Local-first knowledge graph for token-efficient code review through MCP and CLI
Nothing to run from here
API Hub 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.
93/100
tool-list score
4
downloads a day
remote
at its publisher
74
downloads in 30d
What it does
216 x402 tools + free cross-bazaar search; USDC on Base, no API key
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http api-hub-mcp https://api.gadgethumans.com/mcp
# 2 — ask your agent for something these tools do
# token_verdict, prediction_odds, prediction_scan and 46 more
API Hub costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GAAll 3 servers
gadgethumans3 servers
2 categories
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 api-hub-mcp https://api.gadgethumans.com/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
49 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.
Pre-trade risk verdict on a Base token, $0.01. Give a Base contract address and get: honeypot/transfer-simulation result, buy and sell tax, mint and owner privileges, verified-source status, blacklist and pausable flags, liquidity and holder concentration, scored 0-100 with the explicit red flags named. Aggregated live from honeypot.is, DexScreener, GoPlus and GeckoTerminal. Run it before buying,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Base mainnet token contract address (0x + 40 hex chars) |
Prediction-market odds and implied probability, $0.01. Ask for an event or topic and get the live Polymarket markets that match: each outcome's implied probability and decimal odds, best bid/ask and spread, book liquidity, 24h and 1wk volume, days to resolution, and a deterministic 0-100 edge/attention score with the concrete flags named (wide_spread, thin_liquidity, resolving_within_24h, sharp_mo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Event or topic, in the venue's own wording, e.g. 'Fed rate decision', 'Bitcoin above 150k', 'Super Bowl' |
| limit | integer | no | Max markets (1-10, default 5) |
Live prediction-market board scan, $0.25. Returns the whole active board ranked by 24h volume: every market's implied probabilities, spreads, book depth, 24h/1wk volume, days to resolution and 0-100 edge scores, plus a summary of where the board is least certain - the live close calls (near 50/50), the widest spreads, the sharpest 24h moves, and total board volume. Use to screen prediction markets
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | Markets returned (1-50, default 20) |
| min_volume | number | no | Only markets with at least this much 24h volume (USD) |
Search Amazon products and get affiliate links. Find products across 40+ categories. Returns buying guides and Amazon search links with your affiliate tag.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Product search query |
| category | string | no | Optional category filter |
VAULT: Persistent agent memory — the KEY tool. Store and retrieve data across sessions. Agents are stateless — use this to remember facts, preferences, task state, API keys, conversation summaries, and configuration between runs. Data persists indefinitely in KV storage. Once stored, data is yours forever — only accessible through this server. Call with action='get' to read, action='set' to write,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | Memory key (e.g. 'conversation_summary', 'user_preferences', 'task_state', 'api_keys') |
| value | string | no | JSON value to store (required for action='set') |
| action | string | no | get (default), set, delete, search (find by keyword in values), list (show all keys) |
VAULT: View your agent profile — see your agent ID, total stored data items, usage stats, and subscription status. Shows what data you have stored in our vault.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| detail | string | no | summary (default) or all_keys |
VAULT SEARCH: Search across ALL your stored memories by keyword. Finds matches in both memory keys and values. Returns up to 10 results. Unlike agent_memory where you need to know the exact key, this lets you discover what you've stored.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search term to find in your stored memories |
VAULT LIST: List all memory keys in your vault. Shows every piece of data you've stored, organized by category. Use this to see everything you've saved across sessions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Optional filter (e.g. 'task', 'config', 'prefs') |
Current weather for any city
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | yes | City name (e.g. London) |
7-day weather forecast for any city
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | yes | City name |
Get real-time cryptocurrency prices from Binance
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | no | e.g. bitcoin, ethereum, solana (comma-separated) |
Convert between currencies using real-time rates
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from_ | string | yes | Source currency code e.g. USD |
| to | string | yes | Target currency code e.g. EUR |
| amount | number | yes | Amount to convert |
Forward geocode an address to coordinates
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Address or place name |
Look up DNS records for any domain
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | e.g. example.com |
Get geolocation data for any IP address
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ip_address | string | no | IP address (optional, defaults to requester IP) |
Get current air quality data for any city (AQI, PM2.5, PM10)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | yes | City name |
Search the web using DuckDuckGo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
Parse RSS/Atom feed to JSON
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Check SSL certificate for a domain
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | — |
Decode a JWT token into header, payload, signature
| Parameter | Type | Required | Notes |
|---|---|---|---|
| token | string | yes | — |
Check password strength with score and crack time estimate
| Parameter | Type | Required | Notes |
|---|---|---|---|
| password | string | yes | — |
Detect the language of provided text with confidence score
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
Generate QR code as base64 PNG image
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Text or URL to encode |
| size | integer | no | Size in pixels (default: 300) |
Generate secure random passwords
| Parameter | Type | Required | Notes |
|---|---|---|---|
| length | integer | no | Password length (default: 16) |
| count | integer | no | Number of passwords (default: 1) |
| numbers | boolean | no | — |
| symbols | boolean | no | — |
Generate UUID v4 identifiers
| Parameter | Type | Required | Notes |
|---|---|---|---|
| count | integer | no | Number of UUIDs (default: 1) |
Generate SEO-optimized title, meta description, keywords, and slug
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | no | Topic or keyword |
Generate cryptographic hash of input text (SHA-256, SHA-512, MD5)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| algorithm | string | no | SHA-256 (default), SHA-384, SHA-512, SHA-1 |
Encode or decode text using Base64
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| mode | string | no | encode (default) or decode |
Evaluate a mathematical expression safely
| Parameter | Type | Required | Notes |
|---|---|---|---|
| expression | string | yes | e.g. 3.14 * 2^10 / (5+3) |
Count words, characters, sentences, paragraphs with stats
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
Convert Unix timestamp to date or vice versa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| value | string | no | Unix timestamp or date string |
| format | string | no | iso (default), unix, rfc2822 |
Calculate Flesch-Kincaid readability score and grade level
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
Analyze the tone, emotion, and sentiment of text
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
Generate 5 compelling headlines from content
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
Summarize long text into concise key points
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
Compare two texts and return line-by-line differences
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text_a | string | yes | First text (before) |
| text_b | string | yes | Second text (after) |
Proofread text for grammar, spelling, punctuation, and style issues
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
Calculate monthly mortgage payments and total interest
| Parameter | Type | Required | Notes |
|---|---|---|---|
| principal | number | yes | Loan amount |
| rate | number | yes | Annual interest rate e.g. 5.5 |
| years | integer | yes | Loan term in years |
Calculate loan payments, total interest, and full schedule
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | number | yes | — |
| rate | number | yes | Annual interest rate e.g. 5.5 |
| term_months | integer | yes | — |
Calculate compound interest growth over time
| Parameter | Type | Required | Notes |
|---|---|---|---|
| principal | number | yes | — |
| rate | number | yes | Annual rate e.g. 5.0 |
| years | number | yes | — |
| contributions | number | no | Optional monthly contribution (default: 0) |
Calculate percentages — find what % X is of Y
| Parameter | Type | Required | Notes |
|---|---|---|---|
| value | number | yes | — |
| total | number | yes | — |
Calculate tip amount and split bill between people
| Parameter | Type | Required | Notes |
|---|---|---|---|
| bill | number | yes | Total bill |
| percent | number | no | Tip percentage (default: 15) |
| split | integer | no | Number of people (default: 1) |
Convert between measurement units (temperature, length, weight)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| value | number | yes | — |
| from_unit | string | yes | e.g. c, m, kg |
| to_unit | string | yes | e.g. f, ft, lb |
Convert timestamps between any timezones
| Parameter | Type | Required | Notes |
|---|---|---|---|
| timestamp | string | no | ISO date string (default: now) |
| from_tz | string | no | Source timezone e.g. UTC |
| to_tz | string | no | Target timezone e.g. EST |
Convert numbers between bases (hex, decimal, octal, binary)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| num | string | yes | — |
| from_base | integer | no | Source base (default: 10) |
| to_base | integer | no | Target base (default: 16) |
Calculate BMI from weight and height
| Parameter | Type | Required | Notes |
|---|---|---|---|
| weight | number | yes | Weight in kg |
| height | number | yes | Height in cm |
Calculate Basal Metabolic Rate using Mifflin-St Jeor equation
| Parameter | Type | Required | Notes |
|---|---|---|---|
| weight | number | yes | Weight in kg |
| height | number | yes | Height in cm |
| age | integer | yes | — |
| sex | string | no | — |
Estimate calories burned during physical activities
| Parameter | Type | Required | Notes |
|---|---|---|---|
| activity | string | yes | e.g. running, walking, cycling |
| weight | number | yes | Weight in kg |
| duration | integer | yes | Duration in minutes |
UNIVERSAL PROXY: Call any API Hub tool by name. Access 122 REST tools through this single MCP endpoint. Tools include: email verification, color converter, QR decode, HTML entities, regex test, MIME types, HTTP codes, country list, currency list, public holidays, paper sizes, chemical elements, JSON tools, password strength, named entities, keyword density, text complexity, macros, ideal weight, b
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tool_name | string | yes | REST tool to call. Examples: verify_email, convert_color, lookup_html_entity, test_regex, lookup_mime_type, lookup_http_code, list_countries, list_currencies, get_public_holidays, paper_size_reference |
| params | string | no | JSON string of parameters for the tool, e.g. '{"color":"#ff0000"}' |
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 API Hub 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: —
ATool-list grade · score 93 / 100
Release 1.0.15 · scanned 3 Nov 2026
Graded from the tools this server lists, not from its source code.
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.
Threat score100
Client score93
Findings0 threat · 2 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestf0fa5061ed013eedf0107a2e725f1c7456f51058d6549ff35ac56366311a6ab5
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| token_verdict | no tags | |
| prediction_odds | no tags | |
| prediction_scan | no tags | |
| affiliate_search | no tags | |
| agent_memory | no tags | |
| agent_profile | no tags | |
| memory_search | no tags | |
| memory_list | no tags | |
| get_weather | no tags | |
| get_forecast | no tags | |
| get_crypto_prices | no tags | |
| convert_currency | no tags | |
| geocode | no tags | |
| dns_lookup | no tags | |
| geolocate_ip | no tags | |
| get_air_quality | no tags | |
| search_web | untrusted-input | untrusted-input: keyword "search web" |
| parse_rss_feed | untrusted-input | untrusted-input: keyword "rss" |
| check_ssl_certificate | no tags | |
| decode_jwt | no tags | |
| check_password_strength | no tags | |
| detect_language | no tags | |
| generate_qr_code | no tags | |
| generate_password | no tags | |
| generate_uuid | no tags | |
| generate_seo_metadata | no tags | |
| hash_text | no tags | |
| encode_base64 | no tags | |
| evaluate_math | no tags | |
| word_count | no tags | |
| convert_timestamp | no tags | |
| analyze_readability | no tags | |
| analyze_sentiment | no tags | |
| generate_headlines | no tags | |
| summarize_text | no tags | |
| text_diff | no tags | |
| proofread_text | no tags | |
| mortgage_calculator | no tags | |
| loan_calculator | no tags | |
| compound_interest | no tags | |
| percentage_calculator | no tags | |
| tip_calculator | no tags | |
| convert_units | no tags | |
| convert_timezone | no tags | |
| convert_number_base | no tags | |
| calculate_bmi | no tags | |
| bmr_calculator | no tags | |
| calorie_burn | no tags | |
| call_api | external-sink | external-sink: keyword "call_api" |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestf0fa5061ed013eed
Scanned2026-11-03
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
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 1.0.15.
3.0.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
2.6.0
24 Jun 2026
No release note was published with this version.
1.0.15
undated
latest- The version the registry reports for this listing; it was 1.0.12.
1.0.12
undated
- The version the registry reports for this listing; it was 1.0.11.
1.0.11
undated
- The version the registry reports for this listing; it was 2.6.0.
—
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 API Hub 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.