1. Conduid
  2. Developer Tools
  3. Local Context
MCP server · Developer Tools

Local Context

An MCP server that helps AI assistants work with GoLang third-party packages using your local Go module cache.

Unclaimed MIT last commit 7 months ago mcp-toolsmcp-serverdevtools
66Good

Scored 22 hours ago · breakdown

About Local Context

Local Context is an MCP server published by svetlyi in the Developer Tools category: an MCP server that helps AI assistants work with GoLang third-party packages using your local Go module cache. It has been installed 0 times through Conduid.

The repository has 10 stars and 1 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

Install
npx mcp-local-context

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Local Context

Powered by Claude · Grounded in docs

I know everything about Local Context. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

v0.1.1Fixed main · 8 Jan 2026
v0.1.0Initial release · 25 Dec 2025

README

mcp-local-context

What is it and why use this?

An MCP server that helps AI assistants work with GoLang third-party packages using your local Go module cache. Think of it as a free, local alternative to Context7.

  • Free and unlimited - uses your existing GoLang cache, no API limits or costs
  • Works with any module - supports public and private modules already in your cache
  • Universal compatibility - works with all AI tools (Cursor, Claude, GitHub Copilot, etc.)
  • Customizable - add your own prompts and instructions for AI agents

Quick Start

# Install
go install github.com/svetlyi/mcp-local-context@latest

# Find binary path
echo $(go env GOPATH)/bin/mcp-local-context

Add to your IDE (e.g., Cursor): Settings → MCP Servers → Add:

{
  "mcpServers": {
    "local-context": {
      "command": "/path-to-the-binary/bin/mcp-local-context"
    }
  }
}

The server communicates via stdio (standard input/output).

Features

  • Built-in & Custom Prompts: Built-in Go context prompt with automatic discovery of custom prompt files from ~/.mcp-local-context/prompts/*.md
  • Configurable & Extensible: JSON configuration file and easily add new prompt providers (e.g., JavaScript, Python)

Configuration (optional)

Create ~/.mcp-local-context/config.json (optional):

{
  "log_level": "info",
  "log_file": "~/mcp-local-context.log",
  "custom_prompt_dirs": ["~/custom-prompts", "/path/to/other/prompts"]
}

Options:

  • log_level: debug, info, warn, error (default: info)
  • log_file: Path to log file (supports ~/ expansion). Default: OS temp file
  • custom_prompt_dirs: Additional directories for custom prompts. The ~/.mcp-local-context/prompts/ directory is always included

Custom Prompts

Place Markdown files in ~/.mcp-local-context/prompts/. Each .md file is automatically discovered and loaded.

Prompt Configuration

You can configure prompts using key-value pairs at the start of the file. The configuration section ends with a blank line.

Supported configuration keys:

  • title: Custom title/description for the prompt
  • lang: Language identifier (e.g., go, javascript, python)

Example with configuration: ~/.mcp-local-context/prompts/my-custom-prompt.md

title: My Custom Prompt Title
lang: go

# My Custom Prompt

This is my custom prompt that will be provided to AI assistants.

Example without configuration: ~/.mcp-local-context/prompts/simple-prompt.md

A description of my custom prompt.

# My Custom Prompt

This is my custom prompt that will be provided to AI assistants.

Note: If title is not specified, the first line is used as the prompt description. If the first line is a markdown heading (#), the heading markers are automatically removed.

The prompt will be available as a prompt named my-custom-prompt (derived from the filename) with the configured title or extracted description.

Usage

How to use

You can use the MCP in two ways:

Method 1: Directly reference a specific prompt

Manually invoke a specific prompt by name. This gives you precise control over which instructions are used.

For example, in Cursor, you can write:

Create something in Go, use the /local_context/golang-context-rule prompt

Method 2: Ask the AI to use the MCP tools

Ask the AI to use the MCP's automatic language detection tools. The AI will call list_supported_languages and then get_context_instructions with the appropriate language, which automatically provides the right context instructions.

For example:

Create something in Go, use the local-context MCP to get context instructions for Go

or more generally:

When working with third-party packages, use the local-context MCP to get the appropriate context instructions

Available Prompts

golang-context-rule

Systematic approach for working with third-party Go packages using the Go module cache. Guides AI assistants to:

  1. Identify the exact module version from go.mod
  2. Locate the Go module cache
  3. Explore the package structure
  4. Use go doc for documentation
  5. Read source code directly

Future work

  • Module indexing: Index existing modules to find appropriate functionality more efficiently based on the task
  • More languages: Add support for other languages, such as JavaScript, etc.

License

MIT License - see LICENSE file for details.

Contributing

🤝 Contributions are welcome! Please feel free to submit a Pull Request.

Related

🔗 Model Context Protocol Specification

README mirrored from the source repository 22 hours ago. The original is authoritative.

Questions

About Local Context

How do I install Local Context?

Run npx mcp-local-context, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Local Context safe to use with an AI agent?

Its trust score is 66 out of 100 (good). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Local Context still maintained?

The last commit was 7 months ago, with 0 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.