VectorCode

MCP server · GitHub · ★ 874 · graded 2026-10-23Source linked

A code repository indexing tool to supercharge your LLM experience.

No outside reports on file

VectorCode exposes your code to AI systems and external storage, so it should only index non-sensitive projects and run in isolated environments with strict access controls.

Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for VectorCode helpful?

What it can access

Local filesNo local folder access notedLOW
Command executionNo shell command runner notedLOW
Network reachConnects to outside service APINOTED
CredentialsNo API token requiredLOW
Package sourceGitHub (Davidyz/VectorCode)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/Davidyz/VectorCode ↗

All setup options ↓

Check this skill Watch it in my stack Compare Add to allowlist README badge View project

About VectorCode

VectorCode indexes your code repositories and converts them into a searchable format that AI assistants can understand. It helps large language models (LLMs—AI chatbots) quickly find and work with relevant code from your projects without sending raw files repeatedly.

Who it’s for

Developers who want to use AI assistants like Claude for code analysis, refactoring, or understanding large codebases. Teams looking to make their internal code more accessible to AI-powered development tools.

Alternatives

Codebase AI (Codebase context for AI, uses embeddings) - Aider (AI coding assistant with repo awareness) - Continue (IDE extension with code indexing) - OpenDevin (Open-source AI agent for code tasks)

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README at https://github.com/Davidyz/VectorCode (opens external site) for installation and configuration instructions specific to your setup.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

32/100

GitHub stars: 874
Listing last refreshed: 2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Security reports

No reports found for this package in our research (last checked 2026-10-29).

Check a specific version →

Risks to watch for

Code exposure: The tool indexes your repository content, which could include secrets, API keys, or proprietary logic if not filtered before indexing. - Embedding storage: Indexed vectors and code summaries may be stored locally or sent to external services, depending on configuration—verify where data lives. - AI leakage through context: When you share indexed code with an LLM, that AI system can retain and reuse the information in other conversations or training. - Malicious code in dependencies: The indexing tool itself relies on third-party packages; compromised dependencies could read your codebase. - Injection attacks: Specially crafted code comments or strings in your repository could trick the AI into executing unintended actions or revealing sensitive information.

How to lower the risk

Least-privilege permissions

Run the tool with minimal file system access; only point it to repositories you intend to index. - Never index production credentials, private keys, or configuration files with secrets.

Network isolation

Keep indexed data and vector databases on your own machines when possible. - Verify whether the tool sends any data to external AI or cloud services before enabling them.

Monitoring

Log and review what gets indexed to catch unintended sensitive files early. - Check GitHub releases and security advisories for updates to dependencies.

Red flags to watch for

Large index sizes that suggest unnecessary files were included (like .env or vendor folders). - Unexpected network requests from the indexing process to unknown servers.

Questions

How do I install VectorCode?

VectorCode does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/Davidyz/VectorCode.

Are there security reports about VectorCode?

No reports found for this package in our research (last checked 2026-10-29). VectorCode currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include code exposure.

Is VectorCode actively maintained?

VectorCode has 874 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/Davidyz/VectorCode before pinning it in production.

What are alternatives to VectorCode?

Notable alternatives to VectorCode include Codebase AI. You can also compare VectorCode side by side with other MCP servers in the Related tools section on this page.

Maintain or use VectorCode? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for VectorCode

GitHub README Markdown:

markdown

[![AgentArmorHQ Risk Grade for VectorCode](https://agentarmorhq.com/api/badge/davidyz-vectorcode)](https://agentarmorhq.com/skills/davidyz-vectorcode)

HTML embed:

html

<a href="https://agentarmorhq.com/skills/davidyz-vectorcode"><img src="https://agentarmorhq.com/api/badge/davidyz-vectorcode" alt="AgentArmorHQ Risk Grade for VectorCode" height="20" /></a>

Terminal check:

terminal

curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "davidyz-vectorcode"

Share with your security lead

Need sign-off to use VectorCode? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: VectorCode
- **Listing URL:** https://agentarmorhq.com/skills/davidyz-vectorcode
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 874 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (Davidyz/VectorCode)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/Davidyz/VectorCode
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type: App connector
Publisher: Davidyz
Source code: github.com/Davidyz/VectorCode
Est. context load: ~500 tokens / turn (~3 tool schemas, 0.25% of 200k context)
Popularity: 874 GitHub stars
Last updated: 2026-10-29
Last graded: 2026-10-23

Community

Discussions for VectorCode

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for VectorCode helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude