AI agents (Cursor, Claude Desktop, or any MCP client) to collaborate on tasks without message queues or databases. The entire system state lives in a git-trackable folder structure. You can ls your way through agent handoffs and review chains.
- GitHub stars
- 4
- tools
- 6
- transport
- STDIO
- env var
- 1
- last updated
- Sep 30, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
init_workspaceInitialize a new workspace with `init_workspace()`.
Initialize a new workspace with `init_workspace()`.
No parameter schema in public metadata yet.
create_taskUse its `workspace_id` and a unique `operation_id` with `create_task`, then inspect the TASK.
Use its `workspace_id` and a unique `operation_id` with `create_task`, then inspect the TASK.
No parameter schema in public metadata yet.
inspect_taskInspect the TASK with `inspect_task(task_id=...)`.
Inspect the TASK with `inspect_task(task_id=...)`.
No parameter schema in public metadata yet.
create_branch4.0.1 introduced `create_branch`, `inspect_family` and `merge_branches`.
4.0.1 introduced `create_branch`, `inspect_family` and `merge_branches`.
No parameter schema in public metadata yet.
inspect_family4.0.1 introduced `create_branch`, `inspect_family` and `merge_branches`.
4.0.1 introduced `create_branch`, `inspect_family` and `merge_branches`.
No parameter schema in public metadata yet.
merge_branches4.0.1 introduced `create_branch`, `inspect_family` and `merge_branches`.
4.0.1 introduced `create_branch`, `inspect_family` and `merge_branches`.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
FCOP_PROJECT_DIRAbsolute path to your project root (optional, auto-detected if omitted).
Readme
FCoP — File-based Coordination Protocol
Let multiple agents work as a team. Keep tasks and deliveries in files.
New session, same project explanation? An agent says “done”, but where is the delivery record? FCoP keeps assignments, results, problems and reviews in your project's Markdown files, so people and the next agent can inspect the work and continue.
Multi-agent collaboration · Files as protocol · No complex infrastructure · Agent governance
协议原文：中文 · Specification: English · English · 简体中文 · Homepage
Details
- Repository
- github.com/joinwell52-ai/fcop
- Category
- AI & LLM Tools
- Package
fcop-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Penfield Memorypenfieldlabs/penfield-mcpPersistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.4stars
Tessera MCP Servertessera-llm/mcp-serverMCP server for Tessera's LLM cost-optimization layer: anchored spend, drift, recommendations.0stars
Mcp Serveragentled/mcp-serverIntelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits.0stars
Adaptive Recallaiappsapi/adaptive-recallAdaptive memory system with cognitive scoring, knowledge graph, and self-improving ML.3stars
Risk Deskiman/agent-driven-risk-desk-and-skillsPortfolio risk from supplied data or a synthetic example: VaR, ES, stress, credit, FRTB.0stars