mcp server
Human For AI
Hire a real human for real-world verification, product testing, AI output review, and errands.
Description as published by the maintainer. Source
- version 0.1.4
- active
active — Most recent push to the repository was 2026-07-19.
What this server can do
4 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
check_task_status(task_id)- Look up a submitted task by its task_id. Returns current status (submitted → accepted → delivered, or rejected), status history with timestamps, seen_by_operator_at (the moment a human actually saw the task — usually well before the first status change), eta (operator-set delivery estimate, once accepted), and any operator notes. Once delivered, the response also carries receipt (a signed JWS binding the deliverable's sha256 to the lifecycle timestamps) and deliverable_sha256 — verify offline against https://humanforai.dev/.well-known/jwks.json. Required: task_id.
get_human_services- Fetch the Human For AI manifest: available services, operator profile (location, languages, working hours), response times, accepted and rejected task types, and trust & safety policy. Call this first to decide whether and how to hire the human. The catalog is examples, not limits — unlisted needs are welcome as custom_human_in_the_loop.
message_human_operator(from, message, subject, reply_to)- Send a free-form message to the human operator — questions, scoping, custom or recurring projects, anything that is not yet a ready-made task. reply_to is REQUIRED (an email you or your principal can read); it is the only way the operator can answer. Required: message, reply_to.
submit_human_task(deadline, delivery, requester, task_type, description, contact_email, output_format, location_detail, location_required)- Submit a task for the human operator to perform in the real world. Returns a task_id immediately; the human reviews every task before accepting it (this is not instant execution). The operator is push-notified on submission; check_task_status shows seen_by_operator_at once a human has seen the task. Free during the pilot. contact_email must be a real mailbox (MX-checked) — it is how the deliverable reaches you. No mailbox? Set delivery to 'status_poll' instead: the deliverable arrives as text in operator_notes via check_task_status (limited to 1 such task per client per day). Required: task_type, description.
Last successful function declaration observed on . Source: https://humanforai.dev/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://humanforai.dev/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 0 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-07-19 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Package downloads | 69 downloads | Package downloads from the npm registry in this window. Includes continuous integration runs, mirrors and automated installs, so it overstates the number of human users. | 2026-07-30 to 2026-08-05 | npm | |
| Latest published version | 0.1.4 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-13 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-13 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 4 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | humanforai.dev | |
| mcp endpoint status | ok | The server listed 4 functions when asked. | as of probe | humanforai.dev |
Where to get it
Related, by what their authors tagged them
-
aden-hive-hive-browser-edge-cases
— last commit 2026-05-29, shares automation, human-in-the-loop
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like L…
-
aden-hive-hive-hive-browser-automation
— last commit 2026-05-29, shares automation, human-in-the-loop
Required before any browser_* tool call. Teaches the screenshot + browser_click_coordinate workflow that reaches shadow…
-
aden-hive-hive-hive-chart-creation-foundations
— last commit 2026-05-29, shares automation, human-in-the-loop
Required reading whenever any chart_* tool is available. Teaches the one-tool embedding contract (call chart_render → l…
-
aden-hive-hive-hive-colony-progress-tracker
— last commit 2026-05-29, shares automation, human-in-the-loop
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message inc…
-
aden-hive-hive-hive-context-preservation
— last commit 2026-05-29, shares automation, human-in-the-loop
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
-
aden-hive-hive-hive-error-recovery
— last commit 2026-05-29, shares automation, human-in-the-loop
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
-
aden-hive-hive-hive-linkedin-automation
— last commit 2026-05-29, shares automation, human-in-the-loop
Read before automating LinkedIn with browser_* tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Ty…
-
aden-hive-hive-hive-note-taking
— last commit 2026-05-29, shares automation, human-in-the-loop
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anyt…
-
aden-hive-hive-hive-quality-monitor
— last commit 2026-05-29, shares automation, human-in-the-loop
Periodically self-assess output quality to catch degradation before the judge does.
-
aden-hive-hive-hive-terminal-tools-foundations
— last commit 2026-05-29, shares automation, human-in-the-loop
Required reading whenever any shell_* tool is available. Teaches the foreground/background dichotomy (terminal_exec aut…
These share tags the maintainers applied themselves, such as automation, human-in-the-loop. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: agents, ai-agents, automation, claude, human-in-the-loop, mcp, mcp-server, model-context-protocol.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json