What did Hlido score ProposalCraft?

ProposalCraft scored 68/100 (FADING) in Hlido's independent, hands-on review.

How much does ProposalCraft cost?

Hlido recorded the pricing model as: Open source · Free tier. Derived from evidence Hlido holds, not vendor-supplied; verify current prices on the vendor's pricing page.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

ProposalCraft

Name: ProposalCraft review
Item: ProposalCraft
Rating: 68
Author: Hlido Editor

Productivity · tested 2026-08-07 · re-test due 2026-11-07 · by the Hlido desk, not the vendor

In short: An MCP server that drafts client proposals in your own voice, learned from ones that already won — tightly scoped, local-only, and honest that it is a launch-day project.

5 PASS · 0 FAIL of 5 public-surface claims

Visit ProposalCraft → scorecard.json

Quick answer

ProposalCraft scores 68/100 (FADING) on Hlido’s independent, hands-on test (reviewed 2026-08-07). FADING (68) — well-scoped, sensibly defaulted (local storage, MIT, no API key) and demonstrated with a concrete worked example rather than an abstraction. Pricing: Open source · Free tier (free entry point documented).

Hlido Editor · 2026-08-07

ProposalCraft is an MCP server for freelancers and agencies: paste a client brief into Claude and it drafts a send-ready proposal — structured, scoped and priced — in the voice learned from proposals that previously won you work. The scoping is its strength. It does one job, states its constraints plainly on the surface (29 tools, freemium with a free-forever tier, no API key required, works with Claude Desktop and any MCP client, TypeScript, MIT licence, local storage so your data stays yours), and demonstrates the value with a concrete worked example rather than an abstract claim: a real-shaped client email about a Shopify redesign in, a proposal with discovery/design/build phases, deliverables, an investment table and next steps out. Local-only storage is the right default for commercially sensitive material like past proposals and pricing, and MIT plus no-API-key removes the usual adoption friction. Against that: the page carries a "launching on Product Hunt today" banner, so this is day-one software with no track record; there are no customers, usage figures or third-party validation; and the core claim — that it learns and reproduces *your* voice — is precisely the thing that cannot be assessed without feeding it real winning proposals, which we did not do. Output quality on a first-party demo example is weak evidence for a personalisation claim.

Why FADING

FADING (68) — well-scoped, sensibly defaulted (local storage, MIT, no API key) and demonstrated with a concrete worked example rather than an abstraction. Held at FADING because it is launch-day software with no track record, no users and no third-party validation, and its central claim — reproducing your winning voice — is unverifiable from a vendor-authored demo.

Public-surface checklist

PASS Homepage loads (required)
PASS Primary value prop (required) — 'Win more clients. Write fewer proposals.'
PASS Cta present (required) — 'Install free' / 'Get started free'
PASS Pricing or access — Freemium, free-forever tier; boundary not specified
PASS Evidence or demo — Detailed worked example; vendor-authored, no third-party proof

What we saw

4 screenshots captured by the Hlido engine during the reviewed run (run-7e6f326984f7b17c-jabbawocky-github-io). Our own captures — not vendor marketing material.

ProposalCraft — run screenshot 1 (home.png) — home.png

ProposalCraft — run screenshot 2 (pageguide_html.png) — pageguide_html.png

ProposalCraft — run screenshot 3 (page_install.png) — page_install.png

ProposalCraft — run screenshot 4 (page_install.png) — page_install.png

What it does well

Tightly scoped to one job — brief in, send-ready proposal out — with no feature sprawl
Local storage by default: past proposals and pricing never leave the machine
No API key required, MIT licensed, free-forever tier — minimal adoption friction
Concrete worked example (real-shaped brief → structured proposal with phases, deliverables, investment table)
29 MCP tools; works with Claude Desktop and any MCP client
States its constraints openly on the landing page rather than burying them

What it fails at

Launch-day project (Product Hunt banner live) — no track record whatsoever
No customers, usage figures, or third-party validation
The core personalisation claim is unverifiable from a vendor-authored demo
Proposal quality depends entirely on the corpus of past proposals a user supplies — unaddressed on the surface
Freemium boundary is not specified: what the free-forever tier excludes is unclear
Not tested by us with real winning proposals, which is the only meaningful test

Best for

Freelancers and small agencies who write similar proposals repeatedly
Claude Desktop users who want drafting inside their existing workflow
Anyone unwilling to upload commercially sensitive pricing to a cloud service

Not recommended for

Teams needing collaborative review, approvals or version control on proposals
Buyers who require a track record before trusting client-facing output
Users without a body of past proposals for it to learn from

Pricing & access

ModelOpen source · Free tier
Free entry pointYes — a free tier or open-source edition is documented
Pricing findable on the public surfacePASS Freemium, free-forever tier; boundary not specified (tested 2026-08-05)

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-08-05.

Related agents

Agent relevance

MCP Behavioral-testable

Agentic-Commerce Readiness 59/100 · INTEGRABLE

Independent readiness for agent delegation & transaction. How it’s scored · check live

MCP-native: 29 tools invoked from Claude Desktop or any MCP client, with no separate UI. The agent does the drafting inside the user's existing assistant.

Agent-friendly score: 8/10

Evidence

MCP server drafting proposals from a client brief, in the user's learned voice — source (2026-08-07) verified
29 tools, TypeScript, MIT licence, no API key required — source (2026-08-07) verified
Local storage — user data stays on the machine — source (2026-08-07) verified
Freemium with a free-forever tier — source (2026-08-07)
Launching on Product Hunt on the day of review — no track record — source (2026-08-07) verified

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: public-surface-tier-1+editorial-narrative-v2 · Methodology version 2026.05 · Next review due 2026-11-07

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/jabbawocky-proposalcraft.svg)](https://hlido.eu/check/?agent=jabbawocky-proposalcraft)

HTML

<a href="https://hlido.eu/check/?agent=jabbawocky-proposalcraft"><img src="https://hlido.eu/badge/jabbawocky-proposalcraft.svg" alt="Hlido trust score"></a>