create_project_intelligence_cacheLABSCO SUMMARY
A cache is only worth loading if you know it is still true.
The interesting part is not the write, it is validate_project_intelligence_cache and invalidate_project_cache — a stale picture of a codebase is worse than no picture, because the assistant acts confidently on it. Treat the validate call as part of the load ritual rather than an optional extra. Note the platform line before you commit: this is built and supported on macOS, with Linux flagged experimental.
What it is
A project-context cache for Claude Desktop. It captures an understanding of a codebase — architecture, technologies, momentum, next steps — into a Memory MCP entry, so a later session loads that entry instead of re-exploring the repository. Around it sits a session-rules engine and coordination across Memory, Filesystem, Git, Claudepoint and database MCPs.
What you get
create_project_intelligence_cachewrites the current understanding of a project into Memory MCPload_project_intelligence_cachereads it back at the start of a sessionvalidate_project_intelligence_cachechecks whether the cached picture still matches the projectrefresh_project_intelligenceupdates a cache after the project has moved oninvalidate_project_cachedrops one when it can no longer be trusted- A session-rules engine with enforcement levels from
hard_blockdown tolog_only, so a rule can stop an action or merely record it - Project directories are auto-detected across the common layouts —
~/Projects/,~/Developer/,~/Code/,~/RiderProjects/and others
Requirements
Node.js 18.0.0 or higher and npm 8.0.0 or higher, plus Claude Desktop. Published as conversation-continuity-mcp version 1.0.0. Two MCP dependencies are installed for you: @modelcontextprotocol/server-memory and @modelcontextprotocol/server-filesystem. It needs read and write access to your project directories and to ~/Library/Application Support/Claude/. macOS 10.15+ is the supported platform; Linux is marked experimental and Windows is not there yet. MCP_CONDUCTOR_PROJECT_DIR and MCP_CONDUCTOR_WORKSPACE override the auto-detected paths.
Setup effort
One command — curl -fsSL https://raw.githubusercontent.com/lutherscottgarcia/mcp-conductor/main/install.sh | bash
USE CASES
01
Starting a session on a project you left last week
Load the cached architecture and current state instead of asking the assistant to read its way around the repo again.
02
Handing a project to a teammate mid-feature
Cache the current understanding under the project name so the next person's assistant starts where yours left off.
03
Catching a cache that has gone stale
Check the stored picture against the project before trusting it, and drop it when the structure has moved.
04
Keeping an assistant inside your workflow rules
Encode 'ask before writing' as a rule and pick how hard it bites — from a blocking rule down to a logged note.
5 tools
Listed in project docs. Your client may show a different list.
load_project_intelligence_cachevalidate_project_intelligence_cacherefresh_project_intelligenceinvalidate_project_cacheBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
Node.js 18.0.0 or later
INSTALLATION
Connect your client
Server setup
TERMINAL
curl -fsSL https://raw.githubusercontent.com/lutherscottgarcia/mcp-conductor/main/install.sh | bashMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"conversation-continuity": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MCP_CONDUCTOR>/dist/index.js"
],
"env": {
"MCP_CONDUCTOR_PROJECT_DIR": "/Users/<YOUR_USERNAME>/Projects",
"MCP_CONDUCTOR_WORKSPACE": "/Users/<YOUR_USERNAME>/Projects/claude"
}
}
}
}Claude Desktop — advanced
CLAUDE DESKTOP — ADVANCED · JSON
{
"mcpServers": {
"conversation-continuity": {
"command": "node",
"args": [
"<YOUR_PATH_TO_DIST>/index.js"
],
"env": {
"MCP_CONDUCTOR_PROJECT_DIR": "/Users/<YOUR_USERNAME>/Projects",
"MCP_CONDUCTOR_WORKSPACE": "/Users/<YOUR_USERNAME>/Projects/claude",
"LOG_LEVEL": "info"
}
},
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
},
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/<YOUR_USERNAME>/Projects"
]
}
}
}
