@ivotoby/openapi-mcp-server
An MCP server that exposes OpenAPI endpoints as resources
No outside reports on file
This connector gives your AI direct control over external web services, so only expose APIs you fully trust and carefully review what data the AI can read or modify.
Based on public adoption and transparency signals as of Oct 28, 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 reachLocal or standard API callsLOW
- CredentialsNo API token requiredLOW
- Package sourcenpm (@ivotoby/openapi-mcp-server)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y @ivotoby/openapi-mcp-serverAbout @ivotoby/openapi-mcp-server
This tool lets AI assistants call OpenAPI endpoints (web services with standard API descriptions) as if they were built-in resources. It reads an OpenAPI specification file and turns API calls into actions the AI can perform directly.
Who it’s for
Developers who want Claude or other AI systems to interact with web APIs and services. Useful for automating tasks that need to query or update data from external services.
Alternatives
- Anthropic's built-in tool use: Claude's native ability to call APIs via defined tools (no extra server needed).
- OpenAI's GPT with custom actions: Similar feature within the OpenAI ecosystem.
- LangChain OpenAPI toolkit: Python-based library for wrapping OpenAPI specs into LLM tools.
Setup
Check these steps against the project’s own instructions before running anything.
Install via npm: npm install @ivotoby/openapi-mcp-server. Then add to your Claude Desktop config file's mcpServers section with the OpenAPI spec URL or file path you want to expose.
Why this grade
Signal-based grade (3/7 points): listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- Weekly npm downloads
- 7.1k
- Listing last refreshed
- 2026-10-28
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
- API endpoint access: The server can call any endpoint described in the OpenAPI spec, potentially modifying data or triggering actions on your services. Bad specs could expose more than intended.
- Credential exposure: API keys or authentication tokens used by the server could be logged, cached, or leaked to the AI if not handled carefully.
- Malicious specs: A fake or compromised OpenAPI spec file could describe fake endpoints designed to trick the AI into sending sensitive data or making harmful requests.
- Unvalidated responses: The server may pass API responses directly to the AI without filtering, leaking secrets or internal details that were returned.
- No built-in rate limits: The AI could spam API calls, causing service degradation or unexpected billing charges.
How to lower the risk
Least-privilege permissions
- Provide only the OpenAPI endpoints the AI actually needs.
- Use read-only API keys or tokens where possible, never admin credentials.
Network isolation
- Firewall the server so it can only reach approved internal APIs.
- Never expose it to untrusted networks or the public internet.
Monitoring
- Log all API calls the server makes and review them regularly.
- Set up alerts for unusual patterns, large data transfers, or failed auth attempts.
Red flags to watch for
- OpenAPI specs from unknown or untrusted sources.
- Specs that reference sensitive endpoints (admin panels, payment systems, user data).
- Sudden spikes in API usage or errors after deployment.
Questions
How do I install @ivotoby/openapi-mcp-server?
Run npx -y @ivotoby/openapi-mcp-server in your terminal, or add the server entry to your claude_desktop_config.json or .cursor/mcp.json as shown in the Setup section on this page. Full setup docs and environment variables are in github.com/ivo-toby/mcp-openapi-server.
Are there security reports about @ivotoby/openapi-mcp-server?
No reports found for this package in our research (last checked 2026-10-29). @ivotoby/openapi-mcp-server currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include api endpoint access, credential exposure, malicious specs.
Is @ivotoby/openapi-mcp-server actively maintained?
@ivotoby/openapi-mcp-server has 7.1k weekly npm downloads. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/ivo-toby/mcp-openapi-server before pinning it in production.
What are alternatives to @ivotoby/openapi-mcp-server?
Notable alternatives to @ivotoby/openapi-mcp-server include Anthropic's built-in tool use (Claude's native ability to call APIs via defined tools (no extra server needed)), OpenAI's GPT with custom actions (Similar feature within the OpenAI ecosystem), LangChain OpenAPI toolkit (Python-based library for wrapping OpenAPI specs into LLM tools). You can also compare @ivotoby/openapi-mcp-server side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use @ivotoby/openapi-mcp-server? 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/ivo-toby-mcp-openapi-server)HTML embed:
<a href="https://agentarmorhq.com/skills/ivo-toby-mcp-openapi-server"><img src="https://agentarmorhq.com/api/badge/ivo-toby-mcp-openapi-server" alt="AgentArmorHQ Risk Grade for @ivotoby/openapi-mcp-server" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "ivo-toby-mcp-openapi-server"- Compare @ivotoby/openapi-mcp-server →
- Add to a team allowlist
- Claude and terminal guide →
- Download the PDF guide
Share with your security lead
Need sign-off to use @ivotoby/openapi-mcp-server? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: @ivotoby/openapi-mcp-server
- **Listing URL:** https://agentarmorhq.com/skills/ivo-toby-mcp-openapi-server
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Local or standard API calls
- **Credentials:** No API token required
- **Package source:** npm (@ivotoby/openapi-mcp-server)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts @ivotoby/openapi-mcp-server`
- **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 28, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- ivo-toby
- Source code
- github.com/ivo-toby/mcp-openapi-server
- Install command
- npm install @ivotoby/openapi-mcp-server
- Est. context load
- ~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
- Popularity
- 7.1k weekly npm downloads
- Last updated
- 2026-10-28
- Last graded
- 2026-10-28
Community
Discussions for @ivotoby/openapi-mcp-server
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