Server providing Argo CD integration for MCP clients.
Rivtor is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Deploy full-stack apps (frontend, backend, Postgres, Redis) from your agent and get live URLs.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user rivtor-mcp '--' npx -y rivtor mcp
# 2 — ask your agent for something these tools do
# verify, issues, issue_resolve and 17 more
Rivtor costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
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. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user rivtor-mcp '--' npx -y rivtor mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Its publisher also runs it at https://api.rivtor.com/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http rivtor-mcp https://api.rivtor.com/mcpOne config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
20 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Run safe live checks against a deployed project and return the verdict, issues and private report URL. Does not redeploy or change the app.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
List persistent verification, security and production issue groups for a project, with pagination and their current disposition.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| status | string | no | — |
| severity | string | no | — |
| limit | integer | no | — |
| offset | integer | no | — |
Mark an issue as resolved (fixed) or dismissed (false positive) for this project. A resolved issue reopens on recurrence.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| id | string | yes | — |
| status | string | yes | — |
Apply server-validated configuration fixes (canonical URL, same-project CORS, safe security headers) for verification issues, then verify again. Requires consent: true. Does not modify application code or database schemas.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| consent | boolean | yes | — |
| issue_ids | array | no | — |
| fixes | array | no | — |
Execute a named saved journey with the project's encrypted, consented test account inside an isolated browser; no payment, deletion or non-login writes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| journey | string | yes | — |
Import an app from another host without deleting the source host. action=scan (default) sends request (the documented provider/config/source mappings) and stores an encrypted, names-only plan; credentials are accepted only in request and are never returned. action=approve/deploy/copy/sync runs…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| action | string | no | — |
| id | string | no | — |
| request | object | no | — |
| approval | object | no | — |
Return the current state of an import: plan, revision, digest, phase results and any running operation (absent when finished).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| id | string | yes | — |
Pack the project folder at path (respects .gitignore; .env files are never uploaded; only files changed since the last deploy are uploaded), upload it and deploy every service it contains
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Absolute path (or relative to the server's working directory) of the project root to deploy. |
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| dry_run | boolean | no | Only detect and return the deploy plan; nothing is built or changed. |
| env | object | no | Env vars to set before deploying, e.g. {"STRIPE_SECRET_KEY": "..."}. |
| clean | boolean | no | Rebuild every service from scratch without build/dependency caches. Slower; use when a cached dependency looks stale or broken. |
| verify | boolean | no | False skips functional checks, but mandatory client-secret scanning always runs. |
| approval_token | string | no | Token from the approval page after a deploy returned needs_approval (a destructive migration). |
Current state of every service (status, URL, framework, release), data service (Postgres/Redis/R2 usage) and the last deployment of a project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
Runtime logs of a project (summarised by default; filter by service, time window and level), or the build/deploy log of one deployment when deployment_id is given.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| service | string | no | Service name, e.g. "api". |
| since | string | no | Time window such as "15m", "2h" or an ISO timestamp. |
| level | string | no | — |
| limit | integer | no | — |
| summary | boolean | no | Default true: grouped summary. false = raw lines. |
| deployment_id | string | no | Return the build/deploy log of this deployment instead of runtime logs. |
| kind | string | no | Default: build with deployment_id, else runtime. audit lists recent tool calls and changes. |
Set (vars) and/or remove (remove) environment variables for a project, optionally for a single service. Running services restart with the new values (no rebuild).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| vars | object | no | Map of KEY to value. |
| remove | array | no | Keys to delete. |
| service | string | no | Limit to one service; default applies to all services. |
Point traffic back at a previous release in seconds. Without release_id, rolls back to the release before the current one.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| release_id | string | no | — |
Read the project's Postgres. action query: run read-only SQL (5 s timeout, max 500 rows).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| action | string | yes | — |
| sql | string | no | Required for action=query. |
Create temporary Postgres credentials for the project (a new login valid 1 hour, with the app's database permissions) and return the connection string. The result is a credential.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
Download a pg_dump (custom format) of the project's Postgres and write it to output on this machine (default ./<project>.dump; an existing file at that path is overwritten). Returns the path and size.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| output | string | no | File path to write, e.g. ./backup.dump. |
Overwrite the project's Postgres with a snapshot (one is taken before every migration; list them with db action snapshots).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| snapshot_id | string | no | — |
| timestamp | string | no | ISO time, e.g. 2026-11-10T09:30:00Z |
| approval_token | string | no | — |
Attach a custom domain (e.g. app.example.com) to a project's service. Returns the exact DNS record to create at the domain's DNS provider; TLS is issued automatically once DNS resolves.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Project slug. Optional: defaults to rivtor.json in the working directory, else its folder name. |
| hostname | string | yes | Fully qualified hostname, e.g. "www.example.com". |
| service | string | no | Service to route to; default is the project's primary public service. |
Permanently delete a project, all its services AND its data (databases, files). Needs an admin-scope key and a human approval: the first call deletes nothing and returns
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | yes | Project slug to delete (required, never inferred). |
| approval_token | string | no | One-time token from the approval page (rva_...). |
| confirm_token | string | no | Older API versions only; current ones use approval_token. |
Create a checkout link for upgrading the user's Rivtor plan (hobby, pro or team). No charge is made by this tool; payment is completed in the browser.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plan | string | no | Default hobby. |
| interval | string | no | Default month. |
List the user's Rivtor projects with their URLs and status.
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Rivtor or to call it, 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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (20 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| verify | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| issues | no tags | |
| issue_resolve | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| verify_fix | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| verify_journey | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| import | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| import_status | no tags | |
| deploy | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| status | no tags | |
| logs | no tags | |
| env_set | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| rollback | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| db | sensitive-source | sensitive-source: parameter "sql" |
| db_connection | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| db_export | untrusted-inputsensitive-sourcestate-write | untrusted-input: keyword "download"; sensitive-source: keyword "dump"; state-write: declares readOnlyHint: false, destructiveHint: true |
| db_restore | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| domain_add | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| destroy | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| upgrade | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| list_projects | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.6.1. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Rivtor can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.