# MCPJam Inspector

## Docs

- [Get the authenticated account](https://mcpjam-platform-api-keys.mintlify.app/api-reference/catalog/get-the-authenticated-account.md): The user behind the API key (keys act as their creator, scoped to one organization).
- [List a project's eval suites](https://mcpjam-platform-api-keys.mintlify.app/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.
- [List a project's servers](https://mcpjam-platform-api-keys.mintlify.app/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 chat sessions](https://mcpjam-platform-api-keys.mintlify.app/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.
- [List projects](https://mcpjam-platform-api-keys.mintlify.app/api-reference/catalog/list-projects.md): Projects the caller can access. API keys only ever see projects inside the key's organization.
- [Get a chatbox](https://mcpjam-platform-api-keys.mintlify.app/api-reference/chatboxes/get-a-chatbox.md): One chatbox's full read-only settings: model, system prompt, tool-approval policy, attached servers, and share link. A chatbox that exists but belongs to a different project reads as `404 NOT_FOUND`.
- [List a project's chatboxes](https://mcpjam-platform-api-keys.mintlify.app/api-reference/chatboxes/list-a-projects-chatboxes.md): The chatboxes published from this project — name, access mode, attached servers, and share link. Read-only.
- [Boot your computer from an environment](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/boot-your-computer-from-an-environment.md): Attach the environment to the caller's computer, which re-provisions it from the pinned image (installed files are wiped). The environment must have a `ready` build, and the computer provider must match the build's. Bodyless. Guest callers are denied (a write).
- [Build a computer environment](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/build-a-computer-environment.md): Trigger a build of the environment's image and respond `202`. The build runs asynchronously — poll the builds list for status. Bodyless. Guest callers are denied (a write).
- [Create a computer environment](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/create-a-computer-environment.md): Create a personal-draft environment from a Dockerfile and respond `201` with its detail. Build it (`POST .../build`) before a computer can boot from it. Guest callers are denied (a write).
- [Delete a computer environment](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/delete-a-computer-environment.md): Permanently delete an environment. Computers booted from it fall back to the base image. Deleting a project-shared environment requires project admin. Bodyless — any field is rejected. Guest callers are denied (a write).
- [Get a computer environment](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/get-a-computer-environment.md): One environment's Dockerfile, sharing, and latest build. An environment that exists but belongs to a different project reads as `404 NOT_FOUND`.
- [List a project's computer environments](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/list-a-projects-computer-environments.md): The custom Computer images (digest-pinned Dockerfile environments) saved in the project — your own personal drafts plus the project-shared ones.
- [List an environment's builds](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/list-an-environments-builds.md): An environment's builds, newest first, each with its status and capped log preview.
- [Reset your computer to its image](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/reset-your-computer-to-its-image.md): Reset the caller's computer back to its current image, wiping mutable state. Bodyless. Guest callers are denied (a write).
- [Share an environment with the project](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/share-an-environment-with-the-project.md): Promote a personal-draft environment to a project-shared one. Requires project admin. Bodyless. Guest callers are denied (a write).
- [Update a computer environment](https://mcpjam-platform-api-keys.mintlify.app/api-reference/computer-environments/update-a-computer-environment.md): Edit an environment's name and/or Dockerfile. Re-build it for the changes to take effect on a computer. Guest callers are denied (a write).
- [Cancel a run](https://mcpjam-platform-api-keys.mintlify.app/api-reference/eval-runs/cancel-a-run.md): Request cancellation of an in-flight run; marks the run and its pending/running iterations `cancelled`. A no-op success when the run is already cancelled; returns `409` when the run already reached a terminal status (`completed`/`failed`/`timed_out`).
- [Create an eval run (async)](https://mcpjam-platform-api-keys.mintlify.app/api-reference/eval-runs/create-an-eval-run-async.md): Creates a suite run from an existing `suiteId` (rerun) and/or inline `tests`, then **detaches execution and responds `202` immediately** with the `runId`. Validation and quota errors surface on this request; poll `GET /eval-runs/{runId}` for progress. The run appears live in the hosted UI Runs tab,…
- [Create an eval suite (author-only, does not run)](https://mcpjam-platform-api-keys.mintlify.app/api-reference/eval-runs/create-an-eval-suite-author-only-does-not-run.md): Creates a runnable eval suite — the suite record plus its test cases — and responds `201` **synchronously**, WITHOUT executing anything. Use this to author a suite, then run it later with `POST /eval-runs` (passing the returned `suiteId`).
- [Get an iteration trace](https://mcpjam-platform-api-keys.mintlify.app/api-reference/eval-runs/get-an-iteration-trace.md): Full trace envelope for one iteration: conversation messages, expected-vs-actual tool call analysis, and spans. The shape is rich and may evolve — treat it as an open document. Returns `404` with `details.reason: "TRACE_NOT_AVAILABLE"` when the iteration finished without a stored trace.
- [Get an iteration's step results](https://mcpjam-platform-api-keys.mintlify.app/api-reference/eval-runs/get-an-iterations-step-results.md): One row per authored test step, in order, with `status` (`ok`/`fail`/`skipped`/`pending`), a `reason`, and any `evidence` (screenshots, replay-video offset, widget tool calls). The fastest way to see which step failed and why. Unlike `/trace`, a missing trace is not a `404` — step verdicts still ret…
- [Get run status](https://mcpjam-platform-api-keys.mintlify.app/api-reference/eval-runs/get-run-status.md): Run status, result, and summary. Poll until `status` is terminal (`completed`, `failed`, or `cancelled`).
- [List a suite's runs](https://mcpjam-platform-api-keys.mintlify.app/api-reference/eval-runs/list-a-suites-runs.md): Recent runs for a suite, newest first.
- [List run iterations](https://mcpjam-platform-api-keys.mintlify.app/api-reference/eval-runs/list-run-iterations.md): Per-iteration results: actual tool calls, structured token usage, and latency. Cursor-paginated.
- [Call a tool](https://mcpjam-platform-api-keys.mintlify.app/api-reference/execution/call-a-tool.md): Executes a tool on the server and returns the MCP `CallToolResult` directly. Tool-level failures (`isError: true` in the result) are **successful calls** — the server answered; only transport/auth errors use the error envelope.
- [Render a prompt](https://mcpjam-platform-api-keys.mintlify.app/api-reference/execution/render-a-prompt.md): Renders a prompt with arguments and returns the MCP `GetPromptResult` directly (`description?`, `messages`).
- [Export a server snapshot](https://mcpjam-platform-api-keys.mintlify.app/api-reference/export/export-a-server-snapshot.md): Lists tools, resources, and prompts in one call and returns a single JSON snapshot — handy for diffing a server's surface over time in CI.
- [List a harness's native built-in tools](https://mcpjam-platform-api-keys.mintlify.app/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.
- [Create a host (from a template or a full config)](https://mcpjam-platform-api-keys.mintlify.app/api-reference/hosts/create-a-host-from-a-template-or-a-full-config.md): Creates a host in the project and responds `201` with the new host's detail. Seed the host config one of two ways: pass `template` (a built-in template id, optional `theme`) to seed server-side from the same presets the inspector UI uses, OR pass `config` (a full host config v2). Exactly one of `tem…
- [Delete a host](https://mcpjam-platform-api-keys.mintlify.app/api-reference/hosts/delete-a-host.md): Permanently delete a host from the project. Pass `{ "force": true }` to delete a host that is still referenced (e.g. by an eval suite). Guest callers are denied (a write).
- [Get a host](https://mcpjam-platform-api-keys.mintlify.app/api-reference/hosts/get-a-host.md): One host's full settings, including its resolved host config. A host that exists but belongs to a different project reads as `404 NOT_FOUND`.
- [List a project's hosts](https://mcpjam-platform-api-keys.mintlify.app/api-reference/hosts/list-a-projects-hosts.md): The hosts saved in the project — the named model + capability profiles you attach to chats and eval suites. Returns the `id`s the host detail/update/delete routes take.
- [Update a host](https://mcpjam-platform-api-keys.mintlify.app/api-reference/hosts/update-a-host.md): Edit a host's display name and/or its host config. Only the fields you pass change. Guest callers are denied (a write).
- [Import OAuth tokens](https://mcpjam-platform-api-keys.mintlify.app/api-reference/oauth/import-oauth-tokens.md): Stores OAuth tokens you obtained yourself (e.g. via the SDK's `runOAuthLogin` — interactive loopback, headless, or client-credentials) for this server, scoped to your user, project, and server. Subsequent API calls against the server inject the stored access token automatically, and `401`s from the…
- [List prompts](https://mcpjam-platform-api-keys.mintlify.app/api-reference/primitives/list-prompts.md): Returns the server's prompts as a collection page.
- [List resources](https://mcpjam-platform-api-keys.mintlify.app/api-reference/primitives/list-resources.md): Returns the server's resources as a collection page.
- [List tools](https://mcpjam-platform-api-keys.mintlify.app/api-reference/primitives/list-tools.md): Returns the server's tools as a collection page. Each item is the MCP tool definition (`name`, `description`, `inputSchema`, ...).
- [Read a resource](https://mcpjam-platform-api-keys.mintlify.app/api-reference/primitives/read-a-resource.md): Reads a single resource by URI and returns its contents.
- [Check OAuth requirement](https://mcpjam-platform-api-keys.mintlify.app/api-reference/server-diagnostics/check-oauth-requirement.md): Lightweight, no MCP connection: reports whether the server is configured to require an OAuth grant.
- [Run the doctor](https://mcpjam-platform-api-keys.mintlify.app/api-reference/server-diagnostics/run-the-doctor.md): Runs the full doctor workflow — probe → connect → initialize → capabilities → primitives — and returns a step-by-step report. The richest signal for "is this server healthy, and why not."
- [Validate a server](https://mcpjam-platform-api-keys.mintlify.app/api-reference/server-diagnostics/validate-a-server.md): Connects to the server, initializes the MCP session, and returns a connection snapshot (server info, negotiated capabilities). The same check the hosted inspector runs when you connect a server.
- [Create (or revive) a relay tunnel for a named project server](https://mcpjam-platform-api-keys.mintlify.app/api-reference/tunnels/create-or-revive-a-relay-tunnel-for-a-named-project-server.md): Registers a server record named `name` if missing, mints a relay tunnel grant for it, and **persists the tunnel bearer URL (including the plaintext `?k=` secret) onto the server record's `url`** so evals and chatboxes can target the tunnel like any remote server. The plaintext persistence is a delib…
- [Revoke a tunnel's live grant](https://mcpjam-platform-api-keys.mintlify.app/api-reference/tunnels/revoke-a-tunnels-live-grant.md): Revokes the grant at the control plane and edge: the public URL stops working immediately and any live tunnel session is disconnected. The server record — including its now-dead `url` — is intentionally left untouched, so the next create revives the tunnel with the same slug.
- [Changelog](https://mcpjam-platform-api-keys.mintlify.app/changelog/overview.md): Track the latest updates, features, and improvements to MCPJam Inspector
- [MCP Apps Conformance](https://mcpjam-platform-api-keys.mintlify.app/cli/apps-conformance.md): Validate MCP Apps tool metadata and ui:// resource wiring from the CLI
- [CI / CD](https://mcpjam-platform-api-keys.mintlify.app/cli/ci.md): Run MCP health checks and OAuth conformance in GitHub Actions, GitLab CI, and other CI environments
- [MCPJam as an MCP Server](https://mcpjam-platform-api-keys.mintlify.app/cli/mcp-server.md): Run MCPJam as a local stdio MCP server so agents can connect to, exercise, and debug other MCP servers
- [OAuth Conformance](https://mcpjam-platform-api-keys.mintlify.app/cli/oauth-conformance.md): Test your MCP server's OAuth implementation across all registration methods and protocol versions
- [OAuth Login & Debugging](https://mcpjam-platform-api-keys.mintlify.app/cli/oauth-login.md): Authenticate with MCP servers and debug OAuth flows
- [CLI Overview](https://mcpjam-platform-api-keys.mintlify.app/cli/overview.md): Stateless MCP server probing, debugging, OAuth, and conformance from your terminal
- [Command Reference](https://mcpjam-platform-api-keys.mintlify.app/cli/reference.md): Complete flag reference for every mcpjam CLI command
- [Server Inspection](https://mcpjam-platform-api-keys.mintlify.app/cli/server-inspection.md): Probe, diagnose, and export MCP server connectivity and capabilities
- [CLI Telemetry](https://mcpjam-platform-api-keys.mintlify.app/cli/telemetry.md): Anonymous command-level telemetry, opt-outs, and debug mode
- [Tools, Resources & Prompts](https://mcpjam-platform-api-keys.mintlify.app/cli/tools-resources-prompts.md): List, read, and call MCP server tools, resources, and prompts
- [Getting Started](https://mcpjam-platform-api-keys.mintlify.app/getting-started.md): Start testing your MCP server in minutes
- [My First ChatGPT App](https://mcpjam-platform-api-keys.mintlify.app/guides/first-chatgpt-app-react.md): Build a simple Coffee Shop ChatGPT App with React
- [My First MCP App](https://mcpjam-platform-api-keys.mintlify.app/guides/first-mcp-app.md): Build a simple Reservation MCP App from scratch
- [Hosted App](https://mcpjam-platform-api-keys.mintlify.app/hosted/overview.md): Use MCPJam Inspector in the browser — no installation required
- [MCPJam](https://mcpjam-platform-api-keys.mintlify.app/index.md): Test, debug, and evaluate MCP servers, MCP apps, and ChatGPT apps.
- [Clients](https://mcpjam-platform-api-keys.mintlify.app/inspector/clients.md): Reusable MCP client configurations for testing servers and apps under realistic conditions
- [Evaluate](https://mcpjam-platform-api-keys.mintlify.app/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.
- [OAuth Debugger](https://mcpjam-platform-api-keys.mintlify.app/inspector/guided-oauth.md): Debug your MCP server's OAuth implementation at every step of the handshake
- [Home](https://mcpjam-platform-api-keys.mintlify.app/inspector/home.md): Org-scoped dashboard with activity stats, recommended servers, and quick-start clients
- [Contribute a Host](https://mcpjam-platform-api-keys.mintlify.app/inspector/host-templates.md): Add a new host preset to MCPJam so widgets can render under that host's identity, capabilities, and sandbox policy.
- [Launch from Code (Beta)](https://mcpjam-platform-api-keys.mintlify.app/inspector/launch-from-code.md): Programmatically launch and configure MCPJam Inspector from your code or build tools
- [Playground](https://mcpjam-platform-api-keys.mintlify.app/inspector/playground.md): Chat with your MCP servers, invoke tools by hand, render widgets, and inspect every step — all in one IDE-style workspace
- [Projects](https://mcpjam-platform-api-keys.mintlify.app/inspector/projects.md): Group your MCP servers into projects, with the ability to share them with your team
- [MCP protocol versions](https://mcpjam-platform-api-keys.mintlify.app/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.
- [Skills](https://mcpjam-platform-api-keys.mintlify.app/inspector/skills.md): Load and use skills to give your agents the context they need to use MCP tools effectively
- [MCP Inspector](https://mcpjam-platform-api-keys.mintlify.app/inspector/tools-prompts-resources.md): Manually test your MCP server's tools, resources, and prompts
- [XAA Debugger](https://mcpjam-platform-api-keys.mintlify.app/inspector/xaa-debugger.md): Debug Cross-App Access flows with authorization server compatibility checks and actionable error guidance
- [Use MCPJam as a Test IdP](https://mcpjam-platform-api-keys.mintlify.app/inspector/xaa-test-idp.md): Register MCPJam's built-in identity provider with your authorization server to test Cross-App Access flows end to end
- [Installation](https://mcpjam-platform-api-keys.mintlify.app/installation.md): Here's a list of all ways to start MCPJam
- [API keys](https://mcpjam-platform-api-keys.mintlify.app/reference/api-keys.md): Which 'API key' is which in MCPJam — and the one you need to call the MCPJam API.
- [MCPJam API](https://mcpjam-platform-api-keys.mintlify.app/reference/public-api.md): Programmatic access to the MCP servers in your MCPJam projects — diagnostics, tool calls, prompt rendering, and asynchronous eval runs.
- [Connecting to MCP Servers](https://mcpjam-platform-api-keys.mintlify.app/sdk/concepts/connecting-servers.md): Learn how to connect to local and remote MCP servers
- [Testing Across Providers](https://mcpjam-platform-api-keys.mintlify.app/sdk/concepts/multi-provider.md): Compare your MCP server's performance across different LLMs
- [Running Evals](https://mcpjam-platform-api-keys.mintlify.app/sdk/concepts/running-evals.md): Measure tool accuracy with statistical evaluations
- [Save Results to MCPJam](https://mcpjam-platform-api-keys.mintlify.app/sdk/concepts/saving-results.md): Save eval results to the MCPJam dashboard with an MCPJam API key (sk_…) for tracking and CI visibility
- [Testing with LLMs](https://mcpjam-platform-api-keys.mintlify.app/sdk/concepts/testing-with-llms.md): Use HostRunner to run prompts and inspect tool calls
- [@mcpjam/sdk](https://mcpjam-platform-api-keys.mintlify.app/sdk/index.md): MCP server unit testing, end-to-end (e2e) testing, and server evals
- [Quickstart](https://mcpjam-platform-api-keys.mintlify.app/sdk/quickstart.md): Get started with @mcpjam/sdk in 5 minutes
- [MCP Apps Conformance SDK](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/apps-conformance.md): Programmatic MCP Apps surface validation with MCPAppsConformanceTest
- [Saving Eval Results](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/eval-reporting.md): API reference for saving eval results to MCPJam
- [EvalSuite](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/eval-suite.md): API reference for EvalSuite
- [EvalTest](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/eval-test.md): API reference for EvalTest
- [HostRunner](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/host-runner.md): API reference for HostRunner
- [LLM Providers](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/llm-providers.md): API reference for LLM provider configuration
- [MCPClientManager](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/mcp-client-manager.md): API reference for MCPClientManager
- [OAuth Conformance SDK](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/oauth-conformance.md): Programmatic OAuth conformance testing with OAuthConformanceTest and OAuthConformanceSuite
- [PromptResult](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/prompt-result.md): API reference for PromptResult
- [Protocol Conformance SDK](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/protocol-conformance.md): Programmatic MCP protocol conformance testing with MCPConformanceTest and MCPConformanceSuite
- [Validators](https://mcpjam-platform-api-keys.mintlify.app/sdk/reference/validators.md): API reference for validator functions
- [Common MCP Errors](https://mcpjam-platform-api-keys.mintlify.app/troubleshooting/common-errors.md): Solutions to common MCP server connection and configuration issues
- [Error code reference](https://mcpjam-platform-api-keys.mintlify.app/troubleshooting/error-codes.md): What every MCPJam Inspector error code means, the likely causes, and the next step to fix it.

## OpenAPI Specs

- [openapi](https://mcpjam-platform-api-keys.mintlify.app/reference/openapi.json)

## Optional

- [Discord](https://discord.gg/JEnDtz8X6z)
- [GitHub](https://github.com/MCPJam/inspector)
- [Website](https://mcpjam.com)