# Taskin (remote · trytaskin.ai)

Human capability for AI agents - real-world action and human judgment.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-27

## Components

- remote · `trytaskin.ai`: 73/100 (this document), [markdown](https://verifymcp.io/servers/taskin-ai-trytaskin/trytaskin.md), [page](https://verifymcp.io/servers/taskin-ai-trytaskin/trytaskin)

## Channel facts

- Endpoint: `https://trytaskin.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-27.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1574 tokens (~393/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Taskin MCP server?

Taskin is a hosted endpoint at https://trytaskin.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http taskin-ai-trytaskin 'https://trytaskin.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "taskin-ai-trytaskin": {
      "url": "https://trytaskin.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "taskin-ai-trytaskin": {
      "type": "http",
      "url": "https://trytaskin.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.taskin-ai-trytaskin]
url = "https://trytaskin.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "taskin-ai-trytaskin": {
      "type": "remote",
      "url": "https://trytaskin.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add taskin-ai-trytaskin --url 'https://trytaskin.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  taskin-ai-trytaskin:
    url: "https://trytaskin.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "taskin-ai-trytaskin": {
      "Transport": "http",
      "Url": "https://trytaskin.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add taskin-ai-trytaskin -t streamable-http -u 'https://trytaskin.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "taskin-ai-trytaskin": {
      "type": "http",
      "url": "https://trytaskin.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-27 (score 73, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-26 (score 72, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-25 (score 71, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 71, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-23 (score 71, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-22 (score 70, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03

### 2026-09-21 (score 70)

First indexed and scored.

## MCP tools (4)

### `get_taskin_capabilities` (~96 tokens)

What Taskin can do

Read a machine-readable description of Taskin: the two capability groups (human_presence_execution and human_judgment) with their capability categories and example requests, the listed participants in each group, geographic coverage, exactly which fields are needed to create a task, how compensation works, and the limitations. Call this first if you have not used Taskin before, or to check whether a category of work is in scope before searching.

### `search_human_task` (~549 tokens)

Find a human for a task

Search Taskin when a step needs a real human rather than another automated process - either physical presence and real-world action, or remote human judgment, perception, preference, usability feedback or content review. Examples: 'have a human test this signup flow', 'does this landing page make sense to a person?', 'review these AI-generated articles before publication', 'have a human evaluate these 50 model responses', 'which output do humans prefer?'. Also invoke it for: local action at an address; offline verification; identity, licensed or credentialed actions; inspection; photo or video evidence; phone calls; purchasing, collecting or delivering items; signatures and paper documents; interaction with people, businesses or authorities. Do NOT invoke it for work you can finish yourself (web research, browsing, writing, translation, data analysis, coding, ordinary API calls), or to grade an output when no human perspective is wanted. Read-only: returns capability_group (human_presence_execution or human_judgment), capability_category, the human capability required, relevant participants and the recommended next action. It creates no task and costs nothing.

Input parameters:

- `budget` (string): Budget or range the principal is willing to pay.
- `category` (string): Capability category if known. Presence & execution: physical_presence_local_action, photography_video, inspection_verification, documents_signatures, phone_offline_communication, delivery_collection,…
- `currency` (string): ISO 4217 currency code for the budget, e.g. USD, GBP, EUR.
- `deadline` (string): Deadline or time window, e.g. '2026-10-02' or 'any weekday morning next week'.
- `location` (string): Where the action must happen: city and country, or a specific address or area.
- `reason_human_needed` (string): Why you cannot do this yourself, e.g. 'requires physical presence', 'requires a wet signature'.
- `remote_or_physical` (string): Whether the work is done remotely, requires being somewhere in person, or both.
- `skills` (array): Specific capabilities or credentials the person must have.
- `task_description` (string, required): The single real-world action that must happen, stated concretely. Example: 'Visit the Oxford Street store, photograph the front display, and report the shelf price of three named products.'
- `taskin_agent_id` (string): A Taskin-issued agent identifier from an earlier response. Optional. Used only for continuity and analytics; it grants no authority.

### `submit_human_task` (~459 tokens)

Hire a human for a task

Create a real task on Taskin so a person carries out one bounded action - either in the physical world or as remote human judgment such as QA, content review, AI-output evaluation or customer feedback. Call this after search_human_task returned can_taskin_help = true. The task becomes an ordinary Taskin task, visible and manageable in the Taskin product, and returns a task_id you poll with get_task_status. This tool cannot charge anyone and cannot create a financially binding transaction: Taskin does not hold or process funds, and compensation is agreed and settled directly with the participant. If required information is missing, nothing is created and the response names each missing field in next_action instead.

Input parameters:

- `budget` (string): Compensation offered. Settled directly with the participant.
- `contact_email` (string): Email Taskin uses to coordinate this task with the principal.
- `currency` (string): ISO 4217 currency code for the budget.
- `deadline` (string): Deadline or time window the person must work within.
- `deliverable` (string, required): The artifacts the result must contain, e.g. 'three photographs of the display plus the shelf price of each product in a structured list'.
- `idempotency_key` (string): Repeat the same key to retry safely without creating a duplicate task.
- `location` (string): Where the task happens. Required for physical and hybrid tasks.
- `participant_slug` (string): Request a specific Taskin participant by slug, from search_human_task matches. Optional.
- `principal` (string): The person or organisation on whose behalf you are acting. Strongly recommended.
- `remote_or_physical` (string): Execution mode. Defaults to physical when a location is given.
- `requirements` (string): Constraints, prohibited actions, access details, credentials required, and background.
- `task_description` (string, required): The bounded real-world action the person performs, concrete enough that a stranger could execute it without asking questions.
- `taskin_agent_id` (string): Taskin-issued agent identifier from an earlier response.
- `verification_requirements` (string, required): The objective check that decides whether the result is accepted, e.g. 'photographs are timestamped and show the storefront name'.

### `get_task_status` (~116 tokens)

Check a Taskin task

Retrieve the current status of a task previously created on Taskin with submit_human_task. Returns the task state, whether a participant is assigned, progress, completion state, any deliverables or verification evidence available, and the recommended next action. Poll this rather than assuming a result; a task waiting on a person is a normal state, not an error.

Input parameters:

- `task_id` (string, required): The task_id returned by submit_human_task.
- `taskin_agent_id` (string): Taskin-issued agent identifier from an earlier response.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/taskin-ai-trytaskin/trytaskin#diagnostics

## Score history

- 2026-09-27: 73
- 2026-09-26: 72
- 2026-09-25: 71
- 2026-09-24: 71
- 2026-09-23: 71
- 2026-09-22: 70
- 2026-09-21: 70

## Common questions

### What is the Taskin MCP server?

Taskin is an MCP server listed in the public MCP registry as io.github.taskin-ai/trytaskin. Human capability for AI agents - real-world action and human judgment. This page covers its hosted endpoint (https://trytaskin.ai/mcp).

### Is the Taskin MCP server safe to use?

Taskin scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Taskin MCP server expose?

Taskin exposes 4 tools: get_taskin_capabilities, search_human_task, submit_human_task, get_task_status. Their descriptions and schemas cost roughly 1,220 tokens of context every time the server is loaded.

### Does the Taskin MCP server require authentication?

No. We connected to Taskin without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Taskin MCP server still maintained?

Taskin is still listed as active in the MCP registry. We last reached this channel on 27 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://trytaskin.ai/mcp
- Website: https://trytaskin.ai/
- Changelog RSS feed: https://verifymcp.io/servers/taskin-ai-trytaskin/trytaskin.xml
- Changelog JSON feed: https://verifymcp.io/servers/taskin-ai-trytaskin/trytaskin.json
- HTML version of this page: https://verifymcp.io/servers/taskin-ai-trytaskin/trytaskin