Project Desk
Separates decisions needing your judgment from scoped tasks an agent can take, with connected agents updating the board through MCP.
≈ 1visits/mo
Little sign of use · estimate, read 2026-10-12
- For
- Software builders directing AI agents across several projects who need to know what needs their judgment
- Price
- Free plan · From $10/mopricing page, read 2026-10-12 ↗
- Activity
- Activity not read yet
- Company
- Wilds, Inc. · Domain since 2026privacy policy · domain registered
- separate decisions needing your judgment from work agents can take
- review what connected agents changed and proved on each project
- keep open decisions out of the agent queue
- Domain since2026domain registered
- HeadquartersMassachusetts, USAper their About page
- Run byWilds, Inc.privacy policy ↗
- Trains on your dataNotrust center ↗
- Trust centertheir owntrust center ↗
- Privacy policy updated2026-06-24privacy policy ↗
“We do not use your desk content to train AI models, and we do not sell it or use it for advertising.”
trust center ↗
These are Project Desk's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.
- MCP serverai.atlier/project-deskverified in the MCP registry
- Stateanswers, requires sign-inchecked 2026-10-13
- Address to connectatlier.ai/mcp
- MCP docsatlier.ai/mcpthe vendor's page ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1
Meterless.ai
Preserves AI workflows and decisions as reusable missions independent of model changes.
22 linking domainsActive—2026 - #2
Agentic TerminalMCP · open
Matches posted tasks with agents, verifying each party's identity and settling payments directly between them over Lightning and USDT.
Little sign of usenot read— - #3
DazbenchMCP · sign-in
Holds task cards with purpose, background and acceptance criteria that connected AI assistants read and update over MCP.
Little sign of useActive— - #4
ZapierMCP · sign-in
Connects and automates workflows across 9,000 apps without code.
7.1MActiveFrom $19.99/mo2012 - #5
Simular
Runs autonomous agents on your computer to automate repetitive screen tasks and workflows.
520kActiveFrom $50/mo2023 - #6
Make
Connects apps and data sources to build automations and AI agents visually or by prompt.
432knot readFrom $9/mo
What is Project Desk?
Separates decisions needing your judgment from scoped tasks an agent can take, with connected agents updating the board through MCP. It is listed in the Atlas under Automation and made by Wilds, Inc.
Who is Project Desk for?
Software builders directing AI agents across several projects who need to know what needs their judgment
How much does Project Desk cost?
Project Desk has a free plan; paid plans start at $10/mo, per its pricing page on 2026-10-12.
Is Project Desk free?
Yes, Project Desk has a free plan, per its pricing page on 2026-10-12.
Do people use Project Desk?
Little sign of use: ≈ 1 visits/mo · estimate, 2026-10.
Who owns Project Desk?
Project Desk is run by Wilds, Inc., per its privacy policy (2026-10-12).
Does Project Desk train AI on your data?
No, per its trust center (2026-10-12): “We do not use your desk content to train AI models, and we do not sell it or use it for advertising.”
Is Project Desk safe?
We do not audit vendors. What Project Desk publishes, read 2026-10-12: a trust center; on training with your data, “We do not use your desk content to train AI models, and we do not sell it or use it for advertising.”.
Does Project Desk give refunds?
In its own words (terms of service, 2026-10-12): “Billing, cancellation, and refunds — including a 14-day money-back guarantee on your first payment — are described in our Refund & Cancellation Policy.”
What are alternatives to Project Desk?
In Automation, by use: Meterless.ai, Agentic Terminal, Dazbench, Zapier, Simular, Make.
Not quite it? Describe the job
betaFive tools from the Atlas that fit it, each judged against what you wrote.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.