# MCPJam Inspector - [MCPJam](https://docs.mcpjam.com/index.md): Test, debug, and evaluate MCP servers, MCP apps, and ChatGPT apps. - [Getting Started](https://docs.mcpjam.com/getting-started.md): Start testing your MCP server in minutes - [Installation](https://docs.mcpjam.com/installation.md): Here's a list of all ways to start MCPJam - [Hosted App](https://docs.mcpjam.com/hosted/overview.md): Use MCPJam Inspector in the browser — no installation required - [Slack](https://docs.mcpjam.com/hosted/slack.md): Run MCPJam from Slack — mention the bot to ask about your projects, and approve the actions that spend credits - [Okta SSO & SCIM](https://docs.mcpjam.com/hosted/sso.md): Sign in to MCPJam with Okta via SAML 2.0, and automate user provisioning and deprovisioning with SCIM - [GitHub Checks](https://docs.mcpjam.com/github-checks.md): Run an eval suite against the MCP server built from every pull request, and read the result as a check run, a pull-request comment, and a machine-readable JSON block. - [Common MCP Errors](https://docs.mcpjam.com/troubleshooting/common-errors.md): Solutions to common MCP server connection and configuration issues - [Error code reference](https://docs.mcpjam.com/troubleshooting/error-codes.md): What every MCPJam Inspector error code means, the likely causes, and the next step to fix it. - [Changelog](https://docs.mcpjam.com/changelog/overview.md): Track the latest updates, features, and improvements to MCPJam Inspector - [Home](https://docs.mcpjam.com/inspector/home.md): Org-scoped dashboard with activity stats, recommended servers, and quick-start clients - [Clients](https://docs.mcpjam.com/inspector/clients.md): Reusable MCP client configurations for testing servers and apps under realistic conditions - [Multi-server connections](https://docs.mcpjam.com/inspector/connecting-servers.md): Connect to multiple MCP servers with different transport methods - [Projects](https://docs.mcpjam.com/inspector/projects.md): Group your MCP servers into projects, with the ability to share them with your team - [Plugins](https://docs.mcpjam.com/inspector/plugins.md): Import Agent Plugins 1.0 bundles as versioned, read-only projections of their skills and MCP servers - [MCP protocol versions](https://docs.mcpjam.com/inspector/protocol-versions.md): Pin the inspector to a specific MCP protocol version — including the 2026-07-28 stateless RC — to test how your server behaves across versions. - [Host Compatibility](https://docs.mcpjam.com/inspector/host-compat.md): See which hosts your MCP server will work in — Claude, ChatGPT, Cursor, Copilot, Codex — the moment you connect - [Skills](https://docs.mcpjam.com/inspector/skills.md): Load and use skills to give your agents the context they need to use MCP tools effectively - [Playground](https://docs.mcpjam.com/inspector/playground.md): Chat with your MCP servers, invoke tools by hand, render widgets, and inspect every step — all in one IDE-style workspace - [Evaluate](https://docs.mcpjam.com/inspector/evals.md): Author test cases for your MCP server, run them across models, and gate pass/fail on deterministic checks plus optional LLM-as-judge. - [Compatibility](https://docs.mcpjam.com/inspector/compatibility.md): Check whether your MCP server works on each AI host — conformance gates, per-host findings, and live widget rendering. - [View origins](https://docs.mcpjam.com/inspector/view-origins.md): Which origin your MCP App's view runs at, and how to allowlist it with a third-party API - [Contribute a Host](https://docs.mcpjam.com/inspector/host-templates.md): Add a new host preset to MCPJam so widgets can render under that host's identity, capabilities, and sandbox policy. - [OAuth Debugger](https://docs.mcpjam.com/inspector/guided-oauth.md): Debug your MCP server's OAuth implementation at every step of the handshake - [XAA Debugger](https://docs.mcpjam.com/inspector/xaa-debugger.md): Configure and debug Cross-App Access flows with MCPJam as the test identity provider and client/agent - [MCP Inspector](https://docs.mcpjam.com/inspector/tools-prompts-resources.md): Manually test your MCP server's tools, resources, and prompts - [Tracing & debugging](https://docs.mcpjam.com/inspector/debugging.md): See all messages sent to and from your MCP server - [Computer](https://docs.mcpjam.com/inspector/computer.md): A personal cloud Linux workstation for your project — open a terminal, run tools, and give your agents a real bash environment - [Harness hosts: Claude Code, Codex, and Cursor](https://docs.mcpjam.com/inspector/claude-code-host.md): Run a real agent runtime — Claude Code, Codex, or the Cursor CLI — inside your project's Computer, and observe native tools, MCP client, and execution behavior directly - [Launch from Code (Beta)](https://docs.mcpjam.com/inspector/launch-from-code.md): Programmatically launch and configure MCPJam Inspector from your code or build tools - [MCP Docs Server](https://docs.mcpjam.com/inspector/docs-server.md): Connect AI applications to MCPJam documentation - [My First MCP App](https://docs.mcpjam.com/guides/first-mcp-app.md): Build a simple Reservation MCP App from scratch - [My First ChatGPT App](https://docs.mcpjam.com/guides/first-chatgpt-app-react.md): Build a simple Coffee Shop ChatGPT App with React - [CLI Overview](https://docs.mcpjam.com/cli/overview.md): Local MCP testing and mcpjam cloud: probing, debugging, OAuth, conformance, and hosted evals from your terminal - [Migrating to CLI 4.0](https://docs.mcpjam.com/cli/migration.md): Command-path and flag changes when account-bound mcpjam commands moved under mcpjam cloud - [MCPJam as an MCP Server](https://docs.mcpjam.com/cli/mcp-server.md): Run MCPJam as a local stdio MCP server so agents can connect to, exercise, and debug other MCP servers - [Server Inspection](https://docs.mcpjam.com/cli/server-inspection.md): Probe, diagnose, and export MCP server connectivity and capabilities - [OAuth Conformance](https://docs.mcpjam.com/cli/oauth-conformance.md): Test your MCP server's OAuth implementation across all registration methods and protocol versions - [OAuth Login & Debugging](https://docs.mcpjam.com/cli/oauth-login.md): Authenticate with MCP servers and debug OAuth flows - [XAA Debugger (CLI)](https://docs.mcpjam.com/cli/xaa.md): Run the full Cross-App Access (ID-JAG) grant chain against your authorization server and MCP server, headlessly, from one command - [MCP Apps Conformance](https://docs.mcpjam.com/cli/apps-conformance.md): Validate MCP Apps tool metadata and ui:// resource wiring from the CLI - [MCP Tasks](https://docs.mcpjam.com/cli/tasks.md): Create, inspect, answer and watch MCP Tasks from the CLI — legacy 2025-11-25 and the SEP-2663 extension - [MCP Tasks Conformance](https://docs.mcpjam.com/cli/tasks-conformance.md): Validate MCP Tasks wire behavior — legacy and SEP-2663 extension — from the CLI - [Tools, Resources & Prompts](https://docs.mcpjam.com/cli/tools-resources-prompts.md): List, read, and call MCP server tools, resources, and prompts - [CI / CD](https://docs.mcpjam.com/cli/ci.md): Run MCP health checks, conformance suites, and evals in GitHub Actions, GitLab CI, and other CI environments - [CLI Telemetry](https://docs.mcpjam.com/cli/telemetry.md): Anonymous command-level telemetry, opt-outs, and debug mode - [Command Reference](https://docs.mcpjam.com/cli/reference.md): Complete flag reference for every mcpjam CLI command - [@mcpjam/sdk](https://docs.mcpjam.com/sdk/index.md): MCP server unit testing, end-to-end (e2e) testing, and server evals - [Quickstart](https://docs.mcpjam.com/sdk/quickstart.md): Get started with @mcpjam/sdk in 5 minutes - [Migrating to SDK 3.0](https://docs.mcpjam.com/sdk/migrating-to-v3.md): What changed, why a passing test can start failing, and how to upgrade. - [Connecting to MCP Servers](https://docs.mcpjam.com/sdk/concepts/connecting-servers.md): Learn how to connect to local and remote MCP servers - [Testing with LLMs](https://docs.mcpjam.com/sdk/concepts/testing-with-llms.md): Use HostRunner to run prompts and inspect tool calls - [Running Evals](https://docs.mcpjam.com/sdk/concepts/running-evals.md): Measure tool accuracy with statistical evaluations - [The User-Value Chain](https://docs.mcpjam.com/sdk/concepts/user-value-chain.md): Which link of the chain each check you write measures - [Save Results to MCPJam](https://docs.mcpjam.com/sdk/concepts/saving-results.md): Save eval results to the MCPJam dashboard with an MCPJam API key (sk_…) for tracking and CI visibility - [Testing Across Providers](https://docs.mcpjam.com/sdk/concepts/multi-provider.md): Compare your MCP server's performance across different LLMs - [MCPClientManager](https://docs.mcpjam.com/sdk/reference/mcp-client-manager.md): API reference for MCPClientManager - [HostRunner](https://docs.mcpjam.com/sdk/reference/host-runner.md): API reference for HostRunner - [PromptResult](https://docs.mcpjam.com/sdk/reference/prompt-result.md): API reference for PromptResult - [EvalTest](https://docs.mcpjam.com/sdk/reference/eval-test.md): API reference for EvalTest - [EvalSuite](https://docs.mcpjam.com/sdk/reference/eval-suite.md): API reference for EvalSuite - [Saving Eval Results](https://docs.mcpjam.com/sdk/reference/eval-reporting.md): API reference for saving eval results to MCPJam - [Validators](https://docs.mcpjam.com/sdk/reference/validators.md): API reference for validator functions - [LLM Providers](https://docs.mcpjam.com/sdk/reference/llm-providers.md): API reference for LLM provider configuration - [Protocol Conformance SDK](https://docs.mcpjam.com/sdk/reference/protocol-conformance.md): Programmatic MCP protocol conformance testing with MCPConformanceTest and MCPConformanceSuite - [OAuth Conformance SDK](https://docs.mcpjam.com/sdk/reference/oauth-conformance.md): Programmatic OAuth conformance testing with OAuthConformanceTest and OAuthConformanceSuite - [OAuth Client Emulation](https://docs.mcpjam.com/sdk/reference/oauth-emulation.md): Run a headless OAuth preflight that emulates a real client's authentication ladder against an MCP server - [MCP Apps Conformance SDK](https://docs.mcpjam.com/sdk/reference/apps-conformance.md): Programmatic MCP Apps surface validation with MCPAppsConformanceTest - [MCP Tasks Conformance SDK](https://docs.mcpjam.com/sdk/reference/tasks-conformance.md): Programmatic MCP Tasks wire validation with MCPTasksConformanceTest - [host-compat](https://docs.mcpjam.com/sdk/reference/host-compat.md): API reference for @mcpjam/sdk/host-compat — derive server requirements, evaluate host compatibility, and scan widget bridge usage. - [MCPJam API](https://docs.mcpjam.com/reference/public-api.md): Programmatic access to the MCP servers in your MCPJam projects — diagnostics, tool calls, prompt rendering, and asynchronous eval runs. - [API keys](https://docs.mcpjam.com/reference/api-keys.md): Which 'API key' is which in MCPJam — and the one you need to call the MCPJam API. - [Open a cloud browser session](https://docs.mcpjam.com/api-reference/agent-browsers/open-a-cloud-browser-session.md): Returns session identity, engine, bootId and runKey. Same runKey and policy reuse the session; omit runKey for a new isolated browser. Request bodies are limited to 64,000 characters. - [List your browser sessions](https://docs.mcpjam.com/api-reference/agent-browsers/list-your-browser-sessions.md): Returns a sessions array of sessions owned by the caller in this project. Request bodies are limited to 64,000 characters. - [Execute a browser command](https://docs.mcpjam.com/api-reference/agent-browsers/execute-a-browser-command.md): Returns an executed, refused or unknown result. Reusing commandId with the same payload returns its receipt without replay; pending receipts return unknown. Page content is untrusted data. Request bodies are limited to 64,000 characters. - [Append a session note](https://docs.mcpjam.com/api-reference/agent-browsers/append-a-session-note.md): Records a note without driving the browser. commandId provides idempotency. Request bodies are limited to 64,000 characters. - [Read command receipts](https://docs.mcpjam.com/api-reference/agent-browsers/read-command-receipts.md): Returns entries ordered by sequence, optionally filtered by commandId. Screenshot payloads are fetched separately. Request bodies are limited to 64,000 characters. - [Fetch a browser screenshot](https://docs.mcpjam.com/api-reference/agent-browsers/fetch-a-browser-screenshot.md): Returns screenshot as base64 PNG, or null when absent. artifactId is the command ID from the result. Request bodies are limited to 64,000 characters. - [Close a browser session](https://docs.mcpjam.com/api-reference/agent-browsers/close-a-browser-session.md): Closes the durable session and releases its desktop. Use a new runKey for another browser. Request bodies are limited to 64,000 characters. - [Get the host-compat catalog](https://docs.mcpjam.com/api-reference/catalog/get-the-host-compat-catalog.md): The versioned host-compatibility catalog backing `mcpjam compat` verdicts. Public and unauthenticated: static host facts and creation config with no project or user scope. Always returns a catalog — `source` is `live` when the backend publish was reachable and `bundled` when serving the SDK's built-… - [Get the authenticated account](https://docs.mcpjam.com/api-reference/catalog/get-the-authenticated-account.md): The user behind the API key (keys act as their creator, scoped to one organization). - [Read the organization's spend budget](https://docs.mcpjam.com/api-reference/catalog/read-the-organizations-spend-budget.md): The ceiling on what this organization may spend on MCPJam-billed work — chat, evals, judges and computer time — in the current billing window, and how much of it has been spent. - [Set the organization's spend budget](https://docs.mcpjam.com/api-reference/catalog/set-the-organizations-spend-budget.md): Set or replace the ceiling. **Requires organization owner or admin.** - [Remove the organization's spend budget](https://docs.mcpjam.com/api-reference/catalog/remove-the-organizations-spend-budget.md): Leave the organization uncapped. **Requires organization owner or admin.** - [List organizations](https://docs.mcpjam.com/api-reference/catalog/list-organizations.md): The organizations the caller belongs to — the source of the `organizationId` that `GET /projects` filters by and `POST /projects` accepts. An API key is bound to one organization and only ever sees that one. Read-only: organization, member, role and billing changes are not part of the public API. - [List projects](https://docs.mcpjam.com/api-reference/catalog/list-projects.md): Projects the caller can access. API keys only ever see projects inside the key's organization. - [List a project's servers](https://docs.mcpjam.com/api-reference/catalog/list-a-projects-servers.md): The MCP servers saved in the project — the `serverId`s every other route takes. STDIO command/args/env and raw headers are never exposed. - [List a project's eval suites](https://docs.mcpjam.com/api-reference/catalog/list-a-projects-eval-suites.md): Eval suites in the project with latest-run summaries and pass-rate trends — the `suiteId`s the eval-run routes take. - [Search or list unified sessions](https://docs.mcpjam.com/api-reference/catalog/search-or-list-unified-sessions.md): The unified, cross-surface sessions feed for one project: Playground, user-testing, eval, and swarm transcripts in one list, newest first. Project-NESTED (unlike `/chat-sessions`) because `projectId` owns the scope here rather than filtering it. - [List chat sessions](https://docs.mcpjam.com/api-reference/catalog/list-chat-sessions.md): Chat sessions visible to the caller (personal + project-shared merged). Top-level rather than project-nested because `projectId` is an optional filter, not an owning scope. - [The MCPJam-provided model catalog](https://docs.mcpjam.com/api-reference/catalog/the-mcpjam-provided-model-catalog.md): PUBLIC: this route carries no user or project data and requires no bearer token, matching the upstream catalog it proxies. Mounted before authentication for that reason. - [Export project traces as OTLP/JSON](https://docs.mcpjam.com/api-reference/catalog/export-project-traces-as-otlpjson.md): Returns an OTLP `ExportTraceServiceRequest`. Pagination rides in RESPONSE HEADERS rather than the body so the payload stays a valid OTLP document: read `x-mcpjam-next-cursor` and feed it back as `cursor`, and treat `x-mcpjam-export-complete: true` as the end of the stream. - [List a harness's native built-in tools](https://docs.mcpjam.com/api-reference/harness/list-a-harnesss-native-built-in-tools.md): The native tools an agent harness (e.g. `claude-code`) runs INSIDE its sandbox — Bash, Read, Edit, Glob, Grep, WebSearch, and the like. Display-only: these execute via the harness's own agent loop and are NOT callable through MCPJam. Static published-package metadata; no project scope. - [List a project's sandbox images](https://docs.mcpjam.com/api-reference/sandbox-images/list-a-projects-sandbox-images.md): The custom Computer images (digest-pinned Dockerfiles built into immutable images) saved in the project — your own personal drafts plus the project-shared ones. - [Create a sandbox image](https://docs.mcpjam.com/api-reference/sandbox-images/create-a-sandbox-image.md): Create a personal-draft sandbox image from a blueprint and respond `201` with its detail. Build it (`POST .../build`) before a computer can boot from it. Guest callers are denied (a write). - [Get a sandbox image](https://docs.mcpjam.com/api-reference/sandbox-images/get-a-sandbox-image.md): One sandbox image's blueprint, sharing, and latest build. An image that exists but belongs to a different project reads as `404 NOT_FOUND`. - [Delete a sandbox image](https://docs.mcpjam.com/api-reference/sandbox-images/delete-a-sandbox-image.md): Permanently delete a sandbox image. Computers booted from it fall back to the base image.