MCP tool reference · #362 of 563 by publishers
recommend
Exposed by 11 servers from 10 publishers, read from the live servers by the Serverdex check; most of them sit in AI & Agents; 18.2% of them take a count parameter; the most-starred is Inspo (1.1k stars).
recommend(…)Parameters
share = % of the 11 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| count | string | number | boolean | 18.2% | 0% | How many picks, 1 to 5 (default 3) |
| limit | integer | 18.2% | 0% | Number of recommendations (default 5) |
| maxPrice | number | 18.2% | 0% | Only listings at or under this price in USD |
| need | string | 18.2% | 100% | The task in plain words, 3 to 300 characters |
| networks | string | 18.2% | 0% | Comma-separated networks: base, polygon, arbitrum, solana |
| query | string | 18.2% | 100% | The goal, business or situation in the customer's words. |
| task | string | 18.2% | 50% | Task phrase or category |
| use_case | string | 18.2% | 100% | What the user needs, e.g. "database", "web scraping", "slack integration", "vector search" |
| actions | array | 9.1% | 100% | List of options to compare (minimum 2) |
| brief | string | 9.1% | 100% | The user's design brief in plain English. E.g. 'calm meditation app', 'dark dev-tool that helps teams ship faster'. |
| budget | number | 9.1% | 0% | Budget in USD, when the customer gave one. |
| category | string | 9.1% | 100% | — |
Source: the input schema each server returns for recommend, aggregated over the 11 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with recommend
11 of 11 · 10 publishers · 11 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes recommend |
|---|---|---|---|---|---|---|
| 1 | Insponutlope · Developer Tools | nutlope | Developer Tools | 1.1k | yes | Orchestrator - start here for a brief. One call returns a macrostructure pick, 5 real exemplars, matching reference components (source via get_reference_jsx), a palette suggestion, and an `evidence` packet measuring the genre's paper band / display class / accent hue. Pass a macrostructure to skip the pick step. No LLM call. |
| 2 | Rendezvouschrisroge · AI & Agents | chrisroge | AI & Agents | 2 | yes | Submit your sealed, immutable recommendation for a rendezvous. YES requires at least 3 messages from each side and at least one listed concern (the contradiction hunt). You never see the counterparty's recommendation. Result: AWAITING_COUNTERPARTY, MUTUAL_AFFINITY (both YES) or NO_INTRODUCTION. |
| 3 | Agent Data Tools: Utilitiesnutshell2000 · Data & Analytics | nutshell2000 | Data & Analytics | 1 | yes | Describe a task in plain words and compare up to five paid APIs for it across the whole Coinbase Bazaar: each pick with the exact URL to call, method, price in USD, networks, 30-day payers and calls, last paid date and the evidence behind the order. Our own listings are marked, never boosted. No matching tool means no charge. Use when an agent must choose which API to call before paying one. Examp |
| 4 | Agent Data Tools: Full list (every tool as its own definition)nutshell2000 · Documents & Knowledge | nutshell2000 | Documents & Knowledge | 1 | yes | Describe a task in plain words and compare up to five paid APIs for it across the whole Coinbase Bazaar: each pick with the exact URL to call, method, price in USD, networks, 30-day payers and calls, last paid date and the evidence behind the order. Our own listings are marked, never boosted. No matching tool means no charge. Use when an agent must choose which API to call before paying one. Examp |
| 5 | Algenta MCP Serverthyn-ai · Other | thyn-ai | Other | 1 | yes | Compare multiple named actions/options and get a ranked recommendation. Use when you need to choose between two or more alternatives with uncertainty. Synchronous deterministic compute; nothing is persisted and no separate rate limit applies. Returns recommended_action, confidence, rationale, and the ranked action list with expected_value and score per action. |
| 6 | 4OVER440ver4 · Other | 40ver4 | Other | — | yes | Recommends 4OVER4 print products for a business, event or goal (a new bakery, a trade show, a wedding); use it when someone describes a print need but names no product. For a named product use show_products; for several printed pieces use marketing_kit. Requires the need in the customer's words. Returns the best products or collection with slugs and From prices, or a help answer. Customer phrases: |
| 7 | VendorIndexandy-chak · Health & Science | andy-chak | Health & Science | — | yes | Recommend the top vendors for a specific category + use case, with the reasoning (which dimensions drove the pick). Best when an agent needs a single answer to 'what should I use for X?'. |
| 8 | Agent Dailygregpunch · AI & Agents | gregpunch | AI & Agents | — | yes | Before calling an external API, ask which provider to use. Give a task phrase or category (e.g. 'send email', 'web search', 'llm', 'scrape a page', 'vector db', 'speech to text', 'payments', 'geocode'). Returns the top healthy pick plus 1-2 fallbacks ranked by live status, vendor status, 7-day uptime and latency, with a reason and data freshness. |
| 9 | OpenNodesopennodes-io · AI & Agents | opennodes-io | AI & Agents | — | yes | Recommend the best AI node + model for a task, with an enforceable cost estimate and human-readable reasons. Use this first when you know the task but not the model. Pass `task` (sent to this registry, which extracts features and discards the text) or `features` already extracted on your side with extractFeatures from @opennodes/core, which keeps the prompt private. Returns ranked candidates with |
| 10 | AgentRanksuperlowburn · AI & Agents | superlowburn | AI & Agents | — | yes | Get quality-ranked recommendations for a use case. Returns the top tools/skills sorted by AgentRank score. Use this when a user needs a tool for a specific purpose (e.g. "I need a database MCP server", "what's good for web scraping?"). |
| 11 | Tuki — Travel Marketplace (Chile y Latinoamérica)tatanmas · E-commerce & Retail | tatanmas | E-commerce & Retail | — | yes | Natural-language recommendation. Pass the user query verbatim (e.g. "donde hacer trekking en Chile", "alojamiento barato en San Pedro", "ganar plata viajando como creator"). Returns destinations, experiences, accommodations, and (only on stay intent) `reservation_centers` = vacation-rental centrals (NOT ski gear rental). Supports optional price_min/price_max in CLP. Routing rule: use THIS tool for |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.