Rivet
NPM · @RIVET-DEV/MCP · 2 COMPONENTS
Manage Rivet Cloud namespaces and actors, run Code Mode, and open the Rivet Actor Inspector.
Available components
Last scanned (19 hours ago)
Scores higher than 40% of npm servers
Category Cloud Infrastructure
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 Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 1.29.0, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 128 of 318 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency6
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
- Actively maintained (last published 57 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- Maintenance
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
- Capabilities
Checks we could not complete (2)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- License in Provenance & TransparencyLicence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 16 Nov 26 0
- Stability: 0.97 → pass security
- 15 Nov 26 0
- Stability: pass → 0.97 functional
- 9 Nov 26 0
- Stability: 0.97 → pass security
- 8 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 6 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 5 Nov 26 −2
- Stability: pass → 0.87 functional
- 4 Nov 26 0
- Dependency health: partial → 0.85 functional
- 2 Nov 26 0
- Dependency health: 0.85 → partial functional
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 21 Nov 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 9 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-rmxm-3fg6-px4f | CVE-2026-118663 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N | yes |
| GHSA-22jm-h49p-29qw | CVE-2026-111767 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:L | yes |
| GHSA-46jr-4wx8-v453 | CVE-2026-111768 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-6prh-2h8m-c8cw | CVE-2026-111769 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:L/A:N | yes |
| GHSA-6qxp-vccf-f47h | CVE-2026-104850 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | yes |
| GHSA-f897-62hf-6gxq | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes | |
| GHSA-rvq5-wwqv-78pq | CVE-2026-111771 | medium | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:N | yes |
| 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 318 packages
| Packages resolved | 318 |
|---|---|
| Deprecated | 1 |
| Stale | 125 |
| No linked repository | 2 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
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.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| namespace | string | – | Rivet namespace this call acts on |
| organization | string | – | Rivet organization slug this call acts on |
| project | string | – | 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.
| Name | Type | Req | Description |
|---|---|---|---|
| actor | – | yes | Selects 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.… |
| namespace | string | – | Rivet namespace this call acts on |
| organization | string | – | Rivet organization slug this call acts on |
| project | string | – | 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.
| Name | Type | Req | Description |
|---|---|---|---|
| actor | – | yes | Selects 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.… |
| namespace | string | – | Rivet namespace this call acts on |
| organization | string | – | Rivet organization slug this call acts on |
| project | string | – | 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.
| Name | Type | Req | Description |
|---|---|---|---|
| token | string | yes | – |
No output schema declared.
No examples provided.
rivet.ui.actor.session.revoke ~28
Revoke a temporary Inspector proxy session.
| Name | Type | Req | Description |
|---|---|---|---|
| token | string | yes | – |
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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| query | string | – | – |
No output schema declared.
No examples provided.
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
claude mcp add dev-rivet-mcp -- npx -y @rivet-dev/mcp
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 69 out of 100 on VerifyMCP. We recorded 9 known advisories against it as of 21 November 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 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Rivet MCP server?
VerifyMCP ran 15 checks on Rivet, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. 2 items could not be completed, a gap on our side rather than a finding about Rivet: License and Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.