Tools & Project Memory
Conventions & Content Tools
Section titled “Conventions & Content Tools”| Tool | Purpose |
|---|---|
get_conventions | Returns universal architecture rules, MCP toolchain usage, and communication style |
list_commands | Lists all available workflow commands with descriptions |
list_agents | Lists all available agent profiles |
activate_agent("<name>") | Activates a platform or cross-cutting agent, loading its full knowledge into context |
list_skills | Lists all available domain-knowledge skills |
get_skill("<name>") | Loads a specific skill’s full content |
get_skill_reference("<name>", "<ref>") | Loads a detailed reference document linked from a skill |
search_content | Full-text keyword search across conventions, commands, and skills |
suggest_next | Recommends the next command based on project command history |
version | Returns the current dev-mcp server version |
Project Memory
Section titled “Project Memory”Project memory persists context across sessions per project. Notes, command history, and project state are tracked automatically.
Requires x-project-id header in .mcp.json — set during /setup.
| Tool | Purpose |
|---|---|
get_project_context | Load project identity, saved notes, and command history at the start of a session |
save_project_note(key, value) | Save a note — token decisions, component APIs, client preferences, environment details |
get_project_note(key) | Retrieve a saved note |
list_project_notes | See all saved notes for the current project |
delete_project_note(key) | Delete a note from project memory |
What to Save
Section titled “What to Save”- Agent name (saved automatically by
/setup) - Client preferences and decisions
- Environment details (store URL, API keys, deployment targets)
- Design decisions that aren’t captured in CONVENTIONS.md
- Known issues or workarounds
Command History
Section titled “Command History”Every run_command call is automatically tracked per project — command name, last run timestamp, run count. This powers suggest_next recommendations.