Leafwright MCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Leafwright PDF template generation and render diagnostics: Do signed PDF URLs and logs preserve account privacy while template-debugging tools evolve?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Render HTML, URLs and templates into PDF documents.

What we know

Render HTML, URLs, and templates to PDF. AI drafts templates and fixes them from logs. Exact operational authority remains unverified from first-party package documentation and must not be inferred. Source-derived feature labels are preliminary; obtain official runtime/tool evidence before applying uncertain fields.

Maintenance / activity evidence

@leafwright/mcp 0.2.4 published 2026-09-08T03:47:31.439Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: low.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Permissions not yet verified. Complete write authority is not verified.
Authentication not yet verified.
Sensitive access: HTML and URL inputs, Potential document contents

Authority is not fully established. Do not treat unknown writes/auth as read-only or absent.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do signed PDF URLs and logs preserve account privacy while template-debugging tools evolve?

The bounded review of the publisher's documented Leafwright PDF template generation and render diagnostics and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Authority is not fully established. Do not treat unknown writes/auth as read-only or absent.
Sensitive access: HTML and URL inputs, Potential document contents
Complete write authority is not verified.
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
repositoryIdentity: no confirmed package-to-repository binding
authentication: exact official auth and credential handling
writeActions: exact exposed tool mutation authority
dataHandling: provider destinations, retention and egress
cost: plans, pay-per-call charges, and payment authorization details
transport and actual executable entry point
Whether local or hosted renderer executes is not verified
Input URLs may contain private resources, auth, or SSRF-sensitive targets
Document storage and output destination require confirmation
Do not apply unverified auth, permissions, transport, lifecycle or write actions; preserve any better existing profile values.

Original activity observations

@leafwright/mcp 0.2.4 published 2026-09-08T03:47:31.439Z

Technical identity

npm/@leafwright/mcp

Exact implementation source: https://www.npmjs.com/package/@leafwright/mcp ↗
Reviewed resource type: MCP Server
Package identity: npm:@leafwright/mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry ↗
@leafwright/mcp
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
Remote OAuth preferred; npx local stdio uses LEAFWRIGHT_API_KEY.
publisher install or stdio launch · Claude Code only · Publisher instructions
claude mcp add --transport http leafwright https://leafwright.co/mcp
Configure / authenticate
MCP100 setup guide
Leafwright supports remote OAuth (no install) and local stdio via npx with LEAFWRIGHT_API_KEY; distinguish methods.
Check connection
Suggested check
For remote mode, complete OAuth then inspect available tools; for local mode set LEAFWRIGHT_API_KEY and verify read-only tool discovery. Do not create designs.
Remove / uninstall / revoke
MCP100 setup guide
If you added this integration to Claude Code under the registration name `leafwright`, run `claude mcp remove leafwright` to unregister that client entry. In Claude Desktop, Cursor, VS Code or another host, delete/disable the corresponding named MCP registration in that host's settings and restart/reconnect. If you installed an npm package globally or operate a separate HTTP server, uninstall/stop it with its original deployment method. This does not delete user data or revoke service credentials.
MCP client unregister, stopping hosted processes, package uninstall, OAuth disconnect and token revocation are distinct actions.
A claude mcp remove command is only valid for Claude Code when the local registration actually has that name. Other MCP hosts require their own UI/config cleanup.
Separate provider credential revocation · publisher documented: Leafwright documents MCP tool `leafwright_logout` as revoking and clearing local MCP auth. This is stronger than a file delete. LEAFWRIGHT_API_KEY / LEAFWRIGHT_MCP_TOKEN are separate project/noninteractive credentials, with no precise published dashboard deletion steps in reviewed MCP doc.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove leafwright

Official Documentation & Sources

What it does

Render HTML, URLs, and templates to PDF. AI drafts templates and fixes them from logs. Exact operational authority remains unverified from first-party package documentation and must not be inferred. Source-derived feature labels are preliminary; obtain official runtime/tool evidence before applying uncertain fields.

Capability: Design & Creative
Resource type: MCP Server
Best fit: Render HTML, URLs and templates into PDF documents.

Representative uses

Render a supplied HTML document to PDF
Convert a webpage URL to a document
Review rendering errors

Limitations

Whether local or hosted renderer executes is not verified
Input URLs may contain private resources, auth, or SSRF-sensitive targets
Document storage and output destination require confirmation
Do not apply unverified auth, permissions, transport, lifecycle or write actions; preserve any better existing profile values.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Not documented in the reviewed sources
Permissions: Not documented in the reviewed sources
Data handling: Not documented in the reviewed sources
Cost: Not documented in the reviewed sources
Risk and cautions: Authority is not fully established. Do not treat unknown writes/auth as read-only or absent.

Access scope and cautions

Write actions: Not verified
Sensitive access: HTML and URL inputs Potential document contents

The reviewed evidence does not establish the complete write authority of this MCP. Consult the unresolved evidence before granting write access.

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The available discovery description lists: Render a supplied HTML document to PDF; Convert a webpage URL to a document; Review rendering errors. These descriptions do not establish a fully verified tool inventory.

Can it modify data or perform write operations?

Not verified. The available evidence does not establish the complete write authority.

What data-handling boundary should I consider?

Recorded sensitive-access context: HTML and URL inputs; Potential document contents.

What limitations and risks should I check before use?

Authority is not fully established. Do not treat unknown writes/auth as read-only or absent. Whether local or hosted renderer executes is not verified. Input URLs may contain private resources, auth, or SSRF-sensitive targets. Document storage and output destination require confirmation. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.