chunkhound
Your entire engineering context, deeply understood
No outside reports on file
Chunkhound gives AI systems deep access to your entire codebase, so never use it with repositories containing secrets, private logic, or sensitive IP unless you fully trust where that context goes.
Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (chunkhound/chunkhound)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/chunkhound/chunkhound ↗
About Chunkhound
chunkhound is an open-source MCP server focused on Memory & knowledge. Your entire engineering context, deeply understood. Source code and documentation are published on GitHub at chunkhound/chunkhound.
Who it’s for
Software developers and teams who use Claude or compatible AI tools and want the AI to have better understanding of their full codebase. It's designed for engineers working on complex projects where AI needs to reference multiple files and understand relationships between code.
Alternatives
- Codebase indexing built into Claude: Use Claude's native file handling and let it learn from files you explicitly share
- Tree-sitter based tools: Use open-source code parsers that build context locally without external processing
- Conventional git-based tools: Use grep, git log, and local analysis rather than AI-driven scanning
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README. The GitHub repository (chunkhound/chunkhound) should contain installation instructions. This is an MCP server, so setup likely involves configuring it in your Claude Desktop or compatible AI tool's mcpServers configuration.
Why this grade
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
- GitHub stars
- 1.5k
- 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).
Risks to watch for
- Full codebase access: This tool reads your entire engineering project, including all source code, configuration files, and potentially secrets if stored in your repo
- Accidental secret exposure: If API keys, database passwords, or credentials are in your code or comments, they're visible to the AI and stored in context
- Intellectual property risk: Your complete codebase is processed and used in AI conversations, which may be logged or stored depending on your AI provider
- No input validation shown: It's unclear if this tool filters malicious code patterns or attempts to trick the AI through specially crafted code comments or files
- Data leakage via AI responses: The AI might accidentally repeat sensitive code snippets, paths, or architecture details in responses that could be seen by others
How to lower the risk
Least-privilege permissions
- Only connect to a separate, scrubbed copy of your repo without secrets or credentials
- Remove API keys and passwords before any AI processing
Network isolation
- Run this tool on your local machine only if possible
- Don't expose it to untrusted networks or shared environments
Monitoring
- Review what files and data the tool actually reads before enabling it
- Check AI conversation logs to see what code details appear in responses
Red flags to watch for
- Tool requests access to hidden folders or system files beyond your project
- No clear documentation of what data it collects or stores
- Unusual network activity after installation
Questions
How do I install Chunkhound?
Chunkhound does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/chunkhound/chunkhound.
Are there security reports about Chunkhound?
No reports found for this package in our research (last checked 2026-10-29). Chunkhound currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include full codebase access, accidental secret exposure, intellectual property risk.
Is Chunkhound actively maintained?
Chunkhound has 1.5k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/chunkhound/chunkhound before pinning it in production.
What are alternatives to Chunkhound?
Notable alternatives to Chunkhound include Codebase indexing built into Claude (Use Claude's native file handling and let it learn from files you explicitly share), Tree-sitter based tools (Use open-source code parsers that build context locally without external processing), Conventional git-based tools (Use grep, git log, and local analysis rather than AI-driven review). You can also compare Chunkhound side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Chunkhound? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/chunkhound-chunkhound)HTML embed:
<a href="https://agentarmorhq.com/skills/chunkhound-chunkhound"><img src="https://agentarmorhq.com/api/badge/chunkhound-chunkhound" alt="AgentArmorHQ Risk Grade for Chunkhound" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "chunkhound-chunkhound"Share with your security lead
Need sign-off to use chunkhound? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: chunkhound
- **Listing URL:** https://agentarmorhq.com/skills/chunkhound-chunkhound
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.5k 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:** Requires API key or token
- **Package source:** GitHub (chunkhound/chunkhound)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/chunkhound/chunkhound
- **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 22, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- chunkhound
- Source code
- github.com/chunkhound/chunkhound
- Est. context load
- ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context)
- Popularity
- 1.5k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-22
Community
Discussions for Chunkhound
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.
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