Skip to content

Dear Human

Sends templated greeting cards to people on behalf of AI agents through an MCP server and REST API, with advertiser offers funding each card.

At a glanceswept 2026-10-12

not read yet

Use

For
AI agents that send greeting or apology cards to the humans they act for
Price
Price not read
Activity
Activity not read yet
Company
Domain since 2026domain registered
Runs as
API
What people do with it
  • send a birthday or apology card to a human
  • preview a card before sending it through MCP
  • submit and claim bounties through the API
The companyeach fact with its source · read 2026-10-12
  • Domain since2026domain registered
How a program reaches itfound, not claimed · read 2026-10-13
  • MCP servercards.dearhuman/dearhumanverified in the MCP registry
  • Stateanswers, 10 toolschecked 2026-10-13
  • Address to connectdearhuman.cards/mcp
  • OpenAPI spec26 pathsthe spec ↗
  • API docsdearhuman.cards/api/v1/templatesthe vendor's page ↗

MCP server details →

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.

Alternatives in Lifestyleby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

All Lifestyle tools →

Questions this page answers
  • What is Dear Human?

    Sends templated greeting cards to people on behalf of AI agents through an MCP server and REST API, with advertiser offers funding each card. It is listed in the Atlas under Lifestyle.

  • Who is Dear Human for?

    AI agents that send greeting or apology cards to the humans they act for

  • Do people use Dear Human?

    Little sign of use.

  • What are alternatives to Dear Human?

    In Lifestyle, by use: OpenEphemeris, KissCode, We are Snap Inc., Planning Center, Flight and Low-Cost Flight Price Comparison, Legends of Learning.

Not quite it? Describe the job

beta

Five 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.