Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Rivet

NPM · @RIVET-DEV/MCP · 2 COMPONENTS · SCANNED SEP 26

Manage Rivet Cloud namespaces and actors, run Code Mode, and open the Rivet Actor Inspector.

+5 this week 64 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security94
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known low-severity CVE affects esbuild 0.27.7, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 127 of 317 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability77
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1085 tokens (~155/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
  • Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 69% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
Install

How do I install the Rivet MCP server?

Rivet runs locally as an npm package, launched with npx -y @rivet-dev/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @rivet-dev/mcp

# add to Claude Code
claude mcp add dev-rivet-mcp -- npx -y @rivet-dev/mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "dev-rivet-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@rivet-dev/mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "dev-rivet-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@rivet-dev/mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add dev-rivet-mcp -- npx -y @rivet-dev/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-rivet-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@rivet-dev/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add dev-rivet-mcp --command npx --arg -y --arg @rivet-dev/mcp
# ~/.hermes/config.yaml
mcp_servers:
  dev-rivet-mcp:
    command: "npx"
    args: ["-y", "@rivet-dev/mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "dev-rivet-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@rivet-dev/mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add dev-rivet-mcp -t stdio -c npx -a -y @rivet-dev/mcp
// mcp.json
{
  "mcpServers": {
    "dev-rivet-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@rivet-dev/mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 26 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Sept 26 +4
    • Stability: unverified → 0.27 ▲ functional
  • 16 Sept 26 59

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 26 Sept 2026 · Analysed npm/@rivet-dev/mcp@2.3.17

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 2 findings
ID CVE Severity Vector Fix available
GHSA-848j-6mx2-7j84 CVE-2025-14505 medium CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L no
GHSA-g7r4-m6w7-qqqr low CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 317 packages
Packages resolved 317
Deprecated 1
Stale 124
No linked repository 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~1,072 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
execute ~259

Execute JavaScript in Secure Exec against the live Rivet namespace, using the `rivet` library bound as a global. This is the tool that reads and mutates real Rivet state; the other tools only describe or embed it. Top-level await is available. Return the final JSON-serializable result, or call globalThis.__return(value) from a nested scope. Direct network, environment, and filesystem access are disabled, so `rivet` is the only way out. Use the search tool to look up an operation signature instead of guessing it. To find actors when no name is known yet: const { names } = await rivet.actors.names.list(); return await rivet.actors.list({ filters: { name: names[0] } }); Name the organization, project, and namespace to act on. Levels the connection URL already pins are fixed and cannot be overridden; levels with a single option are filled in for you. Use target_list to discover the names.

NameTypeReqDescription
codestringyes–
namespacestring–Rivet namespace this call acts on
organizationstring–Rivet organization slug this call acts on
projectstring–Rivet project slug this call acts on

No output schema declared.

No examples provided.

rivet.actor.inspect ~345

Resolve one Rivet Actor and return its id, name, key, status, region, and inspector capabilities, with an embedded Inspector on MCP Apps hosts. Read-only. To find an actor id first, use the execute tool with rivet.actors.names.list() and rivet.actors.list(). Name the organization, project, and namespace to act on. Levels the connection URL already pins are fixed and cannot be overridden; levels with a single option are filled in for you. Use target_list to discover the names.

NameTypeReqDescription
actor–yesSelects exactly one actor. Must be an object, in one of three forms: 1. By id: { "actorId": "1knr9w8pjyaz6ntfubbfiwpmlacl00" } 2. An existing actor by name: { "name": "counter", "key": ["demo"] } 3.…
namespacestring–Rivet namespace this call acts on
organizationstring–Rivet organization slug this call acts on
projectstring–Rivet project slug this call acts on

No output schema declared.

No examples provided.

rivet.ui.actor.session.create ~333

Create a temporary single-actor Inspector proxy session for the embedded Inspector UI. Returns a short-lived token used by rivet.ui.actor.session.renew and revoke. Not needed to read actor data; use the execute tool for that. Name the organization, project, and namespace to act on. Levels the connection URL already pins are fixed and cannot be overridden; levels with a single option are filled in for you. Use target_list to discover the names.

NameTypeReqDescription
actor–yesSelects exactly one actor. Must be an object, in one of three forms: 1. By id: { "actorId": "1knr9w8pjyaz6ntfubbfiwpmlacl00" } 2. An existing actor by name: { "name": "counter", "key": ["demo"] } 3.…
namespacestring–Rivet namespace this call acts on
organizationstring–Rivet organization slug this call acts on
projectstring–Rivet project slug this call acts on

No output schema declared.

No examples provided.

rivet.ui.actor.session.renew ~29

Rotate and renew a temporary Inspector proxy session.

NameTypeReqDescription
tokenstringyes–

No output schema declared.

No examples provided.

rivet.ui.actor.session.revoke ~28

Revoke a temporary Inspector proxy session.

NameTypeReqDescription
tokenstringyes–

No output schema declared.

No examples provided.

search ~78

Search the Rivet Cloud, Engine, actor, and inspector Code Mode API. Returns the call signature and a runnable example for each matching operation, to be pasted into the execute tool. Call this before execute whenever the exact argument shape is not already known. An empty query lists everything.

NameTypeReqDescription
limitinteger––
querystring––

No output schema declared.

No examples provided.

Common questions

What is the Rivet MCP server?

Rivet is an MCP server listed in the public MCP registry as dev.rivet/mcp. Manage Rivet Cloud namespaces and actors, run Code Mode, and open the Rivet Actor Inspector. This page covers its npm package (@rivet-dev/mcp).

Is the Rivet MCP server safe to use?

Rivet scores 64 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 26 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Rivet MCP server expose?

Rivet exposes 6 tools: search, execute, rivet.actor.inspect, rivet.ui.actor.session.create, rivet.ui.actor.session.renew, rivet.ui.actor.session.revoke. Their descriptions and schemas cost roughly 1,072 tokens of context every time the server is loaded.

Is the Rivet MCP server still maintained?

Rivet is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.