Provider-neutral MCP server for AgentDispatch.
Return the team's plan, its limits, and current usage. Use this BEFORE deploy_site or add_custom_domain to know whether a deploy would trip a plan limit, instead of provoking PLAN_LIMIT_EXCEEDED. Also returns the per-token MCP rate-limit ceiling (live remaining is in X-RateLimit-Remaining response header).
ArgumentsA call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
What it does
Deploy and host AI-built websites on EU infrastructure, straight from your AI agent.
Quickstart
# 1 — install (mcprush login holds a key from your dashboard)
npx mcprush@latest add vibedeploy-mcp
# 2 — ask your agent something
> Deploy and host AI-built websites on EU infrastructure, straight from your AI agent.
Vibedeploy is free: there is no plan to choose, no cap to set and nothing that can bill you.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add --transport http vibedeploy-mcp https://mcp.vibedeploy.be/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
39 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Return the team's plan, its limits, and current usage. Use this BEFORE deploy_site or add_custom_domain to know whether a deploy would trip a plan limit, instead of provoking PLAN_LIMIT_EXCEEDED. Also returns the per-token MCP rate-limit ceiling (live remaining is in X-RateLimit-Remaining response header).
Takes no parameters.
Publish a website to a live URL. Deploy a static site or single-page app you built (with AI or by hand) to your platform subdomain (e.g. {name}.vibedeploy.be or {name}.vibedeploy.eu) with automatic SSL, and optionally a custom domain. The fastest way to get a localhost project or an AI-generated site online. DESTRUCTIVE on existing sites: replaces every file on the named site with the supplied set
Takes no parameters.
Patch or replace files on an existing site. Defaults to patch mode: only the listed files change; everything else stays. Pass mode:'replace' to wipe-and-replace the whole site (the legacy behaviour, surfaced explicitly so it can't happen by accident). Use `delete: [paths]` in patch mode to remove specific files without wiping the rest. Use `dryRun: true` to preview the diff before committing. LARG
Takes no parameters.
List sites for the team this connection belongs to.
Takes no parameters.
Return name, url, plan, last deploy time, and recent deploy history.
Takes no parameters.
Soft-delete a site. confirm=true is required. The site moves to status 'deleted' immediately (its hostname is freed and it stops serving), and is fully purged after the team's recovery window by a sweeper. Use this for the normal 'remove this from my dashboard' flow. The response field 'accepted' is true when the soft-delete is recorded; the response also includes 'purgesAt' so you can tell the us
Takes no parameters.
Return a privacy-safe traffic summary for a site over the last `period` days (default 7): total page views, distinct-visitor count, top pages, daily counts, device/browser breakdowns, and Web Vitals averages. Never exposes raw visitor IPs or user-agents.
Takes no parameters.
Return the bytes of one file currently served by the site. Use this to inspect or edit existing content (call read_file → modify → update_site mode:'patch') so a new chat can iterate on a site without re-uploading. Files larger than 5242880 bytes can't be read in one call. Use list of paths from get_site.filePaths to discover what's available.
Takes no parameters.
Batched version of read_file. Pass up to 50 paths; each is fetched independently with the same per-file rules as read_file. The whole batch is capped at 8388608 bytes total — once that's exhausted, remaining paths fail with BATCH_BUDGET_EXCEEDED so the agent can re-request them in another call.
Takes no parameters.
Return SHA-256 + size for every file currently served. Use BEFORE re-deploying to skip files whose content hasn't changed: hash your local files, diff against this list, and only ship the differences via update_site mode:'patch' or begin_deploy → add_files. For SPAs with content-hashed bundle names this typically reduces a full-site redeploy to a handful of files.
Takes no parameters.
Return SHA-256 + size for every file in the site's editable source tree (the platform's copy of the pre-build code, not the served dist). Use BEFORE editing so you know which paths exist and which haven't changed since the last build. autoPromote:true will mirror the served dist into source for static-only sites whose source tree is empty (does nothing if the dist looks built).
Takes no parameters.
Return the bytes of one source file (the platform's editable copy of the pre-build code), letting an AI in any future chat fetch and edit content without needing the original local files. Use list_source_files first to discover paths. For the served dist, use read_file instead.
Takes no parameters.
Batched read across the editable source tree (up to 50 paths). Each entry is independent: a missing/oversized file fails its own slot but doesn't abort the batch. Cumulative cap 8388608 bytes; remainder fails with BATCH_BUDGET_EXCEEDED.
Takes no parameters.
Stage edits to a site's editable source tree (not the live dist). Use list_source_files first to discover what's there. The dist is unchanged until you re-deploy via update_site or run build_and_deploy. Sites have source storage enabled by default; if a legacy site doesn't, the call fails with SOURCE_STORAGE_NOT_ENABLED and the user should contact VibeDeploy support to enable it.
Takes no parameters.
Remove one file from the site's editable source tree. The served dist is unchanged.
Takes no parameters.
Run a build inside a hardened one-shot pod against the site's editable source tree (write source first via write_source_files / list_source_files autoPromote), then atomically swap the build output into the live dist. Reuses the same build pod the GitProject git-deploy flow uses, so the same isolation guarantees apply: no SA token, no DB/Vault reach, NetworkPolicy-restricted egress. The first run
Takes no parameters.
Search for a literal string or basic regex across all files in either the served dist or the editable source tree. Use this BEFORE batch-reading files to find candidates — saves the 'read 14 batches just to find which 3 files matter' round trip. Pass `target: "source"` to search the editable tree (requires Site.sourceStored=true).
Takes no parameters.
Publish a website to a live URL from a public archive link. Point this at a tar(.gz) archive on github / gist / S3 and the server fetches and deploys it, no upload from your side. Server-side fetch of a tar(.gz) archive from a public HTTPS URL, then deploy its contents. Sidesteps the case where your code-execution sandbox can reach github / gist / S3 etc. but not mcp.vibedeploy.be's upload endpoin
Takes no parameters.
Download the external images a site references (e.g. from the old site it was rebuilt from), store them on this VibeDeploy site under assets/img/, and rewrite the HTML <img> references to local paths so the site no longer depends on the original. Call this once AFTER deploying a site rebuilt with the Website Converter. Auto-detects the external image URLs from the site's own HTML; downloads are SS
Takes no parameters.
Apply one or more literal find/replace edits to a single file on the site, in one tool call. Designed for tiny edits where uploading the full file would be wasteful (one nav-button reference, one encoding fix, one env var bump). Each edit must specify how many matches it expects; mismatches abort the whole call with NO writes. For dist edits the change goes live immediately; for source edits you s
Takes no parameters.
Apply find/replace edits across MANY files in one tool call. Batch sibling of update_file_content. Per-file edit semantics identical (count: 1 default, -1 = all, positive int asserts exact count). Whole call is atomic across files: validation runs first, writes only proceed if every edit's count check passes.
Takes no parameters.
Read the form-to-email relay config of a site, plus the resolved delivery mode, the active From address, and (for a custom sender domain) the DNS records to publish and their verification status. Submissions: POST JSON to the returned `endpoint` with Content-Type: application/json (UTF-8). Flat object of form fields (strings/numbers/booleans; checkbox groups may be arrays of strings, joined with '
Takes no parameters.
Configure the built-in form-to-email relay, fully self-service. Supports a custom From (via a verified sender domain or your own SMTP relay), an explicit Reply-To, and full email branding (subject template, field labels/order, logo, accent color, or a custom HTML body). Requires team role owner or admin. Pass config:null to switch the relay off. If you set a custom `sender` without an `smtpRelay`,
Takes no parameters.
Check the DNS records for a site's custom sender domain (DKIM TXT + SPF include). Once the DKIM record is observed, the sender domain is marked verified and the relay sends from the custom From (DKIM-signed). Until then it falls back to the platform address. DNS can take a few minutes to propagate — re-run if it fails the first time. Not needed when the site uses a custom smtpRelay.
Takes no parameters.
Start attaching a user-owned domain to an existing site. Returns a TXT record the user must add at their DNS provider. Idempotent: calling twice with the same (siteName, domain) returns the existing record instead of creating a duplicate. After the TXT is published (typically within minutes; up to 24h), call verify_custom_domain with the returned recordId. The site itself must already exist on a p
Takes no parameters.
Check the TXT record the user added at step 1 and, if found, attach the domain to the site's ingress. If verification fails, the most common cause is DNS propagation delay; wait a few minutes and try again. Once verified, the domain serves the site immediately (HTTPS issues automatically within ~30s).
Takes no parameters.
Remove a custom domain from a site. The site itself is unaffected; only the custom hostname is detached. The {name}.vibedeploy.be subdomain keeps serving the site.
Takes no parameters.
Return all custom domains attached to a site. Each entry has a recordId you can pass to verify_custom_domain or remove_custom_domain.
Takes no parameters.
Read the DNS records VibeDeploy tracks for a site (the records it created/manages on your behalf), oldest first. Returns each record's host, type, and value. Any team member, including viewers, can read DNS records. This tool is read-only and does NOT create, change, or delete any DNS record.
Takes no parameters.
Check whether a domain can be registered and get an INDICATIVE retail price. IMPORTANT: this is a read-only lookup — it does NOT buy, register, reserve, or pay for any domain, and it changes nothing. The returned price is GROSS (includes 21% VAT) and indicative only. Set alternatives:true to also check the same name across other common TLDs (be, com, net, eu, nl, io, dev, app). Requires a valid te
Takes no parameters.
Opens a staging session for a multi-call deploy. Use when the site is too large to fit in a single deploy_site/update_site call. Pair with add_files (one or more times) OR a single tarball upload to the returned uploadUrl, then commit_deploy. Active session limit per token: 5. Default TTL: 1 hour.
Takes no parameters.
Append files to an open staging session. Call as many times as needed; commit_deploy applies them all at once. Validates path/extension/encoding on every call so a bad file fails fast. Same 500 MB cap as single-call deploys, but cumulative across the session. LARGE TEXT FILES: a file that looks too big to inline (100-250 KB of HTML/CSS/JS) usually still fits in ONE call — gzip it locally, base64 t
Takes no parameters.
Stream a single file across multiple calls when its content exceeds the per-MCP-call output budget. LAST RESORT — try these first: (1) add_files with encoding:'gzip+base64' fits ~250 KB of text source in ONE call (gzip locally, base64, send — no chunking, no ordering hazards); (2) begin_deploy's uploadUrl takes a 100 MB tarball in one HTTP POST if your sandbox can reach mcp.vibedeploy.be; (3) depl
Takes no parameters.
Atomically apply a staging session's files to the live site. Runs preflight + secret/malware scan against the complete staged set; on failure the session stays open and can be re-attempted or aborted. For replace-mode against a site with existing files, requires confirm:"I-want-to-replace-all-files".
Takes no parameters.
Discard a staging session and its scratch dir. Live site is untouched. Returns immediately; cleanup is best-effort and the sweeper will retry if it fails.
Takes no parameters.
Return staging sessions for the team this token belongs to. Defaults to currently-active ones (open + committing). Up to 50 rows.
Takes no parameters.
Return the most recent 50 deploy and snapshot history entries for a site, newest first. Includes the source (how it was triggered), an optional label, the associated Longhorn snapshot name (if any), the file count, and the number of secrets detected. Any team member can read history.
Takes no parameters.
List the Longhorn volume snapshots for a site. Snapshots are point-in-time backups of the site's served files. Any team member can list snapshots. Returns NO_VOLUME if the site has no volume yet (it has never been deployed).
Takes no parameters.
Take a point-in-time Longhorn snapshot of a site's served files. This is an additive backup — it does not change anything served. It records a manual-snapshot history entry and runs retention cleanup. Viewers cannot create snapshots. Returns NO_VOLUME if the site has no volume yet (it has never been deployed).
Takes no parameters.
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Vibedeploy costs nothing to install and nothing to call, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is a hosted endpoint: the publisher runs it and we connect to it. The scanner reads packages and source, and neither exists to read here, so there is no grade — not a withheld one, an unmeasured one. What can be checked instead is on Installation: what it asks to reach and what it writes.
Release history
Pinned to 1.0.1 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
No release note was published with this version.
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Writing one takes an account with at least 50 real tool calls against Vibedeploy in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.