agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.
No outside reports on file
Agent-inspect is a development aid that handles sensitive agent behavior data—guard evidence files like source code, keep CI logs private, and assume any shared traces could reveal how your agent works.
Based on public adoption and transparency signals as of Oct 29, 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 (agent-inspect)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y agent-inspectEverything 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: B (from public signals such as stars and downloads, not a code review). Graded 2026-10-29.
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 Agent Inspect
Agent-inspect is a debugging tool for TypeScript AI agents that lets you inspect how an agent made decisions, check what tools it called, and test whether it took the right path. It can run offline and save evidence (logs and traces) that you can share safely or use in automated tests.
Who it’s for
TypeScript developers building AI agents who want to catch bugs in agent behavior before shipping code. Teams using CI/CD pipelines who need to verify agents make correct tool choices.
Alternatives
- Langsmith (LangChain's tracing): Agent tracing and inspection for LLM workflows
- OpenTelemetry: General-purpose tracing and observability for any application
- Custom logging + grep: Manual log inspection for TypeScript agent runs
Setup
Check these steps against the project’s own instructions before running anything.
Install via npm:
npm install agent-inspect
Then import and use in your agent code. Follow the project's README for detailed setup with your specific agent framework.
Why this grade
Signal-based grade (4/7 points): listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 168
- Weekly npm downloads
- 23.6k
- 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
- Access to agent logs and traces: The tool inspects your agent's decision-making data, which may include sensitive prompts, user inputs, or tool results—keep this data private
- Exposes agent behavior patterns: Shared evidence files could reveal how your agent works, what tools it has, or what it was asked to do
- No input sanitization guarantee: If agent logs contain malicious text (e.g., prompt injection attempts), the inspection UI could execute that text if not carefully handled
- Offline claim is only as good as what you inspect: Even offline tools can leak data if you upload or share the evidence files carelessly
- CI pipeline exposure: Test output and logged evidence might be visible in build logs or artifacts accessible to unintended people
How to lower the risk
Least-privilege permissions
- Run only on machines where developers already have code access
- Restrict who can see or download evidence files and CI logs
Network isolation
- Use offline mode; don't auto-upload traces to untrusted services
- Keep evidence storage on internal servers, not public cloud storage
Monitoring
- Audit who accesses agent evidence files regularly
- Check CI logs for accidental leaks of sensitive prompts or user data
Red flags to watch for
- Evidence files shared via Slack, email, or public forums
- CI output containing full agent traces or internal tool names
- No way to redact sensitive fields before sharing
Questions
How do I install Agent Inspect?
Run npx -y agent-inspect 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/rajudandigam/agent-inspect.
Are there security reports about Agent Inspect?
No reports found for this package in our research (last checked 2026-10-30). Agent Inspect currently holds Grade B (Some risk signals) based on public adoption and transparency signals. Key risk areas to watch include access to agent logs and traces, exposes agent behavior patterns, no input sanitization review.
Is Agent Inspect actively maintained?
Agent Inspect has 168 GitHub stars and 23.6k 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/rajudandigam/agent-inspect before pinning it in production.
What are alternatives to Agent Inspect?
Notable alternatives to Agent Inspect include Langsmith (LangChain's tracing) (Agent tracing and inspection for LLM workflows), OpenTelemetry (General-purpose tracing and observability for any application), Custom logging + grep (Manual log inspection for TypeScript agent runs). You can also compare Agent Inspect side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Agent Inspect? 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/rajudandigam-agent-inspect)HTML embed:
<a href="https://agentarmorhq.com/skills/rajudandigam-agent-inspect"><img src="https://agentarmorhq.com/api/badge/rajudandigam-agent-inspect" alt="AgentArmorHQ Risk Grade for Agent Inspect" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "rajudandigam-agent-inspect"Share with your security lead
Need sign-off to use agent-inspect? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: agent-inspect
- **Listing URL:** https://agentarmorhq.com/skills/rajudandigam-agent-inspect
- **Type:** App connector
- **Risk Grade:** Grade B (Some risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 168 GitHub stars, 23.6k weekly npm downloads
#### 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 (agent-inspect)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts agent-inspect`
- **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 29, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- rajudandigam
- Source code
- github.com/rajudandigam/agent-inspect
- Install command
- npm install agent-inspect
- Est. context load
- ~900 tokens / turn (~5 tool schemas, 0.45% of 200k context)
- Popularity
- 168 GitHub stars, 23.6k weekly npm downloads
- Last updated
- 2026-10-29
- Last graded
- 2026-10-29
Community
Discussions for Agent Inspect
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