Hindsight-MCP: Integrate Dev History Data into SQLite for AI-Enhanced Coding

Hindsight MCP

An MCP server for AI-assisted programming that integrates development history data (Git commits, test results, Copilot sessions) into a searchable SQLite database, allowing AI assistants to access and analyze development history.

Developer tools Knowledge management and memory #Development history #AI programming #Code analysis #Test tracking .Rust

rating : 2.5 points

downloads : 4.4K

update time : 2026-03-12

Open Site

What is Hindsight MCP?

Hindsight MCP is a Model Context Protocol (MCP) server specifically designed for AI-assisted programming. It automatically collects and integrates your development history data, including Git commit records, test run results, and GitHub Copilot conversation content, and then stores this information in a unified SQLite database. Through the MCP protocol, AI assistants (such as Copilot) can query this historical data to more intelligently understand your project context, answer questions about development progress, and even help you diagnose problems.

How to use Hindsight MCP?

Using Hindsight MCP is very simple. First, install the tool in your development environment. Then, configure the MCP server in VS Code. After the configuration is complete, when you have a conversation with Copilot Chat (in Agent mode), Copilot can automatically call Hindsight's tools to query your development history, such as answering questions like 'What have I been working on recently?' or 'Help me find the commits related to the authentication function.' You can also run tests through the command line, and the results will be automatically recorded by Hindsight.

Applicable scenarios

Hindsight MCP is very suitable for developers who need to frequently review code changes, track test status, or analyze development patterns. For example, when you join a new project and want to understand recent developments, when you forget how a certain function is implemented, or when you want to analyze the association between test failures and specific code changes, Hindsight can provide strong data support.

Main features

Development history integration

Automatically collect data from Git, test runners (such as cargo-nextest), and GitHub Copilot sessions, and store them in a unified manner, breaking data silos.

Intelligent full-text search

Provide a powerful search tool that can perform keyword searches across commit information and Copilot conversation content to quickly locate relevant information.

Test result tracking

Associate test run results (success, failure, time consumption) with specific Git commits to facilitate tracing the reasons for changes in test status.

Activity timeline and summary

Visualize events such as commits and tests in a timeline format and generate activity statistical summaries for a specified period, making it clear at a glance.

Seamless AI integration

Integrate with AI assistants such as VS Code Copilot through the standard MCP protocol, allowing you to directly query development history in natural language.

Automated data ingestion

Git commits and Copilot sessions can be automatically recorded. Test results can also be automatically run and imported through a simple command.

Advantages

Improve context awareness: Enable AI assistants to answer based on your complete development history, making suggestions more accurate.

Simplify problem troubleshooting: Quickly locate changes that introduce bugs by associating commits and test results.

Improve knowledge retention: New team members or future you can quickly understand project decisions and implementation details by searching the history.

Non-intrusive integration: Run as an MCP server and seamlessly collaborate with existing development toolchains (Git, Cargo, VS Code).

Centralized data management: Centralize all development-related data in one place for easy query and analysis.

Limitations

Currently mainly targeting the Rust ecosystem: Test integration deeply depends on `cargo-nextest`, with limited support for other languages.

Requires a specific environment: Must be used in VS Code and depends on the Agent mode of GitHub Copilot.

Initial setup steps: Need to install the tool and configure the MCP settings in VS Code, with a certain learning cost.

Data privacy considerations: All development history (including Copilot conversations) will be stored in the local database, and users need to pay attention to data security.

How to use

Install Hindsight MCP

Use Rust's package manager Cargo to install the server program.

Install a test runner (optional)

If you need to record test results, you need to install Rust's next-generation test runner.

Configure VS Code

Create or edit the `.vscode/mcp.json` file in the root directory of your project and add the configuration of the Hindsight server.

Verify and use

Restart VS Code and run 'MCP: List Servers' in the command palette to confirm that the server has been loaded. Then switch to Agent mode in Copilot Chat and start asking questions.

Run and record tests

In the project directory, use the command provided by Hindsight to run tests and automatically record the results.

Usage examples

Review recent work

After a week of work, a developer wants to quickly understand what main tasks and commits have been completed this week.

Troubleshoot test failures

The CI pipeline reports test failures, and the developer needs to find out which recent commit caused the failure.

Find implementation code

A developer remembers having discussed the implementation of a certain function with Copilot before but forgets where the code is.

New members familiarize themselves with the project

A developer newly joining the project wants to understand the evolution history of a core module.

Frequently Asked Questions

Will Hindsight collect my private code or conversations?

Do I have to use it in VS Code and Copilot?

Does it support programming languages other than Rust?

Is the data automatically updated?

What if my project has multiple Git repositories?

After installation, Copilot is not using Hindsight's tools. What should I do?

Related resources

GitHub repository

Source code, issue tracking, and latest releases of the Hindsight MCP project.

Model Context Protocol (MCP) official website

Official documentation and specifications for the MCP protocol, which is the basis for Hindsight to communicate with AI assistants.

cargo-nextest documentation

Documentation for Rust's next-generation test runner, which Hindsight depends on to obtain test data.

VS Code Copilot documentation

Official usage guide for GitHub Copilot, learn how to enable and use the Agent mode.

🚀 hindsight-mcp

An MCP server for AI-assisted coding that leverages development history.

🚀 Quick Start

Prerequisites

VS Code v1.99+ with GitHub Copilot
cargo-nextest (for test ingestion): cargo install cargo-nextest

Installation

cargo install hindsight-mcp

Configure VS Code

Create .vscode/mcp.json in your project:

{
  "servers": {
    "hindsight": {
      "type": "stdio",
      "command": "hindsight-mcp",
      "args": ["--workspace", "${workspaceFolder}"]
    }
  }
}

Verify Setup

Open VS Code Command Palette (Cmd+Shift+P).
Run "MCP: List Servers".
Confirm hindsight is listed.
In Copilot Chat, switch to Agent mode.
Ask: "What have I been working on recently?"

That's it! Copilot will use hindsight tools to answer questions about your development history.

✨ Features

Full-text search across commits and Copilot conversations.
Track test results linked to specific commits.
Activity summaries and timeline views.
Automatic git and Copilot session ingestion.

📦 Installation

cargo install hindsight-mcp

💻 Usage Examples

Basic Usage

# Run all tests and ingest
hindsight-mcp test

# Test specific package
hindsight-mcp test -p my-crate

# Preview without writing to database
hindsight-mcp test --dry-run

Advanced Usage

# Using stdin mode
NEXTEST_EXPERIMENTAL_LIBTEST_JSON=1 cargo nextest run \
  --message-format libtest-json 2>/dev/null | \
  hindsight-mcp test --stdin

# Using ingest command with explicit commit
NEXTEST_EXPERIMENTAL_LIBTEST_JSON=1 cargo nextest run \
  --message-format libtest-json 2>/dev/null | \
  hindsight-mcp ingest --tests --commit $(git rev-parse HEAD)

📚 Documentation

MCP Tools

Tool	Purpose	Example Prompt
`hindsight_timeline`	Chronological activity view	"Show recent commits and test runs"
`hindsight_search`	Full-text search	"Find commits about authentication"
`hindsight_failing_tests`	Query test failures	"What tests are failing?"
`hindsight_activity_summary`	Aggregate stats	"Summarise my week"
`hindsight_commit_details`	Commit info with tests	"Details for commit abc123"
`hindsight_ingest`	Trigger data refresh	"Refresh development history"

Tool Arguments Reference

hindsight_timeline

limit (int): Max events, default 50
workspace (string): Filter by path

hindsight_search

query (string): Search query (required)
source (string): "all", "commits", or "messages"
limit (int): Max results, default 20

hindsight_failing_tests

limit (int): Max tests, default 50
workspace (string): Filter by path
commit (string): Filter by SHA

hindsight_activity_summary

days (int): Days to summarise, default 7

hindsight_commit_details

sha (string): Commit SHA (required)

hindsight_ingest

workspace (string): Path to ingest (required)
source (string): "git", "copilot", or "all"
incremental (bool): Only new data, default true
limit (int): Max items

Data Sources

Source	Data Collected
Git	Commits (SHA, author, message, timestamp, parents)
Tests	Run metadata, outcomes, durations, failure output
Copilot	Chat sessions, prompts, responses, attached files

Git and Copilot data are ingested automatically. Test results require running hindsight-mcp test.

CLI Reference

hindsight-mcp [OPTIONS] [COMMAND]

Commands:
  ingest    Ingest data from various sources
  test      Run tests and ingest results

Options:
  -d, --database <PATH>   Database path [default: ~/.hindsight/hindsight.db]
  -w, --workspace <PATH>  Workspace path [default: current directory]
  -v, --verbose           Debug logging
  -q, --quiet             Errors only
      --skip-init         Skip database init
  -h, --help              Print help
  -V, --version           Print version

Test Subcommand Options

hindsight-mcp test [OPTIONS] [-- <NEXTEST_ARGS>...]

Options:
  -p, --package <PKG>     Package(s) to test
      --bin <BIN>         Binary(ies) to run
  -E, --filter <EXPR>     Filter expression
      --stdin             Read from stdin
      --dry-run           Preview only
      --no-commit         Do not link to commit
      --commit <SHA>      Explicit commit SHA
      --show-output       Show test output

Environment Variables

Variable	Description
`HINDSIGHT_DATABASE`	Database path
`HINDSIGHT_WORKSPACE`	Default workspace

Database Location

Platform	Default Path
macOS	`~/Library/Application Support/hindsight/hindsight.db`
Linux	`~/.local/share/hindsight/hindsight.db`
Windows	`%LOCALAPPDATA%\hindsight\hindsight.db`

🔧 Technical Details

Troubleshooting

Problem	Solution
Server does not start	Check binary path; run with `--verbose`
No data showing	Run `hindsight_ingest` tool via Copilot
Log interference	Use `--quiet` in production

Development

Building from Source

git clone https://github.com/Rbfinch/hindsight-mcp.git
cd hindsight-mcp
cargo build --release

Running Tests

cargo install cargo-nextest
cargo nextest run --workspace

Workspace Structure

hindsight/
├── crates/
│   ├── hindsight-mcp/      # MCP server binary
│   ├── hindsight-git/      # Git log processing
│   ├── hindsight-tests/    # Test result processing
│   └── hindsight-copilot/  # Copilot session parsing

Fuzzing

cd crates/hindsight-tests
cargo +nightly fuzz run fuzz_nextest_run

cd crates/hindsight-copilot
cargo +nightly fuzz run fuzz_session_json

📄 License

MIT

Markdownify MCP

Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.

The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.

A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.

Python

23.9K

4.5 points

Duckduckgo MCP Server

Certified

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.

UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.

37.5K

5 points

Context7

Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.

The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.

Python

55.5K

4.8 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご

Hindsight MCP

Overview

Content Details

Alternatives

What is Hindsight MCP?

How to use Hindsight MCP?

Applicable scenarios

Main features

How to use

Usage examples

Frequently Asked Questions

Related resources

Installation

🚀 hindsight-mcp

🚀 Quick Start

Prerequisites

Installation

Configure VS Code

Verify Setup

✨ Features

📦 Installation

💻 Usage Examples

Basic Usage

Advanced Usage

📚 Documentation

MCP Tools

hindsight_timeline

hindsight_search

hindsight_failing_tests

hindsight_activity_summary

hindsight_commit_details

hindsight_ingest

Data Sources

CLI Reference

Environment Variables

Database Location

🔧 Technical Details

Troubleshooting

Development

📄 License

Alternatives