MCP server for advanced web search using Tavily
Nothing to run from here
Not Human Search is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
14
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Search the agentic web. 4,100+ sites, 11 tools incl. check_url + verify_mcp for probe-before-use.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http not-human-search-mcp https://nothumansearch.ai/mcp
# 2 — ask your agent for something these tools do
# search_agents, get_site_details, get_stats and 11 more
Not Human Search costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NAAll 1 server
nothumansearch.ai1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http not-human-search-mcp https://nothumansearch.ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
14 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search for websites, APIs, and services that AI agents can actually use. Results are ranked by agentic readiness score (0-100) based on llms.txt, OpenAPI specs, ai-plugin.json, structured APIs, and MCP server availability. Use this to discover payment APIs, job boards, data sources, or any web service your agent needs to call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as |
| has_api | boolean | no | Only return sites with a documented structured API |
| has_llms_txt | boolean | no | Only return sites that publish an llms.txt file (LLM-first site summary) |
| has_mcp | boolean | no | Only return sites that expose an MCP server |
| has_openapi | boolean | no | Only return sites with a published OpenAPI / Swagger spec |
| limit | integer | no | Max results (default 10, max 20) |
| min_score | integer | no | Minimum agentic readiness score 0-100 (higher = more agent-ready) |
| query | string | no | Keyword query (e.g. 'payment API', 'weather data', 'job board') |
Get the full agentic readiness report for a specific domain: score, category, all 7 signal checks (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org), plus any cached llms.txt content and OpenAPI summary. When an exact search_id newly records this organic-result selection, the response also carries an optional record_action_interest opportunity for this
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain to look up (e.g. 'stripe.com'). Do not include scheme or path. |
| search_id | string | no | Optional receipt returned by a receipt-bearing NHS discovery tool. If this domain was returned, NHS records a detail selection and may return a separate, noncommercial action-interest opportunity requ |
Current Not Human Search index stats: total sites, average agentic score, top category, sites added in the last 7 days, count of sites exposing an MCP server, and count scoring a perfect 100/100.
No parameter schema on file.
Submit a URL for NHS to crawl and score. Use when you discover an agent-first tool, API, or service that isn't in the index yet. NHS will fetch the site, check its 7 agentic signals (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org), compute a score, and add it to the index. The site becomes searchable within a few seconds if the crawl succeeds.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Full URL to submit (include scheme, e.g. 'https://example.com'). Homepage is best — NHS will check /.well-known/ paths, /robots.txt, /llms.txt, etc. relative to the site root. |
On-demand agentic-readiness check for any URL. Runs the NHS 7-signal crawler live (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org) and returns a score 0-100 with per-signal breakdown. Use before calling an unfamiliar API to confirm it's agent-usable. Re-runnable without the submissions-table side-effect of submit_site — ideal for verify-before-use wo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Full URL or bare domain (e.g. 'stripe.com' or 'https://stripe.com'). Homepage works best — NHS probes the /.well-known/ paths, /robots.txt, /llms.txt relative to the site root. |
Actively probe any URL to check if it is a live, spec-compliant MCP server. Sends a JSON-RPC tools/list request and verifies a valid response. Use this before depending on a third-party MCP endpoint — manifests and documentation can claim MCP support without actually serving it. Returns {verified: true/false, endpoint, note}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Full URL of the MCP endpoint to probe (include scheme, e.g. 'https://example.com/mcp'). |
Register an email to get alerted when the indicated domain's agentic readiness score drops. Useful for agents tracking a dependency's agent-readiness health — e.g. an agent that relies on stripe.com's MCP surface wants to know the moment it regresses. Returns an unsubscribe URL. Multiple monitors per email allowed, one per domain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain to monitor (no scheme, e.g. 'stripe.com') |
| string | yes | Email address to receive alert |
List all categories in the Not Human Search index with site counts and average agentic scores. Use this to understand what kinds of agent-ready services exist before searching — counts are live, so the distribution shifts as the index grows.
No parameter schema on file.
Get the highest-scored agent-ready sites in the index, optionally filtered by category. Organic order is always readiness-score order. A supported category creates a query-free discovery receipt that can support separately disclosed provider-funded actions and explicit action interest; unfiltered browsing stays free and does not enter the Stage 1 demand cohort.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as |
| limit | integer | no | Max results (default 10, max 50) |
List agent-ready sites newly added to the Not Human Search index, sorted newest first. A supported category creates a query-free discovery receipt that can support separately disclosed provider-funded actions and explicit action interest; unfiltered catalog watching stays free and does not enter the Stage 1 demand cohort.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as |
| days | integer | no | Look back window in days (default 7, max 90) |
| limit | integer | no | Max results (default 10, max 50) |
List sites in the index that expose a live MCP server, ranked by agentic readiness. The result set carries a query-free discovery receipt and any eligible provider-funded actions appear separately without changing organic order. Pairs naturally with verify_mcp for a probe-before-use workflow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as |
| limit | integer | no | Max results (default 10, max 20) |
| query | string | no | Optional keyword to narrow results (e.g. 'payments', 'jobs', 'weather') |
Record the caller's attestation that its human or company principal currently wants one controlled next step with a site returned organically by a receipt-bearing NHS discovery tool. This creates a private Stage 1 demand receipt that expires with the source discovery receipt, no later than 30 days after it. It does not contact the provider, create an action ticket or charge, change rank or score,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action_type | string | yes | The one next step the principal currently wants. |
| caller_attests_principal_interest | boolean | yes | Caller attests current principal interest under the exact published v1 wording; this is not authority to contact the provider. |
| confirmation_version | string | yes | https://nothumansearch.ai/privacy#action-interest-v1 |
| domain | string | yes | Bare domain that appeared in the referenced organic results; no scheme or path. |
| search_id | string | yes | Committed privacy-safe receipt returned by a receipt-bearing NHS discovery tool. |
Prepare a signed action ticket for a separately disclosed provider-funded offer returned beside a receipt-bearing NHS discovery result. This step never returns the provider action URL or records a handoff. It requires the discovery receipt and the caller's explicit ticket-authorization attestation. It accepts controlled constraints only—no name, email, contact detail, raw prompt, agent identity, o
| Parameter | Type | Required | Notes |
|---|---|---|---|
| budget_band | string | no | — |
| consent_version | string | yes | https://nothumansearch.ai/privacy#consent-v1 |
| demand_topic | string | yes | One controlled topic already present on the referenced search receipt. |
| offer_id | string | yes | Provider-funded offer ID returned separately beside a receipt-bearing NHS discovery result. |
| principal_consent | boolean | yes | Caller attests that the human/company principal authorized this ticket preparation under the published versioned wording. |
| region_code | string | no | Optional uppercase ISO country or country-region code. |
| requirement_flags | array | no | — |
| search_id | string | yes | Discovery receipt proving the provider appeared organically. |
| urgency | string | no | — |
Present the exact ticket bearer returned by prepare_provider_action. NHS records one privacy-safe handoff receipt, then returns the attributed provider action URL. Optionally and separately, the principal may authorize the exact DNS-verified provider to resolve only the ticket's controlled topic, region, USD budget band, urgency, and allowlisted requirement flags. Declining that optional disclosur
| Parameter | Type | Required | Notes |
|---|---|---|---|
| attribution_token | string | yes | Exact bearer returned by prepare_provider_action; NHS does not store the raw token. |
| controlled_intent_disclosure_consent_version | string | no | https://nothumansearch.ai/privacy#controlled-intent-disclosure-consent-v1; required only when the optional disclosure consent is true. |
| handoff_consent_version | string | yes | https://nothumansearch.ai/privacy#handoff-consent-v1 |
| principal_controlled_intent_disclosure_consent | boolean | no | Optional separate authorization for the exact DNS-verified provider to resolve the bounded controlled-intent bundle after handoff. False or omitted does not block handoff. |
| principal_handoff_consent | boolean | yes | Caller attests the principal authorized the separate observed handoff under the exact published wording. |
| ticket_id | string | yes | Action ticket ID returned by prepare_provider_action. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Not Human Search or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.7.1.
1.7.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Not Human Search can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.