AgentArmorHQ
Sign in

open-agent-connector

MCP server · GitHub · ★ 847 · graded 2026-10-19Source linked

Open-source, self-hosted alternative to Composio, Nango, Merge.dev, and Arcade.dev for AI agent integrations. Run GitHub, Slack, Hacker News, and custom HTTP actions over MCP or REST.

No outside reports on file

This tool is safe only if you carefully manage API credentials, validate all custom HTTP endpoints, monitor agent actions closely, and keep your server patched and isolated from other systems.

Based on public adoption and transparency signals as of Oct 19, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Open Agent Connector helpful?

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 (Anil-matcha/open-agent-connector)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/Anil-matcha/open-agent-connector ↗

All setup options ↓

Check this skillWatch it in my stackCompareREADME badgeView project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-19.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Open Agent Connector

This tool lets AI agents perform actions on external services like GitHub, Slack, and Hacker News through a standard connection method called MCP. You can also add custom HTTP actions, and it works with self-hosted setups instead of relying on third-party services.

Who it’s for

Developers building AI agents who want to avoid vendor lock-in and prefer hosting their own integration layer. Teams that need to connect agents to multiple platforms without using external integration platforms.

Alternatives

  • Composio: Cloud-hosted integration platform for AI agents (vendor-managed, not self-hosted).
  • Nango: Managed integration service focused on sync and authentication.
  • Merge.dev: Platform for unified API access across business tools.
  • Arcade.dev: AI agent actions and integrations as a service.

Setup

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

Follow the project's README at https://github.com/Anil-matcha/open-agent-connector (opens external site) for installation and configuration steps 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
847
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.

Risks to watch for

  • Account credentials: Storing API keys or tokens for GitHub, Slack, and other services means a breach could expose all connected accounts.
  • Custom HTTP actions: Poorly configured custom endpoints might let the AI make unintended requests to internal systems or leak sensitive data.
  • Prompt injection: An attacker could craft malicious Slack messages, GitHub issues, or Hacker News content that tricks the agent into harmful actions.
  • No built-in audit trail: Without careful logging, you may not know what actions the agent performed or when.
  • Self-hosted security burden: Running your own server means you are responsible for patching, updates, and keeping dependencies secure.

How to lower the risk

Least-privilege permissions

  • Create API tokens with only the minimum permissions needed (e.g., read-only for Hacker News).
  • Use separate service accounts for the agent, never shared credentials.

Network isolation

  • Run the connector on an isolated network segment away from production systems.
  • Limit outbound connections to only required external services.

Monitoring

  • Log all actions the agent performs and review logs regularly.
  • Set up alerts if the agent tries to access unexpected services or makes bulk requests.

Red flags to watch for

  • Unknown dependencies added to the project suddenly.
  • Agent making requests to IPs or domains it was not configured to use.
  • Unusual amounts of data being transferred or stored.

Questions

How do I install Open Agent Connector?

Open Agent Connector does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/Anil-matcha/open-agent-connector.

Are there security reports about Open Agent Connector?

No reports found for this package in our research (last checked 2026-10-30). Open Agent Connector currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include account credentials, custom http actions, prompt injection.

Is Open Agent Connector actively maintained?

Open Agent Connector has 847 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/Anil-matcha/open-agent-connector before pinning it in production.

What are alternatives to Open Agent Connector?

Notable alternatives to Open Agent Connector include Composio (Cloud-hosted integration platform for AI agents (vendor-managed, not self-hosted)), Nango (Managed integration service focused on sync and authentication), Merge.dev (Platform for unified API access across business tools), Arcade.dev (AI agent actions and integrations as a service). You can also compare Open Agent Connector side by side with other MCP servers in the Related tools section on this page.

README badge and team notes

Maintain or use Open Agent Connector? 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 Open Agent Connector

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Open Agent Connector](https://agentarmorhq.com/api/badge/anil-matcha-open-agent-connector)](https://agentarmorhq.com/skills/anil-matcha-open-agent-connector)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/anil-matcha-open-agent-connector"><img src="https://agentarmorhq.com/api/badge/anil-matcha-open-agent-connector" alt="AgentArmorHQ Risk Grade for Open Agent Connector" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "anil-matcha-open-agent-connector"

Share with your security lead

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

### AgentArmorHQ Security Review Memo: open-agent-connector
- **Listing URL:** https://agentarmorhq.com/skills/anil-matcha-open-agent-connector
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 847 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 (Anil-matcha/open-agent-connector)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/Anil-matcha/open-agent-connector
- **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 19, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
Anil-matcha
Source code
github.com/Anil-matcha/open-agent-connector
Est. context load
~550 tokens / turn (~3 tool schemas, 0.27% of 200k context)
Popularity
847 GitHub stars
Last updated
2026-10-29
Last graded
2026-10-19

Community

Discussions for Open Agent Connector

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 Open Agent Connector 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