HumanOps
NPM · @HUMANOPS/MCP-SERVER · SCANNED OCT 4
MCP server for AI agents to dispatch real-world tasks to verified human operators
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 236 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability77
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1387 tokens (~99/item across 14 items; 14 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
- Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 80% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the HumanOps MCP server?
HumanOps runs locally as an npm package, launched with npx -y @humanops/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @humanops/mcp-server
claude mcp add thepianistdirector-humanops -- npx -y @humanops/mcp-server
{
"mcpServers": {
"thepianistdirector-humanops": {
"command": "npx",
"args": [
"-y",
"@humanops/mcp-server"
]
}
}
} {
"servers": {
"thepianistdirector-humanops": {
"command": "npx",
"args": [
"-y",
"@humanops/mcp-server"
]
}
}
} codex mcp add thepianistdirector-humanops -- npx -y @humanops/mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"thepianistdirector-humanops": {
"type": "local",
"command": [
"npx",
"-y",
"@humanops/mcp-server"
],
"enabled": true
}
}
} openclaw mcp add thepianistdirector-humanops --command npx --arg -y --arg @humanops/mcp-server
mcp_servers:
thepianistdirector-humanops:
command: "npx"
args: ["-y", "@humanops/mcp-server"] {
"McpServers": {
"thepianistdirector-humanops": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@humanops/mcp-server"
]
}
}
} assistant mcp add thepianistdirector-humanops -t stdio -c npx -a -y @humanops/mcp-server
{
"mcpServers": {
"thepianistdirector-humanops": {
"command": "npx",
"args": [
"-y",
"@humanops/mcp-server"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Sept 26 −3
- Stability: pass → 0.80 functional
- 29 Sept 26 +1
- Stability: 0.97 → pass security
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Sept 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 23 Sept 26 −3
- Stability: pass → 0.80 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Oct 2026 · Analysed npm/@humanops/mcp-server@0.2.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cancel_task ~45
Cancel a pending or accepted task. The escrowed funds (reward + platform fee) will be refunded to your account.
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | yes | The task ID to cancel |
No output schema declared.
No examples provided.
check_verification_status ~39
Check the AI Guardian verification status and result for a task. Returns focused verification details including decision and confidence.
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | yes | – |
No output schema declared.
No examples provided.
dispatch_credential_task ~239
Create a task requiring a human operator to deliver credentials (account login, API key, phone verification code, etc.) via an end-to-end encrypted channel. A unique ECDH keypair is generated automatically — only you can decrypt the result. The server never sees plaintext credentials. IMPORTANT: Save the returned private_key — you need it to call retrieve_credential later.
| Name | Type | Req | Description |
|---|---|---|---|
| callback_secret | string | – | Optional secret to sign webhook callbacks |
| callback_url | string | – | Optional webhook URL for status updates |
| deadline | string | yes | ISO 8601 deadline for task completion |
| description | string | yes | Detailed description of what credentials are needed |
| digital_category | string | yes | Category of credential task |
| digital_instructions | string | – | Step-by-step instructions for the operator |
| idempotency_key | string | – | Optional key to make task creation safe to retry |
| proof_requirements | array | yes | List of proof requirements (e.g., 'screenshot of account creation') |
| reward_usd | number | yes | Reward in USD for the operator |
| title | string | yes | Short title for the credential task |
No output schema declared.
No examples provided.
dispatch_digital_task ~197
Create a Tier 1 digital task for a human operator. Includes CAPTCHA solving, form filling, browser interaction, content review, and data validation. No physical location needed — operators complete these tasks remotely.
| Name | Type | Req | Description |
|---|---|---|---|
| callback_secret | string | – | Optional secret to sign webhook callbacks |
| callback_url | string | – | Optional webhook URL for status updates |
| deadline | string | yes | ISO 8601 deadline for task completion |
| description | string | yes | Detailed description of what needs to be done |
| digital_category | string | yes | Category of digital task |
| digital_instructions | string | – | Specific step-by-step instructions for the digital task |
| idempotency_key | string | – | Optional key to make task creation safe to retry |
| proof_requirements | array | yes | List of proof requirements |
| reward_usd | number | yes | Reward in USD for the operator |
| title | string | yes | Short title for the task |
No output schema declared.
No examples provided.
fund_account ~189
Add funds to your HumanOps account. **Recommended: use USDC deposits** (default). Send USDC to your deposit address (get it via get_deposit_address), then call this with the tx_hash to verify. Fiat methods (card, bank_transfer) are coming soon.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | yes | Amount in USD (min: $5, max: $10,000). For USDC deposits, this is the expected amount. |
| chain | string | – | Blockchain network the USDC was sent on (required for USDC deposits). Base recommended for lowest fees. |
| payment_method | string | – | Payment method. Defaults to 'usdc'. Card and bank_transfer are coming soon. |
| return_url | string | – | Optional return URL after fiat payment (not used for USDC) |
| tx_hash | string | – | On-chain transaction hash (required for USDC deposits) |
No output schema declared.
No examples provided.
get_balance ~33
Check your HumanOps account balances. Returns deposit balance (available to create tasks) and escrow balance (locked in active tasks).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_deposit_address ~54
Get your USDC deposit address. Send USDC to this address on a supported chain (Base, Polygon, Ethereum, Arbitrum) to fund your HumanOps account. This is the recommended way to add funds.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_task_result ~33
Get the current status, proof, and AI Guardian verification result for a task.
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | yes | – |
No output schema declared.
No examples provided.
list_digital_categories ~43
List available digital task categories with descriptions, pricing, and trust tier requirements. Returns both Tier 1 (standard digital) and Tier 2 (credential) categories.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_tasks ~80
List your tasks with optional status filter. Returns paginated results ordered by creation date.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max results (default: 20, max: 100) |
| offset | number | – | Pagination offset (default: 0) |
| status | string | – | Filter by status (e.g., PENDING, ACCEPTED, COMPLETED) |
No output schema declared.
No examples provided.
post_task ~197
Create a new task for a human operator. Supports physical tasks (VERIFICATION, PHOTO, DELIVERY, INSPECTION), digital tasks (CAPTCHA_SOLVING, FORM_FILLING, etc.), and credential tasks (ACCOUNT_CREATION, API_KEY_PROCUREMENT, etc.). For digital tasks prefer dispatch_digital_task; for credential tasks prefer dispatch_credential_task. Funds will be escrowed from your account (reward + platform fee).
| Name | Type | Req | Description |
|---|---|---|---|
| callback_secret | string | – | Optional secret to sign webhook callbacks |
| callback_url | string | – | – |
| deadline | string | yes | ISO 8601 deadline for task completion |
| description | string | yes | – |
| idempotency_key | string | – | Optional key to make task creation safe to retry |
| location | object | yes | – |
| proof_requirements | array | yes | – |
| reward_usd | number | yes | – |
| task_type | string | yes | – |
| title | string | yes | – |
No output schema declared.
No examples provided.
request_payout ~45
Request a payout of available earnings. Currently only available through the HumanOps operator portal.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | yes | Amount to withdraw in USD (min: $10) |
No output schema declared.
No examples provided.
retrieve_credential ~88
Retrieve and decrypt the credential delivered by a human operator for a completed Tier 2 task. Requires the private_key returned by dispatch_credential_task. The decryption happens locally — the server never sees the plaintext.
| Name | Type | Req | Description |
|---|---|---|---|
| private_key | string | yes | The base64-encoded private key returned by dispatch_credential_task |
| task_id | string | yes | The task ID from dispatch_credential_task |
No output schema declared.
No examples provided.
search_operators ~105
Search for available human operators near a location who can perform real-world tasks like verifications, photo documentation, deliveries, and inspections.
| Name | Type | Req | Description |
|---|---|---|---|
| lat | number | yes | Latitude of the task location |
| lng | number | yes | Longitude of the task location |
| min_rating | number | – | Minimum operator rating (0-5) |
| radius_km | number | – | Search radius in kilometers (default: 50, max: 500) |
| task_type | string | – | – |
No output schema declared.
No examples provided.
What is the HumanOps MCP server?
HumanOps is an MCP server listed in the public MCP registry as io.github.thepianistdirector/humanops. MCP server for AI agents to dispatch real-world tasks to verified human operators. This page covers its npm package (@humanops/mcp-server).
Is the HumanOps MCP server safe to use?
HumanOps scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 October 2026. It declares no install or post-install scripts. 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 HumanOps MCP server expose?
HumanOps exposes 14 tools: search_operators, post_task, dispatch_digital_task, dispatch_credential_task, retrieve_credential, and 9 more. Their descriptions and schemas cost roughly 1,387 tokens of context every time the server is loaded.
Is the HumanOps MCP server still maintained?
HumanOps is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the HumanOps MCP server under?
HumanOps declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.