What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the codeindex MCP server?
Structural code intelligence over MCP: symbols, callers, imports and blast radius, 40+ languages.
How to install codeindex
Copy-paste configuration for popular MCP clients.
CODEINDEX_WORKSPACEDirectory to index. Defaults to the enclosing project root of wherever the client starts the server, which is the right answer for every editor and agent that launches it inside a repository. Set it only when the server runs somewhere other than the code.
CODEINDEX_NO_DAEMONSet to 1 to keep the index inside this server process. By default every session on one repository shares a single background daemon that parses and watches the tree once, and each session is a thin relay onto it. Turn that off for a sandbox with no writable runtime directory.
CODEINDEX_DAEMON_IDLE_SECSSeconds with no session attached before the shared daemon exits and returns its memory. Default 900. Set 0 to keep it resident.
{
"mcpServers": {
"codeindex": {
"command": "npx",
"args": [
"-y",
"@munhq/codeindex"
],
"env": {
"CODEINDEX_WORKSPACE": "<YOUR_CODEINDEX_WORKSPACE>",
"CODEINDEX_NO_DAEMON": "<YOUR_CODEINDEX_NO_DAEMON>",
"CODEINDEX_DAEMON_IDLE_SECS": "<YOUR_CODEINDEX_DAEMON_IDLE_SECS>"
}
}
}
}Related MCP servers

distil
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.

chat-recall
One searchable history across every AI coding tool, with secret scanning and a shared task board.

cloud-tools
Multi-cloud cost, inventory and waste analysis over MCP: AWS, GCP, Cloudflare and OVH.

Munim Computer Use
Accessibility-first desktop control for AI agents with background input, agent pointer, and Chrome integration across macOS, Windows, and Linux.

Layerbridge
Read, edit and export the Figma file open in a local plugin. No REST API, no rate limits.
Bridges any GraphQL API to Claude Code — auto-generates MCP tools via schema introspection.
