robots.txt
# robots.txt for mcpjam.com — all crawlers welcome.
# Content-Signal (see contentsignals.org) states how content may be used:
# search = build a search index / show in results
# ai-input = use as live AI input (RAG, grounding, answers)
# ai-train = use to train AI models
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: Claude-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: meta-externalagent
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Sitemap: https://www.mcpjam.com/sitemap.xml
llms.txt
# MCPJam
> Test and debug MCP servers, ChatGPT apps, and MCP apps. Open-source inspector,
> OAuth debugger, evals, and cross-client testing. Test your MCP server for
> every user, across every major AI client.
## Start here
- [Set yourself up to work with MCPJam](https://www.mcpjam.com/agent-setup.md): Choose a CLI or MCP workflow, connect your server, and verify its capabilities.
- [How to test an MCP server — the complete guide](https://www.mcpjam.com/mcp-server-testing): MCP server testing validates protocol, tool schemas, agent behavior, OAuth, and cross-client compatibility before production. The full workflow and a checklist.
## Developer resources
- [MCPJam API reference](https://docs.mcpjam.com/reference/public-api): REST API for the MCP servers in your MCPJam projects — diagnostics, tool calls, prompt rendering, and asynchronous eval runs.
- [MCPJam OpenAPI description](https://www.mcpjam.com/openapi.json): Machine-readable OpenAPI 3.1 description of the same API, written for function calling — unique operationIds, typed parameters, and typed response schemas throughout. Served from this domain; it redirects to the canonical copy the docs host publishes.
- MCPJam API base URL: https://app.mcpjam.com/api/v1 (in preview). Authenticate with `Authorization: Bearer <api key>`; a key is scoped to one organization.
- [MCPJam API keys](https://app.mcpjam.com/settings/api-keys): Create an API key yourself in Settings — no sales call, no waitlist.
- [MCPJam documentation](https://docs.mcpjam.com): Product documentation. Its own index for language models is at https://docs.mcpjam.com/llms.txt.
- [MCPJam Inspector on npm](https://www.npmjs.com/package/@mcpjam/inspector): Run the inspector locally with `npx @mcpjam/inspector@latest` — no account and no API key required.
- [MCPJam CLI on npm](https://www.npmjs.com/package/@mcpjam/cli): First-party MCP server and CLI (`@mcpjam/cli`) for running evals and conformance checks locally or in CI.
- [MCPJam source code](https://github.com/MCPJam/inspector): The open-source core — client, inspector, CLI, SDK, and local evals.
## Machine-readable endpoints on this domain
- [/robots.txt](https://www.mcpjam.com/robots.txt): Crawl rules plus a Content-Signal policy (search=yes, ai-input=yes, ai-train=yes).
- [/sitemap.xml](https://www.mcpjam.com/sitemap.xml): Every canonical URL on this domain, with last-modified dates.
- [/llms.txt](https://www.mcpjam.com/llms.txt): This file.
- [/index.md](https://www.mcpjam.com/index.md): Curated Markdown of the homepage. The pricing page has one too, at https://www.mcpjam.com/pricing.md.
- [/openapi.json](https://www.mcpjam.com/openapi.json): The OpenAPI description listed above, served from this domain.
- [/agent-setup.md](https://www.mcpjam.com/agent-setup.md): Setup instructions for coding agents — pick a CLI or MCP workflow, connect a server, verify its capabilities.
- [/blog/rss.xml](https://www.mcpjam.com/blog/rss.xml): RSS feed of the guides and articles listed below.
- [/.well-known/mcp](https://www.mcpjam.com/.well-known/mcp): MCP discovery manifest (SEP-1960) naming the hosted MCP server's endpoint, capabilities, and authorization server.
- [/.well-known/oauth/client-metadata.json](https://www.mcpjam.com/.well-known/oauth/client-metadata.json): OAuth Client ID Metadata Document identifying the MCPJam client app to OAuth-protected MCP servers.
- Content negotiation: `/` and `/pricing` answer `Accept: text/markdown` with the curated Markdown at /index.md and /pricing.md; other pages answer it with a Markdown conversion of the same page. Document routes also carry RFC 8288 `Link` headers with rel="service-doc" and rel="service-desc".
## Features
- [MCPJam Inspector — test & debug MCP servers locally](https://www.mcpjam.com/features/inspector): Open-source playground for MCP servers: connect a server, run its tools, compare models side by side, read the full waterfall trace. Free and npx-installable.
- [Test Agent Skills + MCP locally](https://www.mcpjam.com/features/skills): Load Anthropic Agent Skills alongside your MCP servers and watch a real model use both. Skills viewer plus an LLM playground, running locally with one npx command.
- [MCP OAuth & EMA Debugger: Visualize Auth Flows](https://www.mcpjam.com/features/oauth-debugger): The MCP OAuth Debugger visualizes every step of the auth flow so you see where it breaks, with spec conformance checks and EMA / XAA (Cross-App Access) tracing.
- [Cross-client testing for MCP servers](https://www.mcpjam.com/features/cross-client-testing): Generate an eval suite from your MCP server's tools, run it with a real model, and get accuracy, latency, and diagnosed failure patterns, not only protocol checks.
- [MCP testing SDK — @mcpjam/sdk](https://www.mcpjam.com/features/sdk): Test MCP servers in code with @mcpjam/sdk: connect clients, run unit and end-to-end tests, score agent-in-the-loop evals, and check OAuth conformance.
- [MCPJam CLI — test MCP servers from the terminal](https://www.mcpjam.com/features/cli): Probe, debug, and test MCP servers from the terminal with the MCPJam CLI: run a full health check, OAuth conformance, tool calls, and evals in CI.
- [CI/CD eval gates for MCP servers](https://www.mcpjam.com/features/ci-cd-actions): Gate every PR on how models use your MCP server. Wire MCPJam evals into GitHub Actions, track accuracy over time, and catch behavior regressions early.
- [User Testing — human acceptance testing for MCP](https://www.mcpjam.com/features/user-testing): Hosted, shareable UAT environments that mirror the major AI hosts. Testers break things safely, and their sessions become replayable regression tests.
- [Synthetic acceptance testing with Swarms](https://www.mcpjam.com/features/swarms): Turn loose AI personas that act like your users to acceptance-test your MCP server at scale, with multi-turn journeys across every client, before launch.
## Comparisons
- [MCPJam Inspector vs MCP Inspector (2026) — where the overlap ends](https://www.mcpjam.com/compare/mcpjam-vs-mcp-inspector): Honest side-by-side of MCPJam Inspector and the official MCP Inspector: protocol validation, OAuth debugging, tracing, evals, and when to use each. Tested hands-on.
- [MCP evals vs agent evals (2026) — what's the difference?](https://www.mcpjam.com/compare/mcp-evals-vs-agent-evals): Agent evals measure the agent you built. MCP evals measure how ChatGPT, Claude, or Cursor use your MCP server — what each covers and when you need both.
- [MCPJam vs Postman for MCP (2026) — which should you use?](https://www.mcpjam.com/compare/mcpjam-vs-postman): Honest comparison of MCPJam and Postman for testing MCP servers: protocol inspection, OAuth debugging, model-in-the-loop evals, open source, and when each wins.
- [MCPJam vs mcp-use (2026) — build vs test your MCP server](https://www.mcpjam.com/compare/mcpjam-vs-mcp-use): MCPJam vs mcp-use: mcp-use is a framework to build MCP servers and agents; MCPJam is a dedicated tool to test, debug, and eval them. Both open source.
- [MCPJam vs Alpic (2026) — test your MCP server vs deploy it](https://www.mcpjam.com/compare/mcpjam-vs-alpic): MCPJam vs Alpic: Alpic deploys, hosts, and monitors MCP servers in production; MCPJam is a deployment-neutral tool to test, debug, and evaluate them.
## Who it's for
- [MCPJam for developers — test MCP servers as you build](https://www.mcpjam.com/for/developers): Reproduce any MCP failure in minutes: run your server through a real agent, read the trace, debug OAuth step by step, and gate PRs with evals. Free and open source.
- [MCPJam for engineering managers — reliability as a gate](https://www.mcpjam.com/for/engineering-managers): Make MCP reliability a merge gate: evals on every PR, failures your team can reproduce, and client coverage maintained for you instead of by your engineers.
- [MCPJam for product managers — launch-ready MCP](https://www.mcpjam.com/for/product-managers): Know if your MCP integration is launch-ready: pass rates on realistic requests, failure patterns named, and tester sessions you can replay before users hit them.
- [MCPJam for AI & platform leads — one MCP quality bar](https://www.mcpjam.com/for/ai-platform-leads): Standardize how every team tests MCP: one platform for local testing, CI gates, and cross-client coverage — open-source inspector plus a hosted team platform.
- [MCPJam for marketers — reach users inside ChatGPT & Claude](https://www.mcpjam.com/for/marketers): ChatGPT and Claude are where your users work now. Ship an MCP integration that performs in every client, with cross-client test evidence before every launch.
- [MCPJam for MCP client teams — parity and coverage](https://www.mcpjam.com/for/mcp-clients): MCPJam tracks what the major AI clients support and how servers behave in each. If you build an MCP client, stay at parity with ChatGPT and Claude.
- [MCPJam for enterprise — SSO, compliance, and support](https://www.mcpjam.com/for/enterprise): Adopt MCP testing without new risk: SSO/SAML, RBAC, audit retention, SOC 2 (in progress), and an SLA. Strictly pre-production — it never touches live traffic.
## MCP clients directory
- [MCP clients directory](https://www.mcpjam.com/clients): Every MCP client we track, with capabilities and testing walkthroughs.
## Latest guides and articles
- [ChatGPT Plugin Extensions: what changes for app builders](https://www.mcpjam.com/blog/chatgpt-plugin-extensions): Sidebar apps, conversation panels, file viewers, composer mentions, and rich forms: what OpenAI's Plugin Extensions let your app do inside ChatGPT, how they build on MCP Apps, and what to test.
- [How to Build an MCP Server in TypeScript: Step-by-Step Guide](https://www.mcpjam.com/blog/build-mcp-server-typescript): Learn how to build a secure, production-ready Model Context Protocol (MCP) server in TypeScript using the v2 SDK. Master tools, resources, and prompts.
- [OpenAI DevDay 2026: what matters for plugin builders](https://www.mcpjam.com/blog/openai-devday-2026): Organic discovery, Plugin Extensions, and Dots: the three OpenAI DevDay 2026 announcements that matter most if you build ChatGPT plugins or MCP servers, and what to do about them.
- [Multi-account connections in MCPJam](https://www.mcpjam.com/blog/multi-account-connections): How multi-account connections let an agent pull data from several accounts of the same app through one MCP server, how ChatGPT routes each tool call with link_id, and how to test it in MCPJam.
- [WebMCP Testing: How to Test and Debug Tools](https://www.mcpjam.com/blog/test-webmcp): Learn how to test and debug WebMCP tools with MCPJam Inspector and Playground. Follow a pizza demo to inspect tool calls, inputs, and agent behavior.
- [Swarms, User Testing, Evals, and CI/CD for MCP servers](https://www.mcpjam.com/blog/our-new-platform): Run User Testing, Swarms, Evals, and CI/CD gates on your MCP server to see if users actually succeed in ChatGPT, Claude, and Copilot. Test local servers via desktop app, CLI, or SDK.
- [MCPJam vs MCP Inspector V2: Choosing the Right MCP Testing Tool](https://www.mcpjam.com/blog/mcpjam-vs-mcp-inspector-v2): Compare MCPJam and MCP Inspector V2 for testing Model Context Protocol (MCP) servers. Learn when to use protocol testing versus end-to-end agent behavior evaluations.
- [MCP Client Changelog August 2026: Host Updates & What to Test](https://www.mcpjam.com/blog/mcp-client-changelog-august-2026): The August 2026 MCP Client Changelog. See what changed in Cline, Goose, Claude Code, Codex, Claude, AgentCore, GitHub Copilot, and VS Code, and what to test in your MCP server.
- [MCP Client Changelog July 2026: Host Updates & What to Test](https://www.mcpjam.com/blog/mcp-client-changelog-july-2026): Read the July 2026 MCP Client Changelog. Discover critical updates for Claude, ChatGPT, Goose, Codex, Cline, and AgentCore, and how to test your MCP servers.
- [MCPJam now supports Skills over MCP](https://www.mcpjam.com/blog/skills-over-mcp-charter): Test the tools and the workflow instructions delivered by an MCP server in one place.
- [Jeppesen ForeFlight uses MCPJam to iterate 10x faster on AI experiences for pilots](https://www.mcpjam.com/blog/foreflight-mcpjam): How MCPJam supports secure, personalized flight app experiences for the 75% of US pilots using ForeFlight.
- [MCP Inspector V2 Guide: Setup, Debugging & Alternatives](https://www.mcpjam.com/blog/mcp-inspector-v2-guide): MCP Inspector is the official MCP debugging toolkit. See what's new in V2, including Web/CLI/TUI, OAuth, and transports, plus how it compares to MCPJam.
## Key facts
- The MCPJam Inspector core (client, inspector, CLI, SDK, local evals) is open source and free: https://github.com/MCPJam/inspector
- MCPJam runs locally via `npx @mcpjam/inspector@latest` — no ngrok, no ChatGPT subscription.
- Docs: https://docs.mcpjam.com · App: https://app.mcpjam.com
