Publisher MCP server

Tools: 10

RegressionBot

Visual regression testing as an API. Drop it into CI, drive it from your agent, or let it crawl on a schedule. Catches what your deploys didn't: third-party scripts, CMS edits, font failures. MCP server included.

This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.

https://regressionbot.com/

MCP

MCPBundles

Remote MCP URL

https://mcp.regressionbot.com/mcp

This server may ask you to sign in when your AI client connects.

Last probed Nov 3, 2026 · mcp.regressionbot.com

10tools discovered

For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://mcp.regressionbot.com/mcp
Skill page: https://www.mcpbundles.com/skills/regressionbot-mcp-833e4b7dd6

Explore capabilities (10)

write 3

other 2

Get

Approve

List

Run

Other capabilities

Run Regression Job

other

run_regression_job

Start a visual regression job. Captures screenshots and compares them — either against stored baselines (managed mode) or against a second live origin (live-vs-live mode). WORKFLOW: run_regression_job → poll get_job_status every 5–10s until status=COMPLETED AND summaryStatus=COMPLETE → get_job_summary → (optionally) approve_job. ⚠️ Always wait for summaryStatus=COMPLETE before calling get_job_summary. AI summaries, diff links, and scores are only fully populated once summaryStatus reaches COMPL

Description may be truncated on the public preview.

Add to workspace

Tool inventory (10 tools)

Run Regression Job — Start a visual regression job. Captures screenshots and compares them — either against stored baselines (managed mode) or against a second live origin (live-vs-live mode). WORKFLOW: run_regression_job → poll get_job_status every 5–10s until status=COMPLETED AND summaryStatus=COMPLETE → get_job_summary → (optionally) approve_job. ⚠️ Always wait for summaryStatus=COMPLETE before calling get_job_summary. AI summaries, diff links, and scores are only fully populated once summaryStatus reaches COMPL
Run From Project — Run a visual regression job using a saved project configuration. Loads the stored testOrigin, devices, paths, and other settings for the named project — no need to re-supply params. Use this for repeat runs where the project config is already established — no need to re-supply URLs, devices, or paths. For the first run of a new project, use run_regression_job instead (which creates and saves the config).
Get Project — Retrieve the stored configuration for a named project.
List Projects — List saved project configurations for the authenticated org. A live-vs-live run (one passing baseOrigin) stores no config, so a project name used only that way will not appear here even though list_jobs shows its jobs — absence is not evidence of a different org or key. Each entry reports whether the next managed run will compare against a baseline or re-capture one.
Get Job Status — Retrieve the current status and progress of a visual regression job. Status lifecycle: INITIALIZING → PROCESSING → COMPLETED (or FAILED / APPROVED). - APPROVED is reached either by an approve_job/approve_project call or automatically: a project on baselinePolicy 'rolling' auto-approves every completed managed run, so scheduled runs land in APPROVED without anyone acting. - PROCESSING: workers are capturing and comparing screenshots in parallel. - FINISHING: all workers done, awaiting the next p
Get Job Summary — Retrieve a summary of the completed job. Only call this after get_job_status shows status=COMPLETED AND summaryStatus=COMPLETE. KEY OUTPUTS PER REGRESSION — always present these to the user for every regression: - diffUrl: pre-signed JPEG showing [Baseline | Current | Annotated Diff] side-by-side. Fetch with a plain HTTP GET (no auth). Share this link so the user can see exactly what changed. - changed: whether this page counts as changed. Read this rather than comparing diffPercentage yourself

Get your MCP into directories

A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.

Directory coverage for brands

Frequently Asked Questions

What is the RegressionBot MCP server?

How do I connect RegressionBot to my AI agent?

Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.

How many tools does RegressionBot provide?

Operate this server?

Request removal if you do not want RegressionBot listed here, or claim the listing if you want to manage it on MCPBundles.

Operate RegressionBot?

This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.

Claim this listing

MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal

List Jobs — List recent regression jobs for the authenticated org, ordered by most recent first. Useful for recovering a jobId or checking the status of recent runs.

Approve Job — Promote the current screenshots to baselines, accepting all visual changes as intentional. This is permanent — existing baselines are overwritten. Only call after reviewing regressions in get_job_summary and confirming the changes are expected. THREE FORMS, same tool: - { jobId }: approve every page in the job. - { jobId, where: { decision: ['intentional', 'noise'] } }: approve only the changed pages whose verdict.decision is in the list; pages outside it, or with no verdict, are left pending a

Update Project — Update a saved project configuration. Changing what a capture looks like — testOrigin, baseOrigin, sitemapUrl, paths, scans, devices, masks, customCss, or a gate credential — invalidates the stored baselines, and the next managed run re-captures instead of comparing. Changing anything else (schedule, baselinePolicy, concurrency, AI options) leaves baselines intact, and re-sending an identical value is not a change. GATED ORIGINS: a password-protected preview or staging site needs testAuth (and

Approve Project — Approve the most recent completed job for a project, promoting its screenshots to the new baselines.

Schemas and invoke metadata: Directory API

MCPBundles probed 10 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.

What authentication does RegressionBot require?

RegressionBot may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.

Don't want this listed?

Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.

MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.