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.

com.bereviewable/reviewable-artifacts

NPM · REVIEWABLE-ARTIFACTS-MCP

Reviewable workspace discovery and private HTML review creation via stdio MCP.

0 this week 74 Trust /100

Last scanned (20 hours ago)

Scores higher than 49% of npm servers

Category Design and Media

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 13 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency19
Schema Quality & AI Usability65
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2522 tokens (~93/item across 27 items; 27 tools + 0 resources), lean.Pass
  • 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 Coverage86
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 58% of tool parameters carry a description.Partial
Tool Safety88
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "disconnect" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Partial
  • An AI judge read all 28 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

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.

  • 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 →

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.

  • 21 Nov 26 0
    • Stability: 0.97 → pass security
    • Package version: 0.3.1 → 0.4.3 functional
  • 20 Nov 26 0
    • Stability: pass → 0.97 functional
  • 10 Nov 26 0
    • Stability: 0.97 → pass security
  • 9 Nov 26 +1
    • Package version: 0.3.1 → 0.4.3 functional
  • 8 Nov 26 0
    • Package version: 0.3.1 → 0.4.3 functional
  • 7 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 +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.

  • 4 Nov 26 −3
    • Stability: pass → 0.80 functional
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 21 Nov 2026 · Analysed npm/reviewable-artifacts-mcp@0.4.3

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 →

Dependencies 13 packages
Packages resolved 13
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 27 exposed · ~2,482 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
cancel_preparation ~85

Cancels queued or running preparation work while retaining its accepted source for recovery. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
preparationstringyesPreparation job id returned by prepare_review.

No output schema declared.

No examples provided.

check_authorization ~20

Exchanges an approved browser authorization and activates the granted tools.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

close_exploration ~88

Closes the isolated exploration session and releases its runtime capacity. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
reviewstringyesConfigured review session id.
sessionstringyes–

No output schema declared.

No examples provided.

create_review ~136

Creates a private HTML review in the configured owner workspace and returns an owner-only review URL. It never creates or returns a reviewer share link. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
file_namestring–Optional source filename for the artifact.
htmlstringyesComplete HTML artifact to review.
idempotency_keystringyesStable 8-200 character key; reuse it only when retrying the same artifact.

No output schema declared.

No examples provided.

disconnect ~21

Deletes this local MCP profile's web authorization and returns to connection tools.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

freeze_exploration ~115

Persists the exact displayed frame as an immutable review view and returns the identical PNG. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
epochstringyes–
frame_idstringyes–
reviewstringyesConfigured review session id.
sequenceintegeryes–
sessionstringyes–

No output schema declared.

No examples provided.

get_artifact ~148

Returns current artifact HTML, echoes its current version id, and flags whether it differs from a requested snapshot's version_ref.id. include_targets optionally includes projection targets for anchor resolution. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
expected_version_ref––Version ref or version id expected by the caller.
include_targetsboolean–Include projection targets for stable-anchor resolution.
reviewstringyesConfigured review session id.
snapshot_idstring–Snapshot whose version should be compared.

No output schema declared.

No examples provided.

get_connection_state ~21

Reports whether this MCP profile is connected and the next action.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_execution_package ~75

Fetches a self-contained approved execution package by immutable snapshot reference. Apply only the listed actions to their targets. Stop when delivery_state is stale, revoked, blocked, or ambiguous; never infer unrelated changes.

NameTypeReqDescription
reviewstringyesConfigured review session id.
snapshot_idstringyesImmutable execution package snapshot id.

No output schema declared.

No examples provided.

get_exploration ~87

Returns the current frame of an existing isolated exploration session. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
reviewstringyesConfigured review session id.
sessionstringyes–

No output schema declared.

No examples provided.

get_handoff ~121

Fetches the latest snapshot or a requested snapshot id in JSON or Markdown. The export payload is passed through byte-identical. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
formatstring–Export format; json by default.
reviewstringyesConfigured review session id.
snapshot_idstring–Immutable snapshot id; latest when omitted.

No output schema declared.

No examples provided.

get_preparation ~86

Returns one preparation job, its diagnostics, generation, source and resulting review id. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
preparationstringyesPreparation job id returned by prepare_review.

No output schema declared.

No examples provided.

get_review ~103

Composes the session GET with the consolidations list. Returns the authorized role, decision counts, latest snapshot, and the current HTML visual-projection lifecycle with a safe reason code. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
reviewstringyesConfigured review session id.

No output schema declared.

No examples provided.

get_review_evidence ~104

Fetches the immutable review-evidence sidecar with exact source, bundle, view and visual-region attachment references. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
reviewstringyesConfigured review session id.
snapshot_idstringyesImmutable handoff snapshot id.

No output schema declared.

No examples provided.

get_review_evidence_attachment ~117

Fetches one immutable evidence attachment by the id returned from get_review_evidence. Binary bytes are returned as an MCP embedded resource, never injected into text. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
attachment_idstringyes–
reviewstringyesConfigured review session id.
snapshot_idstringyes–

No output schema declared.

No examples provided.

get_review_view ~90

Returns one immutable frozen view and its exact PNG without starting a runtime session. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
reviewstringyesConfigured review session id.
viewstringyes–

No output schema declared.

No examples provided.

get_threads ~89

Returns review threads; accepts a disposition filter. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
dispositionstring–Only return threads with this disposition.
reviewstringyesConfigured review session id.

No output schema declared.

No examples provided.

list_preparations ~69

Lists durable HTML/ZIP preparation jobs visible to this connection. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_review_views ~82

Lists immutable frozen views for the configured review without starting a runtime session. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
reviewstringyesConfigured review session id.

No output schema declared.

No examples provided.

list_reviews ~88

Lists reviews from the configured owner workspace, or only configured share URLs in share mode. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
handoff_statestring––
lifecyclestring––

No output schema declared.

No examples provided.

open_exploration ~102

Opens a short-lived isolated interaction session for the configured review and returns its first exact viewport frame. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
heightinteger––
reviewstringyesConfigured review session id.
widthinteger––

No output schema declared.

No examples provided.

prepare_review ~151

Uploads an explicit local HTML or ZIP path into a durable private preparation job. The server never interprets this path. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
file_namestring–Optional safe .html, .htm or .zip source filename; defaults to the local basename.
file_pathstringyesExplicit path on the MCP client's machine to an HTML or ZIP file.
idempotency_keystringyesStable 8-200 character key; reuse only for the same file.

No output schema declared.

No examples provided.

retry_preparation ~93

Retries a terminal preparation and optionally selects one HTML entry from a ZIP. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
entry_pathstring––
preparationstringyesPreparation job id returned by prepare_review.

No output schema declared.

No examples provided.

send_exploration_input ~139

Sends one event bound to the exact displayed frame and returns the next exact frame. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
epochstringyes–
frame_idstringyes–
inputobjectyesOne pointer, key, scroll, resize, or close event from the closed interaction vocabulary.
reviewstringyesConfigured review session id.
sequenceintegeryes–
sessionstringyes–

No output schema declared.

No examples provided.

start_web_authorization ~48

Starts browser authorization and returns an approval URL plus a human verification code. The code is not a credential.

NameTypeReqDescription
requested_scopestring––
review_session_idstring––

No output schema declared.

No examples provided.

submit_regeneration ~109

Submits one immutable proposed HTML version against the exact execution package named in the result. The server derives agent identity from the grant. Every execution-package action ref must appear exactly once; non-addressed outcomes require a note.

NameTypeReqDescription
artifactobjectyes–
baseobjectyes–
idempotency_keystringyesStable key for this exact result; reuse the identical key when retrying after an uncertain response.
receiptobjectyes–
schemastringyes–

No output schema declared.

No examples provided.

supply_preparation_resources ~95

Uploads explicit local resource files and retries a preparation without overwriting original package files. Handoffs are immutable and additive-only within agent-context/v1; execution packages carry approved work out and regeneration results carry proposed artifacts back. feedback_type and severity are reserved/non-normative, so consumers must not branch on them.

NameTypeReqDescription
preparationstringyesPreparation job id returned by prepare_review.
resourcesarrayyes–

No output schema declared.

No examples provided.

Install

How do I install the com.bereviewable/reviewable-artifacts MCP server?

com.bereviewable/reviewable-artifacts runs locally as an npm package, launched with npx -y reviewable-artifacts-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 · reviewable-artifacts-mcp

# add to Claude Code
claude mcp add com-bereviewable-reviewable-artifacts -- npx -y reviewable-artifacts-mcp
Common questions

What is the com.bereviewable/reviewable-artifacts MCP server?

com.bereviewable/reviewable-artifacts is an MCP server listed in the public MCP registry as com.bereviewable/reviewable-artifacts. Reviewable workspace discovery and private HTML review creation via stdio MCP. This page covers its npm package (reviewable-artifacts-mcp).

Is the com.bereviewable/reviewable-artifacts MCP server safe to use?

com.bereviewable/reviewable-artifacts scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting 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 com.bereviewable/reviewable-artifacts MCP server expose?

com.bereviewable/reviewable-artifacts exposes 27 tools: get_connection_state, start_web_authorization, check_authorization, disconnect, list_reviews, and 22 more. Their descriptions and schemas cost roughly 2,482 tokens of context every time the server is loaded.

Is the com.bereviewable/reviewable-artifacts MCP server still maintained?

com.bereviewable/reviewable-artifacts 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 licence is the com.bereviewable/reviewable-artifacts MCP server under?

com.bereviewable/reviewable-artifacts declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the com.bereviewable/reviewable-artifacts MCP server?

VerifyMCP ran 15 checks on com.bereviewable/reviewable-artifacts, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about com.bereviewable/reviewable-artifacts: 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.