nohumans.directory
REMOTE · API.NOHUMANS.DIRECTORY · SCANNED OCT 14
We buy from x402 endpoints with real USDC and publish delivery outcomes. Check before you spend.
Available components
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. How we score → Why this is hard to score →
Endpoint Security77
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability62
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1002 tokens (~250/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the nohumans.directory MCP server?
nohumans.directory is a hosted endpoint at https://api.nohumans.directory/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.
remote · api.nohumans.directory
claude mcp add --transport http directory-nohumans-registry 'https://api.nohumans.directory/mcp'
{
"mcpServers": {
"directory-nohumans-registry": {
"url": "https://api.nohumans.directory/mcp"
}
}
} {
"servers": {
"directory-nohumans-registry": {
"type": "http",
"url": "https://api.nohumans.directory/mcp"
}
}
} [mcp_servers.directory-nohumans-registry] url = "https://api.nohumans.directory/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"directory-nohumans-registry": {
"type": "remote",
"url": "https://api.nohumans.directory/mcp",
"enabled": true
}
}
} openclaw mcp add directory-nohumans-registry --url 'https://api.nohumans.directory/mcp' --transport streamable-http
mcp_servers:
directory-nohumans-registry:
url: "https://api.nohumans.directory/mcp" {
"McpServers": {
"directory-nohumans-registry": {
"Transport": "http",
"Url": "https://api.nohumans.directory/mcp"
}
}
} assistant mcp add directory-nohumans-registry -t streamable-http -u 'https://api.nohumans.directory/mcp'
{
"mcpServers": {
"directory-nohumans-registry": {
"type": "http",
"url": "https://api.nohumans.directory/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 14 Oct 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “find_paid_service” rewrote its description, which is the text the model reads security
- Tool “get_service_details” rewrote its description, which is the text the model reads security
- Tool “resolve_endpoint” rewrote its description, which is the text the model reads security
- Tool “what_agents_are_asking_for” rewrote its description, which is the text the model reads security
- Schema quality: 301 → 250 ▲ functional
- “get_service_details” reworded the description of “id” cosmetic
- 12 Oct 26 +3
- Injection markers: fail → pass ▲ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “find_paid_service” rewrote its description, which is the text the model reads security
- Tool “get_service_details” rewrote its description, which is the text the model reads security
- Tool “resolve_endpoint” rewrote its description, which is the text the model reads security
- Tool “what_agents_are_asking_for” rewrote its description, which is the text the model reads security
- Schema quality: 894 → 301 ▲ functional
- Schema quality: excellent → good functional
- “find_paid_service” added an optional parameter “detail” cosmetic
- “find_paid_service” added an optional parameter “mpp_method” cosmetic
- “find_paid_service” added an optional parameter “protocol” cosmetic
- “find_paid_service” reworded the description of “category” cosmetic
- “find_paid_service” reworded the description of “limit” cosmetic
- “find_paid_service” reworded the description of “max_price” cosmetic
- “find_paid_service” reworded the description of “min_score” cosmetic
- “find_paid_service” reworded the description of “query” cosmetic
- “resolve_endpoint” reworded the description of “url” cosmetic
- “what_agents_are_asking_for” reworded the description of “limit” cosmetic
- “what_agents_are_asking_for” reworded the description of “offset” cosmetic
- 29 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “what_agents_are_asking_for” rewrote its description, which is the text the model reads security
- “what_agents_are_asking_for” added an optional parameter “limit” cosmetic
- “what_agents_are_asking_for” added an optional parameter “offset” cosmetic
- 28 Sept 26 +2
- 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
- Tool “get_service_details” rewrote its description, which is the text the model reads security
- Tool “what_agents_are_asking_for” rewrote its description, which is the text the model reads security
- 26 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- 25 Sept 26 −3
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
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 14 Oct 2026 · Probed https://api.nohumans.directory/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=nohumans.directory | CN=WE1,O=Google Trust Services,C=US | 15 Sept 2026 | 14 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | bb439d7199bfbe8c0e6977386698eecf |
| SANs: nohumans.directory, api.nohumans.directory, *.api.nohumans.directory | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of api.nohumans.directory. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| directory. | present | 59725 | 8 | Verified |
| nohumans.directory. | present | 2371 | 13 | Verified |
| api.nohumans.directory. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.nohumans.directory/mcp | Verified | 200 | |
| http (plaintext) | http://api.nohumans.directory/mcp | HTTPS enforced | 301 | https://api.nohumans.directory/mcp |
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 →
find_paid_service Find a paid service ~296
Search paid x402 APIs and datasets by need. Ranked: verified first, then probe score, then price. Each result carries what you choose on: status, score (0..1), evidence_tier, paid_verified (we bought it with real USDC and it delivered), has_sample (a cheap preview exists), price. Relevance comes from the query text; a specific need in plain words matches best. Zero results means nothing listed matches. Results are dated evidence, not guarantees. Returns a summary per listing; detail='full' returns every field. Free, read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Optional filter: one of the most-populated categories. Omit if none fits; query text still finds long-tail ones. |
| detail | string | – | summary (default) or full: every field per listing. |
| limit | integer | – | Max results (default 10). |
| max_price | number | – | Max price per call. Omit for no cap. |
| min_score | number | – | Min probe score, 0..1 (0.8 = reliably passing). |
| mpp_method | string | – | Only listings offering this MPP method, e.g. stripe, tempo, evm. |
| protocol | string | – | Only listings offering this payment protocol. Omit for any. |
| query | string | – | What you need, specifically: data, freshness, format, constraint. Drives relevance. |
| Name | Type | Req | Description |
|---|---|---|---|
| category_expanded | boolean|null | – | – |
| count | integer | yes | – |
| detail | string | – | – |
| results | array | yes | – |
No examples provided.
get_service_details Get a paid service's full record ~136
Full record for one listing id: request and response schemas, sample_query, observed 402 terms (network, payTo, scheme, x402 version), reputation detail, and paid_verification (our latest real USDC purchase, with its settlement tx where proven). Useful before paying: it shows the exact request shape and current reliability. Every timestamp has an _iso twin; on-chain counts describe the seller's wallet, usually shared by several listings, not this endpoint. Free, read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Listing id: the id field of a search result, e.g. f094faea-d9d. |
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| chains | array | – | – |
| description | string | – | – |
| distinct_payers | integer|null | – | – |
| endpoint_url | string | yes | – |
| evidence_note | string|null | – | – |
| evidence_tier | string | – | – |
| has_sample | boolean | – | – |
| id | string | yes | – |
| kind | string | – | – |
| kind_notes | object|null | – | – |
| last_probed_at | integer|null | – | – |
| mpp_methods | array|null | – | – |
| name | string | yes | – |
| obs_network | string|null | – | – |
| obs_pay_to | string|null | – | – |
| obs_scheme | string|null | – | – |
| observed_network | string|null | – | – |
| onchain_daily | array|null | – | – |
| onchain_payto_shared_listings | integer|null | – | – |
| onchain_scope | string|null | – | – |
| onchain_shape | object|null | – | – |
| onchain_unique_payers_30d | integer|null | – | – |
| onchain_wallet | object | – | – |
| p50_latency_ms | number|null | – | – |
| p95_latency_ms | integer|null | – | – |
| p99_latency_ms | integer|null | – | – |
| paid_verification | object | – | – |
| paid_verification_latest | object|null | – | – |
| paid_verified | boolean | – | – |
| paid_verified_at | integer|null | – | – |
| paid_verified_at_iso | string|null | – | – |
| payment_protocols | array | – | – |
| payto_distinct_recent | integer|null | – | – |
| payto_note | string|null | – | – |
| payto_sentinel | boolean | – | – |
| payto_unstable | boolean | – | – |
| price_amount | number | yes | – |
| price_currency | string | – | – |
| probe_count | integer|null | – | – |
| probes_failed | integer|null | – | – |
| probes_passed | integer|null | – | – |
| report_count | integer|null | – | – |
| report_score | number|null | – | – |
| request_schema | object|null | – | – |
| response_mime | string|null | – | – |
| response_schema | object|null | – | – |
| sample_query | string|null | – | – |
| score | number|null | – | – |
| status | string | yes | – |
| status_changed_at | integer|null | – | – |
| transport | string|null | – | – |
| verdict_age_seconds | integer|null | – | – |
| x402_version | integer|null | – | – |
No examples provided.
resolve_endpoint Check an endpoint URL before paying ~94
Check an endpoint URL you already hold before paying it. Returns match 'active' with the listing's full record, 'delisted' (listed here, later removed), or 'unknown' (never checked here; absence is not a verdict either way). The record is dated evidence, not a safety rating. Free, read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The endpoint URL as you hold it, including any query string. |
| Name | Type | Req | Description |
|---|---|---|---|
| detail | object|null | – | – |
| match | string | yes | – |
| note | string|null | – | – |
No examples provided.
what_agents_are_asking_for What agents are asking for ~194
What agents searched this directory for, for deciding which x402 service to build or list. Terms ranked by how many distinct days they were asked, each with catalogue_top: the listings our own search already returns for it. A term being asked does not mean nothing serves it. The window ends a week behind live while the paid tier is on sale (a day when it is not; delay_hours and window_ends_at in the response say which); test traffic, sellers searching their own listings and identifying terms are excluded; floor: a term appears once at least 1 distinct non-seller client IP asked it. Client counts are IP ceilings, never buyer counts. Paged: limit (default 25), offset, next_offset. Free, read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Terms per page, in rank order. |
| offset | integer | – | Where to start; each reply gives next_offset. |
| Name | Type | Req | Description |
|---|---|---|---|
| delay_hours | integer | yes | – |
| distinct_client_ips | integer | – | – |
| k_anonymity_floor | integer | – | – |
| k_anonymity_unit | string | – | – |
| note | string | – | – |
| page | object | – | – |
| read_first | array | – | – |
| scripted_rotation | array | – | – |
| side_lists | object | – | – |
| terms_total | integer | – | – |
| top_category_filters | array | – | – |
| top_needs | array | yes | – |
| total_queries | integer | yes | – |
| window_days | integer | yes | – |
| window_ends_at | integer | – | – |
No examples provided.
What is the nohumans.directory MCP server?
nohumans.directory is an MCP server listed in the public MCP registry as directory.nohumans/registry. We buy from x402 endpoints with real USDC and publish delivery outcomes. Check before you spend. This page covers its hosted endpoint (https://api.nohumans.directory/mcp).
Is the nohumans.directory MCP server safe to use?
nohumans.directory scores 84 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 nohumans.directory MCP server expose?
nohumans.directory exposes 4 tools: find_paid_service, get_service_details, resolve_endpoint, what_agents_are_asking_for. Their descriptions and schemas cost roughly 720 tokens of context every time the server is loaded.
Does the nohumans.directory MCP server require authentication?
No. We connected to nohumans.directory without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the nohumans.directory MCP server still maintained?
nohumans.directory is still listed as active in the MCP registry. We last reached this channel on 14 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.