code-cortex-mcp
Local MCP server that indexes codebases into a queryable knowledge graph for AI coding agents.
Tested on macOS and Linux
Use it
macOS arm64
You need first
- System packages:
CMake,C++23 compiler,zlib
download install.sh from GitHub
curl -fsSL https://raw.githubusercontent.com/tigercosmos/code-cortex-mcp/main/install.sh -o /tmp/install.sh && wc -l /tmp/install.sh && head -n 100 /tmp/install.shrun install.sh --skip-config to install binary to ~/.local/bin
bash /tmp/install.sh --skip-config
Check that it works
code-cortex-mcp --version && which code-cortex-mcp && ls -l ~/.local/bin/code-cortex-mcpThe output should contain “code-cortex-mcp 0.23.0”.
Add it to your agent
claude mcp add code-cortex-mcp -- code-cortex-mcp mcpJSON for Claude Desktop, Cursor and other clients
{
"mcpServers": {
"code-cortex-mcp": {
"command": "code-cortex-mcp",
"args": [
"mcp"
]
}
}
}Add code-cortex-mcp as an MCP server in your AI coding client, then ask the agent to call index_repository on your project folder.
Linux x86_64
You need first
- System packages:
CMake,C++23 compiler,zlib
download install.sh
curl -fsSL https://raw.githubusercontent.com/tigercosmos/code-cortex-mcp/main/install.sh -o /tmp/install.shrun install.sh --skip-config to install portable binary
bash /tmp/install.sh --skip-config
Check that it works
code-cortex-mcp --versionThe output should contain “code-cortex-mcp 0.23.0”.
Add it to your agent
claude mcp add code-cortex-mcp -- code-cortex-mcpJSON for Claude Desktop, Cursor and other clients
{
"mcpServers": {
"code-cortex-mcp": {
"command": "code-cortex-mcp",
"args": []
}
}
}Add code-cortex-mcp as an MCP server in your AI coding client, then ask the agent to call index_repository on your project folder.
What it does
- Index a codebase into a queryable knowledge graphTested
How to use it
- Connect
code-cortex-mcpto your MCP client. - Call the index_repository tool with repo_path set to <your project folder>.
- Connect
- Search code with graph-aware grepTested
How to use it
- Index your project first with index_repository.
- Call the search_code tool with pattern set to <your text> and project set to <project name>.
- Trace call paths and data flowNot shown working
- Inspect a symbol's definition and callersNot shown working
How far pickfit got
macOS arm64
- Installs
- Connects
- 2 of 4 features work
- Works offline
Linux x86_64
- Installs
- Connects
- 3 of 4 features work
- Works offline
Other systems
Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- inspect a symbol definition with callers and related tests
- trace call chains between functions
- search code augmented by the graph
An alternative to codebase-memory-mcp.
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
macOS arm64
An MCP client called one of its tools
- Replayed from scratch
- Works offline
- Checked on 1 Nov 2026
- Version 0.23.0
An MCP client handshake over stdio listed 15 tools, and a call to index_repository returned a result.
Linux x86_64
An MCP client called one of its tools
- Replayed from scratch
- Works offline
- Checked on 31 Oct 2026
- Version 0.23.0
An MCP client handshake over stdio listed 15 tools, and a call to index_repository returned a result.
Differences the test machine hit
- README: curl -fsSL ... | bash installs and configures agents
In the test: used --skip-config to avoid modifying Claude Code/Codex etc. configs in the box; still installs binary correctly - README: project argument optional, inferred from working directory
In the test: MCP tool calls outside indexed directory require explicit "project" (e.g., tmp-testproj) else error