Skip to content
Errand logo

Errand

Dispatches humans to complete physical-world tasks requested by AI agents through an API, MCP server or REST endpoint.

AutomationAPIMobile app
errand.be ↗
At a glanceswept 2026-10-12

not read yet

Use

For
Developers of AI agents who need humans to complete physical-world tasks.
Price
Price not read
Activity
Activity not read yet
Company
founding year not on record
Runs as
APIMobile app
AlternativesSet it up for my teamIs Errand yours? Claim the card →
What people do with it
  • Verify a physical location with a GPS-tagged photo
  • Assign a nearby person an in-person errand
  • Post a paid task with a reward and deadline
The companyeach fact with its source · read 2026-10-14
  • Headquarters강남구, KRper their site
How a program reaches itfound, not claimed · read 2026-10-14
  • MCP serverbe.errand/errandverified in the MCP registry
  • Stateanswers, 7 toolschecked 2026-10-14
  • Address to connecterrand.be/api/mcp
  • MCP docserrand.be/mcpthe 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 Automationby use, among tools still maintained

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

All Automation tools →

Questions this page answers
  • What is Errand?

    Dispatches humans to complete physical-world tasks requested by AI agents through an API, MCP server or REST endpoint. It is listed in the Atlas under Automation.

  • Who is Errand for?

    Developers of AI agents who need humans to complete physical-world tasks.

  • Do people use Errand?

    Little sign of use.

  • What are alternatives to Errand?

    In Automation, by use: Friday AI, Project Desk, Agentic Terminal, Zapier, Simular, Make.

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.