Skip to main content
hc
Submit
mcpSource-backedReview first Safety ✓ Privacy ✓

Code Index MCP Server

Local code indexing MCP server that lets AI assistants search repositories, build symbol indexes, inspect file summaries, monitor changes, and navigate multi-language codebases.

by johnhuang316·added 2026-06-06·
Claude CodeClaude Desktop
HarnessClaude CodeClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • Code Index MCP reads repository files, builds shallow and deep indexes, exposes file summaries, and can return source snippets through search and file resources.
  • Point `--project-path` at one approved repository; avoid broad parent directories, home directories, generated dependency trees, or secret-heavy paths.
  • Deep indexing and watcher refreshes can consume CPU, memory, disk IO, and temp storage on large codebases.
  • The server can create and clear index/cache settings and temporary directories used for stored index data.
  • Search results, file summaries, and symbol bodies can surface credentials, private code, customer data, internal URLs, or proprietary implementation details if they exist in the repository.

Privacy notes

  • Tool calls may expose file paths, filenames, source code snippets, imports, classes, methods, functions, symbols, search matches, complexity summaries, and project settings.
  • Index data and temp directories can persist derived repository structure or symbol metadata outside the source tree.
  • File watcher status, exclude patterns, and settings can reveal local project layout and development conventions.
  • If an MCP client forwards tool results to a model provider, repository contents and search snippets may leave the local machine.
  • Exclude secrets, generated artifacts, vendored dependencies, build output, and private data before indexing.

Prerequisites

  • Python 3.10 or newer.
  • uv or another Python package runner that can install `code-index-mcp`.
  • An approved repository path that the MCP client is allowed to inspect.
  • Optional native search tools such as ripgrep, ugrep, ag, or grep for faster search backends.
  • Review of exclude patterns, file watcher behavior, temp/index storage, and deep-index cost for large repositories.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
10 minutes
Difficulty
intermediate
Tool listing metadata
Disclosure
MIT-licensed Python MCP server for local code indexing and analysis. This entry is separate from semantic code agents and graph-indexing entries because it focuses on local project indexes, file discovery, search backends, and symbol summaries through the `code-index-mcp` package.
Full copyable content
{
  "mcpServers": {
    "code-index": {
      "command": "uvx",
      "args": [
        "code-index-mcp",
        "--project-path",
        "ABSOLUTE_PATH_TO_REPOSITORY"
      ]
    }
  }
}

About this resource

Content

Code Index MCP is a local code-aware MCP server for indexing repositories and answering project navigation questions. It lets an AI assistant set a project path, refresh shallow file indexes, build deeper symbol indexes, search code, find files, inspect file summaries, retrieve symbol bodies, and monitor file watcher status.

Use it when a coding agent needs fast, repeatable local context from a specific repository without granting a broader shell or editor-control server. It is best configured with an explicit project path and reviewed exclude patterns so only the intended source tree is indexed.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI metadata, license, package metadata, MCP server implementation, well-known MCP manifest, FastMCP config, and restart playbook for current setup and operation details.

Features

  • Set or bootstrap a project path for repository-specific indexing.
  • Build shallow file indexes and optional deep symbol indexes.
  • Search code with native search backends such as ugrep, ripgrep, ag, or grep when available.
  • Find files through glob patterns.
  • Summarize files, imports, symbols, methods, functions, and complexity data.
  • Retrieve symbol bodies after building a deep index.
  • Monitor file changes and configure watcher behavior.
  • Store indexes and settings in temp/index directories.
  • Support tree-sitter strategies for Python, JavaScript, TypeScript, Java, Kotlin, C#, Go, Objective-C, Zig, and Rust, with fallback handling for many other file types.
  • Publish .well-known and FastMCP metadata for clients that can import MCP manifests.

Installation

Run with uvx and an explicit project path:

uvx code-index-mcp --project-path ABSOLUTE_PATH_TO_REPOSITORY

Add it to an MCP client:

{
  "mcpServers": {
    "code-index": {
      "command": "uvx",
      "args": [
        "code-index-mcp",
        "--project-path",
        "ABSOLUTE_PATH_TO_REPOSITORY"
      ]
    }
  }
}

You can also start without --project-path and call the set_project_path tool after launch, but an explicit startup path is easier to audit.

Use Cases

  • Find all files or functions related to a feature before editing.
  • Search for deprecated APIs, TODOs, config keys, routes, or error handling.
  • Summarize a file's imports, symbols, functions, and structural complexity.
  • Build a deep index before asking where a symbol is defined or used.
  • Keep a coding session's repository context fresh after file changes.
  • Compare project structure across Python, TypeScript, Java, Go, Rust, C#, and other mixed-language repositories.

Safety and Privacy

Code Index MCP is read-oriented, but it still grants the model visibility into local source code and derived repository metadata. Scope it to one repository, review exclude patterns, and avoid indexing generated artifacts, vendored dependencies, secret stores, customer data, or unrelated sibling projects.

Remember that search snippets and summaries can contain secrets if the repository contains secrets. Treat MCP results as repository data, especially when the MCP client sends tool output to a remote model provider.

Duplicate Notes

Existing catalog entries cover semantic code agents, graph-backed context servers, and token-efficient code search tools. This entry covers the separate johnhuang316/code-index-mcp Python package and its local repository indexing, file discovery, watcher refresh, and symbol-summary workflow.

#code-search#indexing#symbols#repository#local

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.