ai_agents_api_library
Verified catalog of 300+ APIs and MCP servers with opinions and statistics so that AI agents can call after a one-time API key/OAuth setup. JSON, llms.txt and an MCP server for agents.
No outside reports on file
This tool is convenient but creates a larger attack surface—it trusts both the catalog authors and hundreds of external APIs, so careful credential management and limiting which APIs the agent can actually call are essential.
Based on public adoption and transparency signals as of Oct 19, 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 sourcenpm (ai-agents-api-library)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y ai-agents-api-libraryEverything 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.
About AI Agents API Library
This tool catalogs over 300 APIs and MCP servers (a standard for connecting AI to external tools) and provides setup instructions for each. It includes opinions on which APIs work well, statistics about them, and an MCP server you can run so AI agents can browse the catalog and call APIs after you've set up API keys or OAuth once.
Who it’s for
AI developers and teams building agents that need to connect to many third-party services without manually coding each integration. It's useful if you want to let your AI use multiple APIs safely by handling authentication upfront.
Alternatives
- Langchain integrations: A Python library with built-in connections to hundreds of tools and APIs. - Zapier API / Make (Integromat): Web-based platforms for connecting apps without writing code; offer more UI controls but less direct AI agent integration. - OpenAI / Anthropic native tool calling: Build custom tool definitions directly in your agent code rather than relying on a pre-built catalog.
Setup
Check these steps against the project’s own instructions before running anything.
Install via npm:
npm install ai-agents-api-library
Or check the GitHub repository at github.com/eater2/ai_agents_api_library for other installation methods and how to run as an MCP server. Follow the project's README for detailed setup of API keys and OAuth tokens.
Why this grade
Signal-based grade (2/7 points): listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 32
- Weekly npm downloads
- 56
- 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
- API key exposure: The tool stores API keys and OAuth tokens, so if the tool is compromised or misconfigured, attackers could steal credentials for hundreds of services. - Fake catalog entries: Attackers could publish malicious APIs in the catalog that look legitimate but steal data or run harmful commands when called by your agent. - Overly broad permissions: If you grant the agent permission to call any API in the catalog, it could access sensitive services you didn't intend (email, billing, etc.) without additional safeguards. - Data leakage through APIs: APIs you call may log or store the data your agent sends, including internal information the agent shouldn't expose. - Supply chain attack: Updates to the package or catalog could introduce malicious APIs or alter existing ones without obvious warning.
How to lower the risk
Least-privilege permissions
- Only enable APIs your agent genuinely needs; don't allow access to the full catalog.
- Use restricted API keys or scoped OAuth tokens (e.g., read-only) whenever possible.
Network isolation
- Run the MCP server on a separate machine or container from your main application.
- Use a firewall or VPN to limit which APIs the agent can reach.
Monitoring
- Log all API calls the agent makes, including what data it sends and receives.
- Set up alerts if the agent tries to call an unexpected API or uses unusual amounts of data.
Red flags to watch for
- Sudden new APIs appearing in the catalog or changes to existing ones.
- The agent requesting API credentials or attempting to modify catalog entries.
- API responses that seem corrupted, extremely large, or contain executable code.
Questions
How do I install AI Agents API Library?
Run npx -y ai-agents-api-library 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/eater2/ai_agents_api_library.
Are there security reports about AI Agents API Library?
No reports found for this package in our research (last checked 2026-10-30). AI Agents API Library currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include api key exposure.
Is AI Agents API Library actively maintained?
AI Agents API Library has 32 GitHub stars and 56 weekly npm downloads. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/eater2/ai_agents_api_library before pinning it in production.
What are alternatives to AI Agents API Library?
Notable alternatives to AI Agents API Library include Langchain integrations (A Python library with built-in connections to hundreds of tools and APIs. - **Zapier API / Make (Integromat)**: Web-based platforms for connecting apps without writing code). You can also compare AI Agents API Library side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use AI Agents API Library? 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/eater2-ai-agents-api-library)HTML embed:
<a href="https://agentarmorhq.com/skills/eater2-ai-agents-api-library"><img src="https://agentarmorhq.com/api/badge/eater2-ai-agents-api-library" alt="AgentArmorHQ Risk Grade for AI Agents API Library" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "eater2-ai-agents-api-library"- Compare AI Agents API Library →
- Add to a team allowlist
- Claude and terminal guide →
- Download the PDF guide
Share with your security lead
Need sign-off to use ai_agents_api_library? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: ai_agents_api_library
- **Listing URL:** https://agentarmorhq.com/skills/eater2-ai-agents-api-library
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 32 GitHub stars, 56 weekly npm downloads
#### 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:** npm (ai-agents-api-library)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts ai-agents-api-library`
- **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
- eater2
- Source code
- github.com/eater2/ai_agents_api_library
- Install command
- npm install ai-agents-api-library
- Est. context load
- ~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
- Popularity
- 32 GitHub stars, 56 weekly npm downloads
- Last updated
- 2026-10-29
- Last graded
- 2026-10-19
Community
Discussions for AI Agents API Library
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