PricingBlogCommunityDocs

Test your MCP server in every major AI client.

From your first prompt to a continuous gate on every release, MCPJam shows what breaks across every AI client, and how to fix it.

Test in 16+ major AI clients

ClaudeChatGPTCursorCopilotVS CodeClaude CodeCodexPerplexity+8

Get your agent set up with MCPJam

Launch locally, in web, or desktop

Open web appmacOSWindows
Fillen-USSan FranciscoStrictClient contextHost capabilities
ChatGPTs-2291-c3

  1. Show page views and signups for the last 7 days.

  2. show_analytics Complete

    PULSE · MCP APPDemo data

    Page views

    24,800

    Sep 8–14 · Last 7 days

    02.5k5kSep 8: 2800Sep 9: 3400Sep 10: 3100Sep 11: 4200Sep 12: 3600Sep 13: 3300Sep 14: 4400Sep 8Sep 10Sep 12Sep 14

Ask something… Use Slash “/” commands for Skills & MCP prompts

Trusted by 106,000+ developers and 280+ enterprises

“We use MCPJam every day. It has become essential for testing MCP servers locally.”
Jau Chan · Senior Software Engineer, Asana
See how they skip the 2-minute deploy
“If I run out of MCPJam credits, my day stops. I don't know how I would work without it.”
Atlas Wegman · Staff iOS Engineer, Jeppesen ForeFlight
See how they iterate 10x faster

Inspector

See the same prompt land in multiple clients.

Call a tool, read the trace, and compare how your product appears in different clients.

Fillen-USSan FranciscoStrictClient contextHost capabilities
ChatGPTs-2291-c3

    Ask something… Use Slash “/” commands for Skills & MCP prompts

    Swarms

    Test the journeys your users actually take.

    Agent personas run them across every client. Every session is captured and scored.

    Create a swarm of your users

    Simulated users run through your server so you can see what breaks.

    Choose the clients and servers your users will interact with. *

    This will shape the swarm's behavior. You will be able to compare behavior across clients side by side.

    ChatGPTClaudeCursor+ Add client
    acme-payments· v2.15.0-rc.1 · 5 tools

    Describe your users and their behavior. *

    We build the user goals from your input. Your inputs are not final. You can edit personas and goals on the next screen.

    Support agents refunding duplicate charges, finance ops reconciling Tuesday's payouts, and developers wiring a failed-payment webhook.

    Generated personas

    • MCMaya Chen · Support agentFind the duplicate charge on order A-2291 and refund it.8 × 3 clients
    • JHJordan Hale · Finance opsMatch payout po_7Hd2 to its charges and flag anything missing.8 × 3 clients
    • PSPriya Shah · DeveloperCreate an invoice, fail its payment, and confirm the webhook fires.8 × 3 clients

    User Testing

    Then invite real people to try the same ones.

    Share a sandboxed session. Measure user sentiment and uncover usability gaps.

    Refund & reconcile · beta

    Access settings

    Anyone with the link (guests included)

    Has access

    Ratings

    Per-turn ratings

    Preview

    ChatGPTCopy link

    Refund the duplicate charge on order A-2291

    list_charges· refund_charge

    I found two charges for order A-2291: ch_3RkA9 for $129.00 and ch_3RkQ9 for $129.00, 41 seconds apart. I refunded ch_3RkQ9 as a duplicate. The customer will see it in 5 to 10 business days.

    Rate this response
    Message…

    AI can make mistakes. Please double-check responses.

    Previewing as you, signed in. A tester opening this link gets the guest experience, which can differ.

    Evaluate

    Set the quality bar across every AI client.

    Build durable testing and ensure reliability on every deployment.

    Evaluate

    OverviewSuites

    Suite health

    98%average across 12 runs

    acme-paymentsPayments operations
    100%95%
    9/29/39/49/59/69/79/89/99/109/119/129/13

    Runs

    PlatformSuiteClientServer
    RunSuiteClientResultRatePlatformDateLatencyTokensCalls
    #128Payments operationsFailed96%69/72GitHubSep 13, 2:00 AM18.4s16.2k44
    #127Payments operationsPassed98%71/72CLISep 12, 2:00 AM14.2s12.1k41
    #126Treasury reconciliationPassed100%48/48SDKSep 12, 1:14 AM16.8s15.6k38
    #125Billing exception handlingFailed94%45/48CLISep 11, 11:42 PM21.1s18.9k47
    #124Payments operationsPassed99%71/72GitHubSep 11, 2:00 AM11.3s9.4k29
    #123Dispute resolutionPassed100%36/36SDKSep 10, 6:18 PM15.5s11.8k33
    #122Treasury reconciliationPassed97%70/72GitHubSep 10, 2:00 AM17.9s14.7k40

    CI/CD

    Block the ones that fail before they merge.

    Run the same suite on every pull request. A failing check blocks the merge.

    acme/acme-paymentsPrivate
    CodeIssuesPull requestsActions

    list_charges: return full charge objects #482

    Openm.okafor wants to merge 1 commit into release/2.15
    ConversationCommits 1Checks 5

    Some checks were not successful

    1 failing and 4 successful checks

    • BuildSuccessfulRequired
    • Unit testsSuccessfulRequired
    • MCPJam / Protocol conformanceSuccessfulRequired
    • MCPJam / OAuth & securitySuccessfulRequired
    • MCPJam / Evals89% pass rate · 95% requiredRequired

    Merging is blocked

    MCPJam Evals must pass before this pull request can be merged.

    Questions

    Before you start jamming.

    No. MCPJam maintains each client's current behavior so your tests reflect what users experience today.

    With evaluation, not brittle assertions. MCPJam scores tool choice, arguments, and goal completion across repeated runs, then shows why the score changed.

    Those products evaluate an agent you control. MCPJam tests how external AI clients use your MCP server.

    MCPJam is pre-production and never sees live traffic. The Inspector runs locally or in your CI; enterprise controls include SSO, audit logs, and a DPA.

    Yes. The Inspector, CLI, SDK, local evals, and conformance checks are open source and free.

    Ship knowing it works, for every user, in every client.

    Book a demo