BotFriendly
Directory of APIs, merchants, and tools AI agents can actually use.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"botfriendly": {
"url": "https://www.botfriendly.xyz/api/mcp"
}
}
}Remote endpoints
https://www.botfriendly.xyz/api/mcpstreamable-httphttps://mcp.botfriendly.xyzstreamable-httpWhat it can do
Tool inventory
Tools (7)
🟢search_services(query, category, has_mcp, no_human, accepts_mpp, ...)
Search the BotFriendly directory for bot-friendly services, APIs, and tools that AI agents can use. Filter by category, payment/commerce protocol support (x402, MPP, L402, AP2, TAP, Agent Pay, ACE, ACP, UCP, ACTP, ICC), auth method, and more. Results may start with up to 3 promoted listings (paid ads) pinned to the top — site-wide ads on unfiltered searches, category ads on category searches — clearly marked with promoted:true and ad:true. Use promoted=false to exclude ads.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keyword search (Postgres websearch semantics: multiple words are ANDed, so a single distinctive keyword like 'scraping' matches more than a phrase like 'web scraping')"
},
"category": {
"type": "string",
"enum": [
"think",
"see",
"hear-speak",
"create",
"remember",
"search",
"browse",
"communicate",
"execute",
"pay",
"shop",
"markets",
"platforms",
"identify",
"monitor",
"other",
"locate",
"book",
"hire",
"sign",
"trade",
"bet",
"connect",
"automate"
],
"description": "Category id: think (Models), see (Vision), hear-speak (Speech), create (Media), remember (Memory), search (Search), browse (Browsers), communicate (Messaging), execute (Compute), pay (Payments), shop (Merchants), markets (Markets), platforms (Platforms), identify (Identity), monitor (Observability), other (Other). Merged categories also accept their old slugs (trade, bet, connect, automate, locate, book, sign, hire)."
},
"has_mcp": {
"type": "boolean",
"description": "Only services with MCP servers"
},
"no_human": {
"type": "boolean",
"description": "Only services an agent can start using with no human setting up a key: probe-backed — its own (non-documentation) MCP server lists its tools to an unauthenticated client and the service needs no key (no auth, or a wallet), or one of its interfaces answers HTTP 402 to be paid per request"
},
"accepts_mpp": {
"type": "boolean",
"description": "Only services accepting MPP payments"
},
"accepts_x402": {
"type": "boolean",
"description": "Only services accepting x402 payments"
},
"protocol": {
"type": "array",
"items": {
"type": "string",
"enum": [
"x402",
"mpp",
"l402",
"ap2",
"tap",
"agent-pay",
"ace",
"acp",
"ucp",
"actp",
"icc"
]
},
"description": "Only services supporting ALL of these agent payment/commerce protocols. x402 (x402, Coinbase, x402 Foundation); mpp (Machine Payments Protocol, Stripe, Tempo); l402 (L402, Lightning Labs); ap2 (Agent Payments Protocol, Google); tap (Trusted Agent Protocol, Visa); agent-pay (Mastercard Agent Pay, Mastercard); ace (Agentic Commerce Experiences, American Express); acp (Agentic Commerce Protocol, OpenAI, Stripe); ucp (Universal Commerce Protocol, Google, Shopify); actp (Agentic Commerce Trust Protocol, Alibaba, Ant International); icc (Intelligent Commerce Connect, Visa)"
},
"min_score": {
"type": "number",
"minimum": 1,
"maximum": 5,
"description": "Minimum bot-friendly score (1-5)"
},
"auth_method": {
"type": "string",
"enum": [
"api-key",
"m2m-oauth",
"bot-token",
"wallet",
"x402-none",
"none"
],
"description": "Filter by auth method"
},
"sort": {
"type": "string",
"enum": [
"score",
"votes",
"name",
"newest"
],
"description": "Sort order (default: score)"
},
"promoted": {
"type": "boolean",
"description": "Filter by promoted status: true for promoted only, false for organic only"
},
"page": {
"type": "number",
"description": "Page number (default 1)"
}
}
}🟢get_service(slug)
Get full details for a specific service by its slug, including all protocol support, URLs, auth method, billing, and metadata.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Service slug (e.g. browserbase, anthropic-claude-api, firecrawl)"
}
},
"required": [
"slug"
]
}🟢list_categories
List every BotFriendly category with its id (the search_services category value), human label, aliases (older slugs still accepted), description and service count.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_featured
Get site-wide featured/promoted services (max 3). These are paid placements clearly marked as ads.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_protocol_stats
Get every protocol on botfriendly.xyz/protocols with adoption stats: how agents call a service and prove who sent them (MCP, OpenAPI, A2A, XAA) and the agent payment, authorization, and commerce protocols (x402, mpp, l402, ap2, tap, agent-pay, ace, acp, ucp, actp, icc). Each entry carries its sponsor, layer, spec URL, and count — how many listed services support it, or null for protocols that aren't a listing attribute (A2A, XAA).
Input Schema
{
"type": "object",
"properties": {}
}🟡check_site(url, format)
Score how bot-friendly a website is (0-100). Fetches the site the way an agent would — no JavaScript, no cookies — and checks access (reachability, HTTPS, robots.txt, AI crawlers allowed, real 404s), content without JavaScript (H1, 500+ chars of raw text, metadata, JSON-LD), and machine discovery (llms.txt, sitemap, OpenAPI spec or ai-plugin.json), with evidence and fix advice per check. Set format to 'prompt' to instead get a ready-to-paste coding-agent prompt that fixes every failed finding. Rate limited to 6 checks per minute per caller; each check takes a few seconds.
Input Schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Site to check (scheme optional, https assumed; public sites only)"
},
"format": {
"type": "string",
"enum": [
"json",
"prompt"
],
"description": "json (default) returns the full scored report; prompt returns a markdown prompt for a coding agent covering every failed or partial finding"
}
},
"required": [
"url"
]
}🟡submit_service(name, url, category, description, auth_method, ...)
Submit a service to the BotFriendly directory. There is no review queue: each interface URL must be on the service's own domain, or linked from the service's own site, and is fetched during the call; the listing publishes immediately if its MCP server, OpenAPI spec or API completes a handshake — one of has_mcp_server, has_openapi_spec or has_api is required; llms.txt, skill files and feeds only add badges. The url must be the product, not an article (/blog/, /news/ and similar are rejected), and a domain can add at most 2 listings a day and 3 in total. Every listing needs an icon — pass icon_url, or leave it out and the service's own site is checked for one.
Input Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Service name"
},
"url": {
"type": "string",
"description": "Service URL"
},
"category": {
"type": "string",
"enum": [
"think",
"see",
"hear-speak",
"create",
"remember",
"search",
"browse",
"communicate",
"execute",
"pay",
"shop",
"markets",
"platforms",
"identify",
"monitor",
"other",
"locate",
"book",
"hire",
"sign",
"trade",
"bet",
"connect",
"automate"
],
"description": "Category id (see list_categories)"
},
"description": {
"type": "string",
"description": "Short description (max 120 chars)"
},
"auth_method": {
"type": "string",
"description": "Auth method"
},
"has_mcp_server": {
"type": "boolean"
},
"mcp_server_url": {
"type": "string",
"description": "Required when has_mcp_server is true. On the service's own domain, or linked from its site."
},
"has_openapi_spec": {
"type": "boolean"
},
"openapi_spec_url": {
"type": "string",
"description": "Required when has_openapi_spec is true. On the service's own domain, or linked from its site."
},
"has_api": {
"type": "boolean"
},
"api_url": {
"type": "string",
"description": "Required when has_api is true: the API's base URL (api.example.com, or a path under /api or /v1). It must answer in JSON. On the service's own domain, or linked from its site."
},
"icon_url": {
"type": "string",
"description": "Link to the service's icon (PNG, JPEG, SVG or WebP, under 1MB). Fetched and re-hosted, downscaled to 512px. Omit it and the service's site is checked for one."
},
"icon_base64": {
"type": "string",
"description": "Alternative to icon_url: the image inline, as a data: URI or bare base64."
},
"accepts_mpp": {
"type": "boolean"
},
"accepts_x402": {
"type": "boolean"
},
"billing_model": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"contact_email": {
"type": "string",
"description": "Contact email for verification"
}
},
"required": [
"name",
"url",
"category",
"description"
]
}Community
Evidence