openinference
OpenTelemetry Instrumentation for AI Observability
No outside reports on file
This tool is useful for monitoring but requires careful setup to avoid sending sensitive AI conversations to external services and to prevent credential leaks in telemetry data.
Based on public adoption and transparency signals as of Oct 23, 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
- CredentialsNo API token requiredLOW
- Package sourcenpm (@arizeai/openinference-instrumentation-mcp)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y @arizeai/openinference-instrumentation-mcpAbout Openinference
This tool tracks and monitors AI applications by collecting detailed information about what they do (called telemetry). It uses OpenTelemetry, an open standard for observability, to help developers see how their AI systems behave and find problems.
Who it’s for
Developers building AI applications who want visibility into performance, debugging, and behavior tracking. Teams using Arize or other monitoring platforms to understand their AI models in production.
Alternatives
- Langsmith (LangChain's native observability tool)
- Datadog APM (general application performance monitoring)
- New Relic (enterprise observability platform)
- Custom logging (simple file-based telemetry without external dependencies)
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/Arize-ai/openinference (opens external site) for installation and configuration instructions specific to your setup.
Why this grade
Signal-based grade (4/7 points): well starred on GitHub, listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.3k
- Weekly npm downloads
- 3.6k
- Listing last refreshed
- 2026-10-27
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
- Access to AI conversation data: This tool collects detailed traces of what your AI sees and does, including prompts and responses, which could contain sensitive information
- Credential exposure in traces: API keys, tokens, or private data might accidentally be captured in the detailed logs it collects
- Third-party data transmission: Collected telemetry is typically sent to external monitoring systems (like Arize) over the network, requiring secure connections
- Malicious trace injection: If an attacker can feed data into your AI system, they might hide malicious instructions in traces that could confuse debugging or analysis
- Information leakage through metrics: Even anonymized performance data can sometimes reveal patterns about your AI's training data or behavior
How to lower the risk
Least-privilege permissions
- Only grant this tool access to necessary AI model inputs and outputs
- Restrict which applications or services can send telemetry
Network isolation
- Only allow connections to trusted monitoring endpoints (verify the domain)
- Use encrypted connections (HTTPS/TLS) for all telemetry transmission
Monitoring
- Review what data is being collected regularly
- Set alerts if unusual amounts of data are sent to external services
Red flags to watch for
- Traces containing passwords, API keys, or personal information
- Unexpected external domains receiving telemetry
- Performance degradation or excessive memory use from collection
Questions
How do I install Openinference?
Run npx -y @arizeai/openinference-instrumentation-mcp 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/Arize-ai/openinference.
Are there security reports about Openinference?
No reports found for this package in our research (last checked 2026-10-29). Openinference currently holds Grade B (Some risk signals) based on public adoption and transparency signals. Key risk areas to watch include access to ai conversation data, credential exposure in traces, third-party data transmission.
Is Openinference actively maintained?
Openinference has 1.3k GitHub stars and 3.6k weekly npm downloads. Our directory data was last refreshed on 2026-10-27. Check recent commit activity, release tags, and open issues at github.com/Arize-ai/openinference before pinning it in production.
What are alternatives to Openinference?
Notable alternatives to Openinference include Langsmith, Datadog APM, New Relic, Custom logging. You can also compare Openinference side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Openinference? 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/arize-ai-openinference)HTML embed:
<a href="https://agentarmorhq.com/skills/arize-ai-openinference"><img src="https://agentarmorhq.com/api/badge/arize-ai-openinference" alt="AgentArmorHQ Risk Grade for Openinference" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "arize-ai-openinference"Share with your security lead
Need sign-off to use openinference? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: openinference
- **Listing URL:** https://agentarmorhq.com/skills/arize-ai-openinference
- **Type:** App connector
- **Risk Grade:** Grade B (Some risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.3k GitHub stars, 3.6k 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:** No API token required
- **Package source:** npm (@arizeai/openinference-instrumentation-mcp)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts @arizeai/openinference-instrumentation-mcp`
- **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
- Arize-ai
- Source code
- github.com/Arize-ai/openinference
- Install command
- npm install @arizeai/openinference-instrumentation-mcp
- Est. context load
- ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context)
- Popularity
- 1.3k GitHub stars, 3.6k weekly npm downloads
- Last updated
- 2026-10-27
- Last graded
- 2026-10-23
Community
Discussions for Openinference
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