AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Observability/
inspector
inspector logo

inspector

Active·★ 2.3k·NOASSERTION·Updated 2026-10-22

MCPJam describes itself as the development platform for MCP servers, MCP apps and ChatGPT apps. Its README lists seven capabilities: debugging every JSON-RPC message and OAuth exchange with full traces, chatting with any LLM against your server while seeing tool calls and context, inspecting a server's tools, resources and prompts, running evals across several LLMs and tracking accuracy over time, a CLI for probing servers, running doctor checks and exercising OAuth flows, an SDK for assertions in your own tests, and CI/CD integration for end-to-end tests, evals, OAuth checks and spec conformance on every pull request.

There are four ways to run it. The hosted web app at app.mcpjam.com needs no install but only supports HTTPS server URLs and has no STDIO, tunneling, skills or tasks. The desktop app (macOS and Windows installers) supports HTTP/S and local STDIO servers without Node.js. In a terminal, `npx @mcpjam/inspector@latest` needs Node.js 20 or newer and prints a localhost URL. With Docker, `docker run -p 127.0.0.1:6274:6274 mcpjam/mcp-inspector` works, and the README says to always bind to 127.0.0.1 to keep the inspector local-only. The npm badge and README mention Apache-2.0, while GitHub's license detection shows none, so check the repository before redistributing.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-18.

License
Not detected by GitHub
Latest release
v3.16.1 · 2026-10-15
Last commit
2026-10-18
Contributors
162
Forks
296
Open issues and PRs
372
First published
2025-05-23
npm package
@mcpjam/inspector 3.16.1 · 5,832 downloads last week

Source: GitHub, npm and PyPI public APIs.

#anthropic#chatgpt#cicd#debugger#evals#evaluation#inspector#mcp
$ Install
$ npx @mcpjam/inspector@latest
↗ Visit site★ GitHub
01

Features

01Debug: Inspect JSON-RPC messages and OAuth exchanges with full traces.
02Chat: Interact with any LLM against your server, with full trace visibility into tool calls and context.
03Inspect: Explore your server’s tools, resources, and prompts in a single interface.
04Evaluate: Run evaluations across multiple LLMs and track accuracy over time to catch regressions.
05CI/CD: Integrate CLI and SDK into pipelines (e.g., GitHub Actions) for automated testing, evals, and OAuth checks.
02

Why choose it

+Covers the whole MCP development loop: inspect, chat, trace, OAuth debugging, evals, CLI, SDK and CI
+Four ways to run it, from a hosted web app with no install to a local Docker image
+Evals across several LLMs let you catch regressions in how models use your tools
+CLI and SDK can run in GitHub Actions for conformance and OAuth checks on every PR
03

Trade-offs

!The hosted web app only supports HTTPS servers, with no STDIO, tunneling, skills or tasks
!Chat and evals call real LLMs, so check where your server data and prompts are sent
!Many features at once (App Builder, Workspaces, Evals) make it heavier to learn than a simple inspector
!License signals are mixed: Apache-2.0 in the README badge, none detected by GitHub
04

Maintenance check

ActiveChecked: 2026-10-22
Last commit
2026-10-22
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v3.16.2 (2026-10-20)
Open issues
314
Recent issues with at least one comment
—
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 130, 208, 174, 157, 172, 219, 257, 225, 145, 221, 240, 71

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

05

Compatibility

Web
Hosted Web
Verified via docs
macOS
Desktop App
Verified via docs
Windows
Desktop App
Verified via docs
Node.js
CLI
Verified via docs
Docker
Container
Verified via docs
06

Quick start

1
$ npx @mcpjam/inspector@latest
07

Use cases

↳Local Development & Debugging: Rapidly iterate on MCP projects, debug server issues, and test OAuth flows without external tunnels.
↳Automated Testing & CI/CD: Integrate into GitHub Actions or other CI/CD pipelines to run end-to-end tests, evaluations, and specification conformance checks on every pull request.
↳Team Collaboration: Share server configurations and collaborate in real-time on debugging and evaluation within shared workspaces.
08

Alternatives

⚡Top VS:
VSmcp-dap-server★105→VSMCPSpend★71→VSSephera★77→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start
mcs-mcp
★18
→
mcp-dap-server logo
mcp-dap-server★ 105
MCP server to communicate with DAP servers allowing AI Agents the ability to debug live programs.
VSCompare→
MCPSpend logo
MCPSpend★ 71
Real-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted
VSCompare→
Sephera logo
Sephera★ 77
Fast local-first Rust CLI for codebase metrics, AST-compressed LLM context bundles, and built-in MCP server.
VSCompare→
mcs-mcp logo
mcs-mcp★ 18
Provide Monte-Carlo-Simulation and Flow Data diagnostics to AI Agents
VSCompare→
OpenStudy logo
OpenStudy★ 76
Self-hostable study dashboard with a built-in MCP server so Claude can read, write, and teach from your courses, lectures, and deadlines — Making better use of your Claude/ChatGPT subscription
VSCompare→
study-dashboard logo
study-dashboard★ 76
Self-hostable study dashboard with an MCP connector so Claude (claude.ai, Claude Desktop, Claude Code or any Claude surface) can read and write your coursework.
VSCompare→
mcp-ssh-manager logo
mcp-ssh-manager★ 515
MCP SSH Server: 37 tools for remote SSH management | Claude Code & OpenAI Codex | DevOps automation, backups, database operations, health monitoring
VSCompare→
prometheus-mcp-server logo
prometheus-mcp-server★ 519
A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
VSCompare→
See all alternatives →
07
Use cases
08Alternatives
MCPJam /
inspector
↗

Development platform for debugging, testing and evaluating MCP servers and apps

2.3k296
Last commit1d ago
StatusActive
CategoryObservability
Contributors162
Latest releasev3.16.1
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit