mcp-v8
OCI · DOCKER.IO/WHOLELOTTAHOOPLA/MCP-JS
Run JavaScript and TypeScript in sandboxed V8 isolates with policy-controlled host capabilities.
Available components
Last scanned (19 hours ago)
Scores higher than 77% of OCI servers
Category Developer Tools
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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (AGPL-3.0).Pass
- Actively maintained (last published 26 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability70
- 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 2122 tokens (~265/item across 8 items; 4 tools + 4 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 Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage83
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 50% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Oct 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.
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 4 Nov 2026 · Analysed oci/docker.io/wholelottahoopla/mcp-js@0.22.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
get_artifact ~124
Fetch an artifact stored by run_js code via the artifact(key, mime, bytes) global. The payload is returned as a content block matching its mime type: image/* as an MCP image block (visible to the model), audio/* as an audio block, UTF-8 payloads as text, and other binary as base64 text. A JSON metadata block (key, mime_type, size_bytes, created_at, execution_id, encoding) comes first.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Artifact key, as passed to `artifact(key, mime, bytes)` in JS. |
No output schema declared.
No examples provided.
get_artifact_upload_url ~234
Get a one-time URL for uploading a file as an artifact over plain HTTP, so the file's bytes never pass through a tool call. Returns { url, method: "PUT", expires_at, max_bytes }: send the raw file as the request body, e.g. `curl -fsS -T ./file '<url>'`. The URL needs no other credentials, works once, and expires (default 10 minutes); max 16 MiB. Afterwards run_js code reads the file with `artifact.get(key)`. If `url` is absent the server has no public URL configured: append the returned `path` to the origin you reach the server at.
| Name | Type | Req | Description |
|---|---|---|---|
| expires_in_secs | integer|null | – | How long the URL stays valid, in seconds (default 600, max 3600). |
| key | string | yes | Key the uploaded file will be stored under (same key overwrites). |
| mime_type | string|null | – | Mime type to store, e.g. "application/pdf". When omitted, the upload request's Content-Type is used ("application/octet-stream" if none). |
No output schema declared.
No examples provided.
list_artifacts ~50
List metadata (key, mime_type, size_bytes, created_at, execution_id) for all artifacts stored via the artifact(key, mime, bytes) global. Use get_artifact to fetch a payload.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
run_js ~1,573
run javascript or typescript code in v8 Executes code and returns the console output directly. Each call runs in a fresh V8 isolate — no state is carried between calls. TypeScript support is type removal only — types are stripped before execution, not checked. Invalid types will be silently removed, not reported as errors. params: - code (optional): the javascript or typescript code to run. Provide either `code` or `file`. - file (optional): path to a JavaScript/TypeScript file **on the server's own filesystem** to read and execute instead of inline `code`. Provide either `code` or `file`, not both. This is disabled by default: the server must be started with `--allow-run-js-file` (allow any path) or a `run_js_file` policy in `--policies-json` (allow specific paths/dirs), otherwise the call is rejected. The path is resolved on the server, not uploaded from the client. - heap_memory_max_mb (optional): maximum V8 heap memory in megabytes (minimum: 4, default: 8). Override the server default for this execution. - execution_timeout_secs (optional): maximum execution time in seconds (1–300, default: 30). Override the server default for this execution. returns: - output: console output from the execution (everything printed via console.log, console.info, console.warn, console.error) - error: error message if the execution failed, timed out, or was cancelled ## Console Output Use `console.log()` to produce output. `console.info`, `console.warn`, and `console.error` are also supported (with `[INFO]`, `[WARN]`, `[ERROR]` prefixes respectively). eg: ```js const result = 1 + 1; console.log(result); ``` Returns `output: "2"`. ```js const obj = { a: 1, b: 2 }; console.log(JSON.stringify(obj)); ``` Returns `output: '{"a":1,"b":2}'`. async/await is supported. The runtime resolves top-level Promises automatically. ## Artifacts (returning images and other non-text content) Console output is text-only. To return an image — or any other typed payload (audio, CSV, arbitr…
| Name | Type | Req | Description |
|---|---|---|---|
| code | string|null | – | – |
| execution_timeout_secs | integer|null | – | – |
| file | string|null | – | – |
| heap_memory_max_mb | integer|null | – | – |
No output schema declared.
No examples provided.
How do I install the mcp-v8 server?
mcp-v8 runs locally as a container image, launched with docker run --rm -i docker.io/wholelottahoopla/mcp-js:0.22.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · docker.io/wholelottahoopla/mcp-js
claude mcp add r33drichards-mcp-js -- docker run --rm -i docker.io/wholelottahoopla/mcp-js:0.22.0
What is the mcp-v8 server?
mcp-v8 is listed in the public MCP registry as io.github.r33drichards/mcp-js. Run JavaScript and TypeScript in sandboxed V8 isolates with policy-controlled host capabilities. This page covers its container image (docker.io/wholelottahoopla/mcp-js).
Is the mcp-v8 server safe to use?
mcp-v8 scores 50 out of 100 on VerifyMCP. 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 mcp-v8 server expose?
mcp-v8 exposes 4 tools: get_artifact, get_artifact_upload_url, list_artifacts, run_js. Their descriptions and schemas cost roughly 1,981 tokens of context every time the server is loaded.
Is the mcp-v8 server still maintained?
mcp-v8 is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the mcp-v8 server under?
mcp-v8 declares the AGPL-3.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.