Planning and orchestration for AI-driven software development
Planning and orchestration for AI-driven software development
AgentPM is a planning and orchestration system for AI-driven software development. Installed locally as an MCP server, it integrates with any IDE that supports Anthropic's Model Context Protocol specification, including Cursor, Augment, VS Code Copilot, Cline and Roo.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_all | Returns all tasks, optionally filtered by status |
| get_single | Returns a specific task by ID |
| get_next | Returns the next task to work on based on dependencies and status |
| filter_by_status | Returns tasks filtered by status |
| filter_by_priority | Returns tasks filtered by priority |
| create | Creates a new task with the specified properties |
| update | Updates an existing task with new information |
| update_status | Changes the status of one or more tasks |
| delete | Removes a task from the project |
| add_subtask | Adds a subtask to an existing task |
| remove_subtask | Removes a subtask from a task |
| clear_subtasks | Removes all subtasks from one or more tasks |
| expand | Breaks down a task into subtasks using AI |
| expand_all | Expands all pending tasks into subtasks using AI |
| action | The specific action to perform |
| projectRoot | Root directory of the project |
| Action | specific data (task, dependency task, validation results, fix results) |
| Constraints | Limitations, requirements, and boundaries |
| Technologies | Technical stack and tools |
| Features | Detailed functionality requirements |
| Review | Final confirmation and adjustments |
| add | Adds a dependency between two tasks |
| remove | Removes a dependency between two tasks |
| validate | Checks for dependency issues (circular references, missing dependencies) |
| fix | Automatically fixes dependency issues |
| markdownOutput | "apm-artifacts/resources/reports/task-complexity-report.md" |
| threshold | 5 (tasks with complexity ≥ 5 will be recommended for expansion) |
| research | false (whether to use Perplexity AI for research-backed analysis) |
| Task | specific analysis (ID, title, complexity score, recommended subtasks) |
| Metadata | generation timestamp, threshold, task counts, average complexity) |
| apm_project_brief_status | |
| apm_project_brief_result |
{
"mcpServers": {
"agent-pm": {
"command": "npx",
"args": [
"-y",
"@gannonh/agent-pm@latest"
],
"env": {
"PROJECT_ROOT": "/path/to/project/root/",
"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY",
"PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| PROJECT_ROOT | Declared in the maintainer’s client configuration. | Check documentation |
| ANTHROPIC_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| PERPLEXITY_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
One workspace for every AI coding assistant. Shared tasks, memory, and governance.
Chronos Protocol transforms AI development workflows by eliminating temporal blindness in automated systems. The MCP server provides complete
🆕 Looking for persistent memory for Claude Code? Check out memsearch Claude Code plugin — a markdown-first memory system that gives your AI agent long-term memory across sessions.
Eventually I came down to this solution: - It uses in-memory semantic search to find relevant Api endpoints by natural language (such as list