CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Wayforth

wayforthofficial/wayforth
117 toolsSTDIOregistry active
Summary

Gives Claude access to 4,974+ APIs through a single search and execute interface. You describe what you need in natural language (translation, web search, image generation) and it returns ranked services with reliability scores, then executes them without you managing keys or credentials. Seventeen managed services like Groq, DeepL, Serper, and Stability AI work out of the box with credit-based billing. Also supports BYOK for any indexed API and handles payment via credits, USDC, or HTTP 402 micropayments. Useful when you want agents to call external APIs without building authentication pipelines for each one or when you need reliable routing across competing providers based on uptime signals.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Tools

Public tool metadata for what this MCP can expose to an agent.

17 tools
wayforth_runThe Wayforth runtime. One call does everything: searches for the best API, picks the top-ranked service by WayforthRank v2, maps your input to the service's params, and executes it — returning the result directly. Use this instead of wayforth_search + wayforth_execute when you...5 params

The Wayforth runtime. One call does everything: searches for the best API, picks the top-ranked service by WayforthRank v2, maps your input to the service's params, and executes it — returning the result directly. Use this instead of wayforth_search + wayforth_execute when you...

Parameters* required
railstring
Payment rail. 'managed' uses Wayforth's keys (recommended, zero setup). 'byok' uses your stored key.default: managed
inputobject
The actual content to process. Example: {'text': 'Hello world'} for translation, {'city': 'Tokyo'} for weather, {'query': 'AI news'} for search, {'symbol': 'AAPL'} for stocks
intentstring
Natural language description of what you need. Example: 'translate this text to Spanish', 'get weather in Tokyo', 'search the web for AI news', 'get stock price for AAPL'
agent_idstring
Optional: tag this call with your agent's name for per-agent analytics in your dashboard. Example: 'translation-agent', 'my-chatbot'. Max 64 chars, alphanumeric/hyphens/underscores.default:
categorystring
Optional: filter by service category. Options: translation, inference, data, image, audio, communication
wayforth_executeExecute any API service instantly. 15 managed services run with zero API keys — Wayforth holds the credentials. The fastest way to add any API capability to your agent. Optional: include agent_id='my-agent-name' to tag this call for per-agent analytics in your dashboard at way...4 params

Execute any API service instantly. 15 managed services run with zero API keys — Wayforth holds the credentials. The fastest way to add any API capability to your agent. Optional: include agent_id='my-agent-name' to tag this call for per-agent analytics in your dashboard at way...

Parameters* required
paramsobject
Service-specific parameters as a JSON object (e.g. {'text': 'Hello', 'target_lang': 'ES'} for DeepL)
agent_idstring
Optional: tag this call with your agent's name for per-agent analytics. Example: 'translation-agent'. Max 64 chars, alphanumeric/hyphens/underscores.default:
key_sourcestring
Key source: 'managed' (use Wayforth's key, default) or 'byok' (use your stored key)default: managed
service_slugstring
Service to call: groq, deepl, openweather, newsapi, serper, resend, assemblyai, stability, tavily, jina, alphavantage, elevenlabs — or any custom slug for BYOK
wayforth_searchSearch 300+ verified APIs ranked by WayforthRank — real agent payment signals, not ads. Use this when you don't know which service to execute.4 params

Search 300+ verified APIs ranked by WayforthRank — real agent payment signals, not ads. Use this when you don't know which service to execute.

Parameters* required
limitinteger
Number of results to return (1–20)default: 5
querystring
Natural language description of the API service you need (e.g. 'translate text to Spanish', 'generate images')
categorystring
Optional category filter: inference, data, translation, image, code, audio, embeddings
tier_mininteger
Minimum coverage tier: 0=all, 1=tested, 2=verified (default), 3=premiumdefault: 2
wayforth_listBrowse the Wayforth service catalog.3 params

Browse the Wayforth service catalog.

Parameters* required
limitinteger
Number of services to return (1–100)default: 10
categorystring
Filter by category: inference, data, translation, image, code, audio, embeddings
tier_mininteger
Minimum coverage tier: 0=all, 1=tested, 2=verified (default), 3=premiumdefault: 2
wayforth_statsGet current Wayforth catalog statistics.

Get current Wayforth catalog statistics.

No parameter schema in public metadata yet.

wayforth_statusReturn API health and catalog statistics.

Return API health and catalog statistics.

No parameter schema in public metadata yet.

wayforth_queryStructured service discovery using WayforthQL v2. More precise than wayforth_search — supports price caps, protocol filters, x402-only, provider filtering, and explicit sort order. Use when you need deterministic filtering rather than pure semantic ranking.11 params

Structured service discovery using WayforthQL v2. More precise than wayforth_search — supports price caps, protocol filters, x402-only, provider filtering, and explicit sort order. Use when you need deterministic filtering rather than pure semantic ranking.

Parameters* required
limitinteger
Number of results to return (1–50)default: 5
querystring
Natural language query describing the API you need (e.g. 'fast cheap translation', 'image generation under $0.01')
offsetinteger
Pagination offset — skip this many resultsdefault: 0
sort_bystring
Sort order: 'wri' (WayforthRank score, default), 'price' (cheapest first), 'tier' (highest tier first)default: wri
categorystring
Filter by category: inference, translation, data, search, audio, image, etc.
protocolstring
Payment protocol filter (e.g. 'x402' for HTTP 402 native services)
providerstring
Filter by provider name substring (e.g. 'openai', 'google')
tier_mininteger
Minimum coverage tier: 0=all, 1=tested, 2=verified (default), 3=premiumdefault: 2
price_maxnumber
Maximum price per API call in USD (e.g. 0.001 for $0.001/call)
x402_onlyboolean
When true, return only x402-native servicesdefault: false
verified_onlyboolean
When true, return only tier-2+ verified servicesdefault: false
wayforth_compareCompare 2-5 API services side by side. Returns WRI scores, response times, costs, signal counts and a plain-English recommendation. Use this before committing to a service.2 params

Compare 2-5 API services side by side. Returns WRI scores, response times, costs, signal counts and a plain-English recommendation. Use this before committing to a service.

Parameters* required
querystring
Optional: describe your use case to get a relevance score per service. Example: 'fast inference for my chatbot'default:
slugsstring
Comma-separated service slugs to compare. Example: 'groq,together,perplexity'. Compare 2-5 services at a time.
wayforth_similarFind services similar to or commonly used alongside a given service. Returns co-usage patterns from real agent behavior.1 params

Find services similar to or commonly used alongside a given service. Returns co-usage patterns from real agent behavior.

Parameters* required
service_idstring
Service ID or wayforth:// identifier to find co-used services for
wayforth_payPay for a service through Wayforth. Two payment tracks: track='card' (default — no crypto needed): - Deducts from your Wayforth credit balance - Stripe Treasury processes the payment to the service - Get credits at wayforth.io/dashboard → Billing → Card Track track='crypto' (n...4 params

Pay for a service through Wayforth. Two payment tracks: track='card' (default — no crypto needed): - Deducts from your Wayforth credit balance - Stripe Treasury processes the payment to the service - Get credits at wayforth.io/dashboard → Billing → Card Track track='crypto' (n...

Parameters* required
trackstring
Payment track: 'card' (Stripe Treasury credits) or 'crypto' (Base USDC, non-custodial)default: card
query_idstring
Optional query ID from wayforth_search for conversion tracking
amount_usdnumber
Amount to pay in USD (e.g. 0.001)
service_idstring
Service ID from wayforth_search results (e.g. 'wayforth://deepl/...')
wayforth_keysManage BYOK (Bring Your Own Key) stored service keys. Store encrypted API keys for any service and call them via wayforth_execute with key_source='byok'. Keys are encrypted at rest with AES-128 and never returned in plaintext.4 params

Manage BYOK (Bring Your Own Key) stored service keys. Store encrypted API keys for any service and call them via wayforth_execute with key_source='byok'. Keys are encrypted at rest with AES-128 and never returned in plaintext.

Parameters* required
actionstring
Action to perform: 'list' (show stored keys), 'add' (store a new key), or 'delete' (remove a key)
service_namestring
Human-readable label for the service (optional for 'add', defaults to service_slug)
service_slugstring
Service identifier slug (required for 'add'/'delete'), e.g. 'openai', 'anthropic', 'stripe'
api_key_valuestring
The API key to encrypt and store (required for action='add')
wayforth_rememberSave a service to agent memory for quick access later.4 params

Save a service to agent memory for quick access later.

Parameters* required
notestring
Optional note about why you saved this servicedefault:
agent_idstring
Agent identifier (wallet address or session ID) for cross-session persistencedefault:
service_idstring
Service ID or wayforth:// identifier from search results
service_namestring
Human-readable name of the service to save
wayforth_recallRecall services previously saved to memory.2 params

Recall services previously saved to memory.

Parameters* required
querystring
Optional filter to search saved services by name or notedefault:
agent_idstring
Agent identifier used when saving — required for cross-session memory retrievaldefault:
wayforth_identityGet or create your agent identity on Wayforth. Returns your trust score, reputation tier, and usage history.1 params

Get or create your agent identity on Wayforth. Returns your trust score, reputation tier, and usage history.

Parameters* required
agent_idstring
Your unique agent identifier — wallet address or any stable session ID
wayforth_check_agent_identityLook up an agent's identity and reputation on Wayforth. Returns tier (unknown/emerging/established/trusted/elite), trust score (0-100), call history, and cumulative spend. Agents build reputation automatically through x402 pay-per-call usage. No signup required. Tiers unlock h...1 params

Look up an agent's identity and reputation on Wayforth. Returns tier (unknown/emerging/established/trusted/elite), trust score (0-100), call history, and cumulative spend. Agents build reputation automatically through x402 pay-per-call usage. No signup required. Tiers unlock h...

Parameters* required
wallet_addressstring
Base wallet address to look up (0x...). Returns tier, trust score, and activity history.
wayforth_set_wri_alertRegister a webhook to be notified when any API service crosses a WayforthRank WRI score threshold. The webhook fires once per service per 24 hours when the score crosses upward through the threshold. Payload is HMAC-SHA256 signed with X-Wayforth-Signature for verification. Use...4 params

Register a webhook to be notified when any API service crosses a WayforthRank WRI score threshold. The webhook fires once per service per 24 hours when the score crosses upward through the threshold. Payload is HMAC-SHA256 signed with X-Wayforth-Signature for verification. Use...

Parameters* required
categorystring
Optional: only alert for services in this category. Options: translation, inference, search, image, audio, finance, weather, email, data. Leave unset to watch all categories.
notify_urlstring
HTTPS webhook URL to POST to when a service crosses the WRI threshold.
min_signalsinteger
Minimum signal count before alerting. Prevents noise from newly-added services with very few data points. Default: 5.default: 5
threshold_scorenumber
WRI score threshold (50.0 – 99.9). Alert fires when any matching service crosses this score upward.
wayforth_quickstartGet the Wayforth developer quickstart guide. Returns step-by-step instructions for using Wayforth in an agent.

Get the Wayforth developer quickstart guide. Returns step-by-step instructions for using Wayforth in an agent.

No parameter schema in public metadata yet.

Wayforth — The API Runtime for AI Agents

One tool call. Any API. No setup.

Version License Tests


What It Is

Wayforth is the API runtime for AI agents — a single integration that gives any agent access to ~5,000 indexed APIs, ranked by real usage signals and executable with credits or crypto. Agents search, select, and pay for API services in one call without managing keys, credentials, or billing integrations. Built for developers who want their agents to reach the full surface area of the internet without building the infrastructure themselves.


Quick Start

Step 1 — Install the MCP server

uvx wayforth-mcp

Add to Claude Code permanently:

claude mcp add wayforth -- uvx wayforth-mcp

Step 2 — Get an API key

Sign up at wayforth.io/signup and copy your key from the dashboard.

Step 3 — Set your key

export WAYFORTH_API_KEY=wf_live_...

Step 4 — Run your first call

# Search — natural language, no keys needed
wayforth_search("translate text to Spanish")
# → DeepL   WRI: 82  Tier 2 ✓  managed
# → LibreTranslate  WRI: 71  Tier 2 ✓

# Execute — managed services, zero setup
wayforth_execute("deepl", {"text": "Hello", "target_lang": "ES"})
# → {"translations": [{"text": "Hola"}]}

Python SDK:

pip install wayforth-sdk
from wayforth import WayforthClient
client = WayforthClient(api_key="wf_live_...")
results = client.search("real-time stock data")

Full API reference: gateway.wayforth.io/guide/


Managed Services

16 live — managed services with zero API key setup. Wayforth holds the credentials — you call the tool.

ServiceCategoryCredits/call
GroqLLM inference3
Together AILLM inference4
MistralLLM inference4
GeminiLLM inference3
DeepLTranslation20
SerperWeb search3
TavilyWeb search10
BraveWeb search6
Perplexity (in queue)Web search10
OpenWeatherWeather data2
NewsAPINews search3
Alpha VantageFinancial data4
Jina AIContent extraction4
FirecrawlWeb scraping6
AssemblyAISpeech-to-text25
Stability AIImage generation86 (Core) · 150 (Ultra)
ElevenLabs (in queue)Text-to-speech200
ResendEmail3

For Providers

Wayforth routes agent traffic to providers at scale.

  • Discovery — providers are indexed and ranked by WayforthRank, a scoring system driven by real agent payment signals. The more agents pay for a service, the higher it ranks.
  • x402-native — providers supporting the HTTP 402 micropayment protocol receive direct USDC settlement per call, non-custodial.
  • Managed — providers integrated as managed services receive monthly ACH payouts based on routed call volume.
  • Provider Dashboard — analytics portal showing calls, WRI scores, competitor data, estimated earnings, and agent identities. Intelligence and Premium tiers.

Provider plans:

PlanMonthlyAnnual
ObserverFreeFree
Intelligence$99/mo$85/mo · $1,020/yr (save $168)
Premium$299/mo$250/mo · $3,000/yr (save $588)

Register your API: wayforth.io/providers


Catalog

MetricCount
APIs indexed~5,000
Tier 2 verified3,400+
x402-native services277
Categories19

WayforthRank scores every service 0–100 based on uptime history, probe frequency, payment conversion rate, and real agent usage patterns. Higher score = more trustworthy for agent workloads.

Coverage tiers:

  • Tier 0 — submitted, not yet probed
  • Tier 1 — probed, endpoint confirmed reachable
  • Tier 2 — automated reliability testing every 6 hours, score maintained
  • Tier 3 — managed integration, Wayforth holds the key

Payment Rails

Three ways to pay for API calls through Wayforth:

RailMethodSettlement
CardStripe (fiat)Buy credits, spend as API calls
USDCBase blockchainDirect crypto deposits (+5% bonus credits)
x402HTTP 402 protocolPer-call micropayments

x402 is the open HTTP-402 micropayment standard — agents pay per call with no subscription or balance required. Non-custodial escrow pays providers on confirmed execution.


MCP Tools

18 tools available via the Wayforth MCP server:

ToolDescription
wayforth_searchSearch ~5,000 APIs by intent — returns ranked results with WRI scores
wayforth_queryStructured discovery with WayforthQL — filter by tier, latency, region, price, payment rail
wayforth_runIntent-based routing with automatic reliability failover — returns result + failover status
wayforth_executeDirect execution of a managed service; auto-fails over to best alternative if degraded
wayforth_reliabilityReal-time reliability check — WRI score, tier, 7d uptime, last probe, failover candidate
wayforth_payPay for a service call via card credits or USDC on Base
wayforth_listList available services with category and tier filters
wayforth_statusLive API health check and real-time service counts
wayforth_statsCatalog statistics — total services, tier breakdown
wayforth_keysStore your own API keys encrypted at rest (BYOK)
wayforth_rememberStore a persistent memory entry for agent context
wayforth_recallRetrieve stored memories by query
wayforth_compareSide-by-side comparison of two services by slug
wayforth_similarFind services co-used alongside a given service
wayforth_identityGet or create your agent identity — trust score, reputation tier, usage history
wayforth_check_agent_identityLook up another agent's identity by wallet address
wayforth_set_wri_alertSet a webhook to fire when a service crosses a WRI score threshold
wayforth_quickstartGet started guide — returned as a formatted string

WayforthQL

Structured query language for precise API discovery. Filter by tier, latency, region, price, and payment rail.

POST https://gateway.wayforth.io/query
{
  "query": "fast inference for coding agents",
  "tier_min": 2,
  "sort_by": "wri",
  "latency_max": 500,
  "region": "us",
  "protocol": "x402",
  "price_max": 0.001,
  "limit": 5
}

Response fields:

FieldTypeDescription
wayforth_idstringUnique service ID: wayforth://<slug>
namestringService name
wrifloatWayforthRank score, 0–100
coverage_tierintVerification tier (0–3)
pricing_usdcfloatPrice per request in USD
payment_protocolstringOne of: wayforth | x402 | any

protocol filter accepts: wayforth | x402 | any

x402 is the open HTTP-402 payment standard for per-call micropayments.

Full spec: gateway.wayforth.io/wayforthql-spec


Development Status

v0.8.13 — current release

  • Security hardening: SSRF validation on URL-fetching adapters, webhook DNS-rebind IP pinning, account-deletion grace hardening, DB-level email-canonical uniqueness, USDC tx_hash race fix, admin-gate rate limiting
  • /system/health auth-gated — unauthenticated callers receive {status, version} only
  • PostgreSQL password rotated; crawler switched to private network
  • 190+ tests passing, zero failures
  • 99.97% uptime
  • Health monitoring — all 16 managed services probed and tracked every 6h; never-succeeded services excluded from the /system/status degraded aggregate
  • Credits system — per-service credit costs enforced (Groq 3 cr, DeepL 20 cr, Stability AI 86 cr, etc.). Monthly quotas in credits: Free 100 · Starter 6,000 · Builder 21,000 · Pro 72,000 · Growth 240,000
  • Pioneer Program — indefinite enrollment, daily credit drip by tier, 7-day rejoin cooldown. Search responses include pioneer_routing, pioneer_routed_to_boosted, and signal_weight fields for opted-in developers
  • LLM gateway — POST /v1/chat/completions OpenAI-compatible endpoint with Groq → Together AI → Mistral failover and streaming
  • Tier 1 input caps — DeepL 2,000 chars, AssemblyAI ~10 min, Stability AI 1 image per call
  • API key encryption versioning — versioned Fernet keys, zero-downtime rotation
  • Provider email verification — required before service submission
  • Admin audit log — append-only, trigger-enforced
  • BYOK — bring your own API key for any indexed service (AES-256-GCM encrypted at rest)
  • MFA — TOTP-based authentication available

Plan quotas (credits/month):

PlanCredits/monthPrice
Free100Free
Starter6,000$12/mo
Builder21,000$29/mo
Pro72,000$99/mo
Growth240,000$299/mo
Enterprise1,000,000Custom

Pioneer Program: Opt in at POST /account/pioneer/join. Enrolled developers receive daily bonus credits (Growth: 1,200 cr/day) when they route searches through verified boosted services. Enrollment is indefinite — no 30-day cap. Opting out sets a 7-day rejoin cooldown. Field cooldown_days_remaining in the status response shows days remaining on the cooldown (null when enrolled).

Balance API response:

{
  "plan": "growth",
  "credits_remaining": 189375,
  "credits_included": 240000,
  "calls_remaining": 189375,
  "forecast": {
    "daily_avg_credits": 1919.44,
    "days_remaining_at_current_rate": 98
  }
}

calls_remaining is kept as a backward-compatible alias for credits_remaining.

Pricing: wayforth.io/pricing


Links

  • Quickstart: wayforth.io/quickstart
  • API Reference: gateway.wayforth.io/guide/
  • Platform Overview: wayforth.io/Wayforth_Whitepaper_v6.10.pdf
  • Dashboard: wayforth.io/dashboard
  • For Providers: wayforth.io/providers
  • PyPI (MCP): pypi.org/project/wayforth-mcp
  • PyPI (SDK): pypi.org/project/wayforth-sdk
  • Contact: wayforth.io/contact

License

Business Source License 1.1 (BSL 1.1) — converts to Apache 2.0 on April 25, 2030.

© 2026 Wayforth Technologies Inc.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
Search & Web CrawlingFinance & Commerce
Registryactive
Packagewayforth-mcp
TransportSTDIO
UpdatedApr 24, 2026
View on GitHub

Related Search & Web Crawling MCP Servers

View all →
Google Search

com.mcparmory/google-search

Scrape Google search results with SERP data, ads, and knowledge panels
25
Brave Search

io.github.pipeworx-io/brave-search

Brave Search MCP — independent web index (no Google/Bing dependency)
Serper Search and Scrape

marcopesani/mcp-server-serper

Serper MCP Server supporting search and webpage scraping
154
Brave Search Mcp Server

brave/brave-search-mcp-server

Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
1.2k
Google Search Console

com.mcparmory/google-search-console

Query search analytics, manage sitemaps, and inspect site URLs and status
25
Google Search Console

acamolese/google-search-console-mcp

Google Search Console MCP server: SEO audits, performance queries, URL inspection, indexing checks.
3