inspector

MCPJam Inspector is a local development client/emulator for ChatGPT Apps SDK and MCP apps/servers, providing an interactive widget emulator, MCP JSON-RPC tool/resource debugging, an OAuth flow debugger, and an LLM playground to test MCP servers against various models.

Evaluated Mar 30, 2026 (22d ago)
Homepage ↗ Repo ↗ DevTools mcp mcp-tools mcp-inspector chatgpt-apps-sdk oauth-debugger local-development debugging json-rpc developer-tools
⚙ Agent Friendliness
29
/ 100
Can an agent use this?
🔒 Security
36
/ 100
Is it safe for agents?
⚡ Reliability
30
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
45
Error Messages
0
Auth Simplicity
90
Rate Limits
0

🔒 Security

TLS Enforcement
60
Auth Strength
40
Scope Granularity
0
Dep. Hygiene
40
Secret Handling
40

No information is provided about how the tool handles secrets (API keys, OAuth tokens), TLS usage details, dependency scanning/CVE posture, or whether it logs sensitive OAuth/token data. Since it includes an OAuth debugger and an LLM playground, there is an inherent risk of credential exposure via logs/UI if not carefully designed, but this cannot be confirmed from the provided content.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
35
AF Security Reliability

Best When

You are iterating on an MCP server or ChatGPT/MCP app integration and need local, protocol-level visibility (JSON-RPC + OAuth) and a fast emulation/test loop.

Avoid When

You need a documented public REST/GraphQL API contract to integrate this tool directly as a backend dependency in your systems.

Use Cases

  • Emulate and test ChatGPT Apps/Widgets locally
  • Debug MCP server tools/resources/prompts via JSON-RPC logs
  • Inspect and troubleshoot OAuth handshakes for MCP servers/flows
  • Test MCP servers against different LLM providers/models
  • Verify server-exposed metadata (capabilities, instructions, widget metadata)

Not For

  • Not a hosted API service for production inference workloads
  • Not a security scanner/auditor for third-party code
  • Not a substitute for implementing your own OAuth/token verification in the MCP server

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

The README describes an OAuth debugger feature, but it does not document any authentication method required to use the inspector itself (e.g., API keys) nor any scope model for accessing inspector capabilities.

Pricing

Free tier: No
Requires CC: No

The README claims certain 'frontier models' are provided for free in the LLM playground, and also supports 'bring your own API key', but it does not provide a formal pricing/tiers breakdown.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Inspector is primarily a local UI/emulator rather than a programmatic service with documented endpoints; AI agents may need UI automation or reverse-engineering to operate it headlessly.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for inspector.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered