A Human For Hire
NPM · AHFH-MCP
Hire a real human over x402: pay USDC on Solana, post tasks to a human desk, poll replies as JSON.
Available components
Last scanned (18 hours ago)
Scores higher than 29% of npm servers
Category Communication
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 Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 32 of 153 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. 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 7 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability75
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 384 tokens (~64/item across 6 items; 6 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 67% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "submit_payment" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 6 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
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 21 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Nov 26 57
First indexed and scored.
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 21 Nov 2026 · Analysed npm/ahfh-mcp@1.0.1
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 →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 153 packages
| Packages resolved | 153 |
|---|---|
| Stale | 32 |
| 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 →
build_payment ~53
Sign the x402 payment for an item with the wallet in AHFH_PRIVATE_KEY. Returns a PAYMENT-SIGNATURE string. Pass it to submit_payment.
| Name | Type | Req | Description |
|---|---|---|---|
| itemId | string | yes | item id from get_catalog |
No output schema declared.
No examples provided.
get_catalog ~32
List everything the human desk sells: task items with prices in USDC on Solana. Free, no payment needed.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_replies ~54
Poll the human desk for replies to your task. Poll about every 15 seconds. Requires the same seat token and txid as post_task.
| Name | Type | Req | Description |
|---|---|---|---|
| seatToken | string | yes | – |
| txid | string | yes | – |
No output schema declared.
No examples provided.
post_task ~90
Post your task to the human desk over the machine lane. Requires the seat token from submit_payment and the settled transaction id. The human sees it instantly on the desk board.
| Name | Type | Req | Description |
|---|---|---|---|
| seatToken | string | yes | 64-hex seat token from submit_payment |
| task | string | yes | full task text for the human |
| txid | string | yes | settled Solana transaction id from submit_payment receipt |
No output schema declared.
No examples provided.
quote_item ~70
Get the exact x402 payment requirement for an item id from get_catalog. Returns the 402 challenge (amount, payTo address, asset, facilitator). Sign this with build_payment or your own signer.
| Name | Type | Req | Description |
|---|---|---|---|
| itemId | string | yes | item id from get_catalog, e.g. inapp-captcha |
No output schema declared.
No examples provided.
submit_payment ~85
Send the signed payment (PAYMENT-SIGNATURE from build_payment or your own x402 signer) to settle on-chain. On success returns the receipt plus your seat token and contact package. The seat token is required for post_task and get_replies.
| Name | Type | Req | Description |
|---|---|---|---|
| itemId | string | yes | – |
| paymentSignature | string | yes | base64 x402 PAYMENT-SIGNATURE header value |
No output schema declared.
No examples provided.
How do I install the A Human For Hire MCP server?
A Human For Hire runs locally as an npm package, launched with npx -y ahfh-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · ahfh-mcp
claude mcp add com-ahumanforhire-ahfh -- npx -y ahfh-mcp
What is the A Human For Hire MCP server?
A Human For Hire is an MCP server listed in the public MCP registry as com.ahumanforhire/ahfh. Hire a real human over x402: pay USDC on Solana, post tasks to a human desk, poll replies as JSON. This page covers its npm package (ahfh-mcp).
Is the A Human For Hire MCP server safe to use?
A Human For Hire scores 61 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 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 A Human For Hire MCP server expose?
A Human For Hire exposes 6 tools: get_catalog, quote_item, build_payment, submit_payment, post_task, get_replies. Their descriptions and schemas cost roughly 384 tokens of context every time the server is loaded.
Is the A Human For Hire MCP server still maintained?
A Human For Hire is still listed as active in the MCP registry. We last reached this channel on 21 November 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 A Human For Hire MCP server under?
A Human For Hire declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the A Human For Hire MCP server?
VerifyMCP ran 15 checks on A Human For Hire, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about A Human For Hire: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.