What can you do with this server?

StarSeeker MCP server lets you fetch, store, and intelligently search your GitHub starred repositories. * Fetch stars: Retrieve and index all starred repos for a GitHub user (optionally with a token for higher rate limits) using fetch_stars_for_user. * Search stars: Perform AI-powered semantic search with Google Gemini embeddings and cosine similarity, with a hybrid fallback to BM25 keyword ranking combined with repo popularity (star count). Use search_stars with natural language queries to find contextually relevant repos. * Persistent caching: Embeddings and fetched data are cached locally (e.g., ~/.star_seeker_mcp) for faster repeated searches. * Integration: Works as an MCP tool with various clients (Antigravity, VSCode, Cursor AI, Claude Desktop), includes an interactive Agent Playground (UI or CLI), and supports deployment via Docker.

Which integrations are available for this server?

Integrates with the GitHub API to fetch a user's starred repositories for semantic and keyword search.

How do I use StarSeeker MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@StarSeeker MCP find machine learning repos in my stars" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

StarSeeker MCP

by HikmetCTK

Overview Schema Source Related Servers Discussions Admin

Python

Local

🚀 StarSeeker MCP: GitHub Stars Intelligence Agent

A powerful MCP (Model Context Protocol) server that helps you discover relevant repositories from your own starred list on GitHub. It uses BM25 keyword ranking and Gemini Semantic Search to find the best tools for your next project.

📸 Screenshots

Related MCP server: LibrAIum

🚀 Features

Semantic Search: Find repositories based on meaning and context, not just keywords, using Google Gemini (gemini-embedding-001).
Hybrid Search: Google gemini text embedding + BM25( Fallback to BM25 and popularity-based rank fusion when gemini embedding isn't available.)
Docker Ready: Easy containerized deployment.
Fast Performance: Persistent embedding cache and efficient batching.

🛠 File Structure for MCP

mcp_server.py: Main entry point.
server.py: Tool definitions and MCP logic.
search_engine.py: Core logic for BM25 and Gemini embeddings.
github_client.py: GitHub API integration for fetching stars.
config.py: Configuration and environment management.

📋 Prerequisites

Python 3.13+
uv (recommended)
GitHub Personal Access Token (for higher rate limits)
Gemini API Key (for semantic search capabilities)

⚙️ Installation & Setup

Clone the repository:

git clone <repository-url>
cd Star_Seeker_mcp

Set up Environment: Create a .env file in the root directory:
```
GITHUB_TOKEN=your_github_token
GEMINI_API_KEY=your_gemini_api_key
```
Note: You can run without a GITHUB_TOKEN (GitHub API allows ~60 requests/hr or up to 1000 repos without a token), but a GEMINI_API_KEY is required for the Agent Playground and semantic search. I used free tier of Gemini API.
Install Dependencies:
```
uv sync
```

🎮 Quick Start: Agent Playground

The fastest way to experience StarSeeker is through the integrated Agent Playground. It provides a visual chat interface (Gradio) to interact with your GitHub stars.

1. Launch the Visual UI (Recommended)

uv run agent_playground.py

Access: Open http://localhost:8080 in your browser.
Features: Chat with Gemini, ask it to fetch your stars, and then search through them using natural language.

💡 Quick Tip: Once the UI is open, you can simply type:
github name : your_username. Find me some cool React libraries.
The agent will automatically fetch your stars (if not cached) and perform a semantic search.

2. Launch the CLI Version

If you prefer the terminal:

uv run agent_playground.py --cli

🔌 MCP Server (Integration for Antigravity/Cursor/Claude)

If you want to use StarSeeker as a tool inside Cursor, Claude Desktop, or Antigravity, follow these steps.

1. Antigravity (tested with Antigravity)

Antigravity provides the easiest setup experience with a visual interface.

Open Antigravity
Click the 3 dots in the top right corner
Select "MCP Servers" → "Manage Servers" → "View Raw Config"
Paste this configuration and restart Antigravity :

{
  "mcpServers": {
    "star-seeker-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\path\\to\\Star_Seeker_mcp",
        "run",
        "mcp_server.py"
      ],
      "env": {
        "GEMINI_API_KEY": "your_key",
        "GITHUB_TOKEN": "your_token"
      }
    }
  }
}

Replace C:\\path\\to\\Star_Seeker_mcp with your actual installation path
Replace the API keys with your actual keys
Restart Antigravity
You can see writing @MCP Server in Antigravity chat

2.VSCODE

Create mcp.json file in workspace folder or find if it exists.
Add this configuration to mcp.json file

{
  "mcpServers": {
    "github-stars-seeker": {
      "command": "uv",
      "args": [
        "--directory",
        "c:path\\to\\Star_Seeker_mcp",
        "run",
        "mcp_server.py"
      ],
      "env": {
        "GITHUB_TOKEN": "your_github_token",
        "GEMINI_API_KEY": "your_gemini_api_key"
      }
    }
  }
}

click start button .
You can use it

3. Cursor AI

Settings -> Cursor Settings -> MCP.
+ Add New MCP Server.
Name: StarSeeker, Type: command.
Command: uv --directory "C:\path\to\Star_Seeker_mcp" run mcp_server.py

3. Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "star-seeker-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\path\\to\\Star_Seeker_mcp",
        "run",
        "mcp_server.py"
      ],
      "env": {
        "GITHUB_TOKEN": "your_token",
        "GEMINI_API_KEY": "your_key"
      }
    }
  }
}

🛠 MCP Tools

`fetch_stars_tool`

Fetches all starred repositories for a given GitHub username and prepares the search index.

Args: username (required), token (optional)

`search_stars_tool`

Search through the fetched repositories using semantic or keyword search.

Args: username (required), query (required)

🔌 Integrations

Option A: Running with Docker

The Docker image is optimized to only install the core MCP server dependencies (skipping Gradio).

Build and Start:
```
docker-compose up --build -d
```
Access: The server runs on stdio/HTTP inside the container, ready for your tools.

Option B: Running Locally

uv run mcp_server.py

📂 Data Storage & Access

The server stores fetched JSON data and search embeddings in a centralized directory to avoid duplicates and ensure persistence.

File Locations

Local (Windows): explorer %USERPROFILE%\.star_seeker_mcp to open the directory
Local (Linux/macOS): ~/.star_seeker_mcp
Inside Docker: /root/.star_seeker_mcp (backed by a Docker volume)

Terminal Commands to Access Data

View Local Data Files (Windows CMD)

dir %USERPROFILE%\.star_seeker_mcp

View Data Files Inside Running Docker Container

docker exec -it star-seeker-mcp ls -lh /root/.star_seeker_mcp

Copy a Data File from Docker to Local Machine

docker cp star-seeker-mcp:/root/.star_seeker_mcp/yourusername_stars.json .

🧠 How it Works

Data Collection: Fetches repo names, descriptions, and topics via GitHub API.
Indexing:
- Generates vector embeddings for all descriptions using gemini-embedding-001.
- Builds a BM25 index for keyword search fallback.
Retrieval:
- Uses Cosine Similarity for semantic matches.
- For keyword search, it uses a rank fusion of BM25 scores and repository popularity (stars).

📄 License

MIT

Available Tools

2 tools

_fetch_stars_for_userC

Fetch or update the database of starred repositories for a specific GitHub username.

Args: username: The exact GitHub username (e.g., 'gulbaki'). token: Optional GitHub personal access token to avoid rate limits (defaults to GITHUB_TOKEN env).

ParametersJSON Schema

Name	Required	Description	Default
`token`	No
`username`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must fully disclose behavior. It reveals token purpose and default, but the 'update' aspect is unclear—could imply mutation without warning about side effects. No mention of rate limits, errors, or output format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is brief (4 lines), includes args list, front-loaded purpose. No wasted words, though 'Args' section is slightly redundant given schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple (2 params, sibling, output schema exists). Description covers basic usage but lacks clarity on side effects (update vs fetch) and does not fully compensate for missing annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage, so description compensates by detailing both parameters: username (exact, example) and token (optional, purpose, default). Adds moderate value beyond schema stubs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description states 'fetch or update the database of starred repositories', which gives a clear verb and resource, but the dual nature (fetch or update) is ambiguous. Does it always update? Does it only fetch? The sibling 'search_stars' suggests a search function, but no explicit differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Minimal guidance: only mentions 'for a specific GitHub username'. No context on when to use this versus search_stars, no prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_starsA

Search through a user's starred repositories using AI-powered semantic search or keyword matching.

Args: username: The exact GitHub username provided by the user. query: The search terms or project idea to find relevant repositories for.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes
`username`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, and the description does not disclose behavioral traits such as read-only nature, auth requirements, or rate limits. It only describes input semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and uses a clear docstring format with Args section. It conveys necessary information without unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description adequately covers input parameters. It provides sufficient context for a search tool, though it could mention the return type for completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaningful context for both parameters beyond the schema, specifying 'exact GitHub username' and explaining the query as 'search terms or project idea'. With 0% schema coverage, this compensates well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches starred repositories using semantic search or keyword matching. It distinguishes from the sibling _fetch_stars_for_user by implying focused search vs. full listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear argument explanations but lacks explicit guidance on when to use this tool vs. the sibling _fetch_stars_for_user. The usage context is implied but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

2 tool updatesv0.1.0Jul 30, 2026
- First observed_fetch_stars_for_user
- First observedsearch_stars

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored 2026-07-30 17:45 across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one fetches/updates the database of starred repositories, the other searches through them. No ambiguity.

Naming Consistency2/5

Naming is inconsistent: '_fetch_stars_for_user' uses a leading underscore and underscores between words, while 'search_stars' omits the underscore prefix and uses fewer words. No consistent pattern.

Tool Count3/5

With only 2 tools, the server feels minimal but could be sufficient for a focused use case of fetching and searching stars. However, it is borderline for a broader star management tool.

Completeness3/5

The set covers fetching and searching starred repositories, but lacks operations like listing all stars or deleting them. Minor gaps exist, but core functionality is present.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

gread A
io.github.NitroRCr
An MCP server that gives your AI access to the source code and docs of all public github repos
Version Control Code Analysis Documentation Access
5364
neverinfamous-memory-journal-mcp
ai.smithery
A MCP server built for developers enabling Git based project management with project and personal…
Version Control Developer Tools Project Management
320
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102
driflyte-mcp-server
com.driflyte
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Search Web Scraping Knowledge & Memory
211

Related MCP Servers

skillfinder-mcp
Search Knowledge & Memory
Chin-mae
A
license
A
quality
D
maintenance
An MCP server that provides on-demand skill discovery for AI coding agents by querying GitHub repositories, using BM25 search to return relevant SKILL.md content.
Updated 5 months ago (2026-04-18 03:53 UTC)
2
6 npm
MIT
LibrAIum
Version Control Developer Tools Search
nel-neru
A
license
Not graded
quality
B
maintenance
MCP server for searching, retrieving details, suggesting, and adding curated GitHub repositories from a personal library.
Updated 2 days ago (2026-09-17 20:43 UTC)
MIT
github-insights-mcp
jknithin36
A
license
A
quality
B
maintenance
MCP server that enables AI assistants to look up and analyze GitHub repositories, including stars, forks, description, open issues, and README content.
Updated 2 months ago (2026-07-19 20:36 UTC)
2
44 npm
MIT
github-stars-mcp
Databases Version Control Search
ENFernandes
A
license
A
quality
C
maintenance
An MCP server that caches your GitHub starred repositories in a local SQLite database and lets you search, list, and retrieve details about them through any MCP client (Claude Desktop, Cursor, VS Code, etc.), with automatic freshness checks via GitHub's ETag mechanism.
Updated 2 months ago (2026-08-04 13:21 UTC)
5
MIT

🚀 StarSeeker MCP: GitHub Stars Intelligence Agent

📸 Screenshots

🚀 Features

🛠 File Structure for MCP

📋 Prerequisites

⚙️ Installation & Setup

🎮 Quick Start: Agent Playground

1. Launch the Visual UI (Recommended)

2. Launch the CLI Version

🔌 MCP Server (Integration for Antigravity/Cursor/Claude)

1. Antigravity (tested with Antigravity)

2.VSCODE

3. Cursor AI

3. Claude Desktop

🛠 MCP Tools

fetch_stars_tool

search_stars_tool

🔌 Integrations

Option A: Running with Docker

Option B: Running Locally

📂 Data Storage & Access

File Locations

Terminal Commands to Access Data

View Local Data Files (Windows CMD)

View Data Files Inside Running Docker Container

Copy a Data File from Docker to Local Machine

🧠 How it Works

📄 License

Available Tools

Output Schema

TDQS

Output Schema

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

skillfinder-mcp

LibrAIum

github-insights-mcp

github-stars-mcp

`fetch_stars_tool`

`search_stars_tool`