The Yantrix MCP server provides 30+ AI-powered tools across research, memory, language, legal, security, business intelligence, and more — accessed via USDC micropayments.
Research & Fact Verification
Verify claims against real-time sources with confidence scores, perform deep multi-source verification, or batch-verify up to 10 claims simultaneously
Memory Management
Write, read, and semantically search persistent agent memories that survive across sessions (with optional TTL and tags)
Indic Language Processing
Transliterate between 9+ Indic scripts, analyze sentiment/emotions in Indian languages (including Hinglish), detect code-switching, and perform India-specific named entity recognition
Legal & Contract Analysis
Full contract risk scans (risk score, red flags, missing protections) and individual clause analysis with suggested revisions
Security & Compliance
Generate STRIDE threat models and check architectures against PCI-DSS, HIPAA, GDPR, ISO27001, SOC2, and NIST frameworks
Market Intelligence
Score AI/tech trends with hype-vs-reality analysis, compare 2–5 trends head-to-head, and run full competitor scans (pricing, features, funding, strengths/weaknesses)
Content & Education
Generate exams (up to 20 questions, variable difficulty) and rewrite content in styles like Paul Graham, Economist, McKinsey, or Hemingway
India-Specific Data
Look up Indian company profiles (MCA21/GST), retrieve GST registration and filing intelligence by GSTIN, and find bank IFSC codes with branch details
Sales Intelligence
Analyze sales calls for sentiment, objections, commitments, and deal health; extract structured CRM-ready data from transcripts
Utility Tools
Validate phone numbers globally, detect/convert timezones, and find working-hour overlaps across 2–5 locations
Reasoning
Generate the strongest arguments for and against any claim, and detect logical fallacies with severity ratings and corrections
API Infrastructure
Check and consume rate limit quotas, and track API usage events for analytics
Dynamic MCP server for the Yantrix API portfolio. One install gives any MCP-compatible AI agent access to 30+ tools across research, memory, language, legal, security, intelligence, and more.
Unlike static MCP packages, @yantrixai/mcp fetches its tool list from registry.yantrix.ai on startup. When new APIs are added to the Yantrix portfolio, they appear automatically on your next MCP host restart — no package update needed.
Related MCP server: @melis-ai/x402-tools-mcp
npm install -g @yantrixai/mcpOr use directly with npx:
npx @yantrixai/mcpAdd to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"yantrix": {
"command": "npx",
"args": ["@yantrixai/mcp"],
"env": {
"X_PAYMENT_HEADER": "<your-x402-payment-proof>",
"DEV_MODE": "false"
}
}
}
}{
"mcpServers": {
"yantrix": {
"command": "npx",
"args": ["@yantrixai/mcp"],
"env": {
"DEV_MODE": "true"
}
}
}
}Variable | Description | Default |
| x402 payment proof for USDC micropayments | — |
| Skip payment validation (local testing only) |
|
| Custom registry URL |
|
Tools are loaded dynamically from the registry. Current categories:
Category | Tools |
| verify_claim, deep_verify_claim, batch_verify |
| write_memory, read_memory, search_memory |
| transliterate, indic_sentiment, detect_code_switching, indic_ner |
| scan_contract, scan_clause |
| model_threats, check_compliance |
| score_trend, compare_trends, scan_competitor |
| generate_exam |
| rewrite_in_style |
| company_lookup, gst_intelligence, lookup_ifsc |
| analyze_call, extract_crm_data |
| validate_phone, detect_timezone, convert_timezone, find_timezone_overlap |
| check_quota, consume_quota, track_api_event |
| argue_claim, detect_fallacies |
All tools use x402 micropayments in USDC on Base Mainnet.
Costs range from $0.0001 (event tracking) to $0.025 (sales call analysis).
To get a payment header, visit x402.org or use the x402 client SDK.
1. npx @yantrixai/mcp starts
2. Fetches https://registry.yantrix.ai/mcp-registry.json
3. Registers all tools dynamically
4. MCP host calls any tool
5. @yantrixai/mcp routes call to correct Yantrix API
6. Response returned to agentThe registry is cached for 5 minutes. New tools appear on next restart.
No npm republish needed. Just update main.py in the mcp-registry service:
# Add to TOOLS list in mcp-registry/main.py
{
"name": "new_tool_name",
"service": "newapi",
"endpoint": "https://newapi.yantrix.ai/endpoint",
"method": "POST",
"description": "What this tool does.",
"input_schema": {...},
"cost_usdc": "0.005",
"category": "category",
}Deploy the registry → all users get the new tool on next restart.
Registry: https://registry.yantrix.ai
Docs: https://yantrix.ai
x402: https://x402.org
Full sales call analysis — sentiment, objections, commitments, next steps, deal health score. Cost: $0.025 USDC. Service: callsight.
Inputs: transcript (required), call_type, product.
Get the strongest arguments both for and against any claim. Cost: $0.005 USDC. Service: debateclub.
Inputs: claim (required), context, domain.
Batch verify up to 10 claims at once. Cost: $0.020 USDC. Service: groundtruth.
Inputs: claims (required).
Check architecture against compliance framework (PCI-DSS, HIPAA, GDPR, ISO27001, SOC2, NIST). Cost: $0.015 USDC. Service: threatmodel.
Inputs: architecture (required), framework (required).
Check if an agent has rate limit quota available before making an API call. Cost: $0.0005 USDC. Service: ratelord.
Inputs: agent_id (required), api_name (required), calls_needed.
Lookup Indian company profile and regulatory info from MCA21, GST portal. Cost: $0.003 USDC. Service: papertrail.
Inputs: company_name (required), cin, gstin.
Compare 2-5 AI trends head to head with rankings and recommendations. Cost: $0.010 USDC. Service: signal.
Inputs: topics (required).
Consume rate limit quota after making an API call. Cost: $0.0005 USDC. Service: ratelord.
Inputs: agent_id (required), api_name (required), calls_used.
Convert a datetime from one timezone to another. Cost: $0.001 USDC. Service: timezonedetective.
Inputs: datetime (required), from_tz (required), to_tz (required).
Deep multi-source verification with contradictions and domain analysis. Cost: $0.005 USDC. Service: groundtruth.
Inputs: claim (required), domain, require_sources.
Detect Hinglish/Tanglish code-switching with language mix ratios. Cost: $0.003 USDC. Service: indic.
Inputs: text (required), primary_language.
Detect logical fallacies in an argument with severity and correction. Cost: $0.003 USDC. Service: debateclub.
Inputs: argument (required).
Detect timezone from any input — city, country, address, IP hint, phone prefix. Cost: $0.001 USDC. Service: timezonedetective.
Inputs: input (required).
Extract CRM-ready structured data from a call transcript. Cost: $0.010 USDC. Service: callsight.
Inputs: transcript (required).
Find working hours overlap between 2-5 locations for scheduling. Cost: $0.002 USDC. Service: timezonedetective.
Inputs: timezones (required), work_hours_start, work_hours_end.
Generate a full exam with up to 20 questions on any topic. Cost: $0.020 USDC. Service: examforge.
Inputs: topic (required), num_questions, difficulty, question_types.
Get GST registration details and filing intelligence for a GSTIN. Cost: $0.005 USDC. Service: papertrail.
Inputs: gstin (required).
Named entity recognition tuned for Indian names, places, organisations, festivals. Cost: $0.005 USDC. Service: indic.
Inputs: text (required), language (required).
Sentiment analysis with emotion detection in Indian languages including Hinglish. Cost: $0.003 USDC. Service: indic.
Inputs: text (required), language (required).
Lookup Indian bank IFSC code. Returns bank, branch, address, IMPS/RTGS/NEFT/UPI support. Cost: $0.001 USDC. Service: ifsclookup.
Inputs: ifsc (required).
Generate a STRIDE threat model for any system architecture. Cost: $0.010 USDC. Service: threatmodel.
Inputs: architecture (required), system_type, tech_stack, data_sensitivity.
Read a persistent memory by exact key. Cost: $0.001 USDC. Service: memex.
Inputs: agent_id (required), key (required).
Rewrite content in a target writing style (paul_graham, economist, mckinsey_report, hemingway, etc.) Cost: $0.005 USDC. Service: voiceprint.
Inputs: content (required), target_style (required), preserve_facts.
Analyse a single contract clause for risk and get a suggested revision. Cost: $0.005 USDC. Service: contractscan.
Inputs: clause_text (required), jurisdiction.
Full competitor scan — pricing, features, messaging, funding, strengths, weaknesses. Cost: $0.010 USDC. Service: compwatch.
Inputs: company (required), url, focus.
Scan a contract for risk. Returns risk score 0-100, risky clauses, red flags, missing protections. Cost: $0.010 USDC. Service: contractscan.
Inputs: contract_text (required), jurisdiction, contract_type.
Score an AI trend topic. Returns momentum (RISING/STABLE/DECLINING/EMERGING), maturity, hype vs reality. Cost: $0.005 USDC. Service: signal.
Inputs: topic (required), context.
Semantic search across all agent memories. Returns most relevant matches. Cost: $0.005 USDC. Service: memex.
Inputs: agent_id (required), query (required), top_k.
Track an API usage event for analytics. Cost: $0.0001 USDC. Service: heatmap.
Inputs: api_key (required), endpoint (required), status_code, latency_ms.
Convert text between any two Indic scripts or Latin (9 scripts supported). Cost: $0.001 USDC. Service: indic.
Inputs: text (required), source_script (required), target_script (required).
Validate any phone number globally. Returns E.164 format, country, carrier, line type. Cost: $0.001 USDC. Service: phonevalidator.
Inputs: phone (required), country_hint.
Verify a factual claim against real-time web sources. Returns verdict (TRUE/FALSE/UNCERTAIN/OUTDATED/DISPUTED), confidence 0-1, and source. Cost: $0.002 USDC. Service: groundtruth.
Inputs: claim (required), context.
Write or update a persistent memory for an agent. Survives across sessions. Cost: $0.001 USDC. Service: memex.
Inputs: agent_id (required), key (required), value (required), tags, +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 33 tools
Most tools have distinct purposes, but there is some overlap in the verification domain (verify_claim, deep_verify_claim, batch_verify) and timezone tools (detect_timezone, convert_timezone, find_timezone_overlap) that could cause mild confusion. The descriptions help differentiate them, but an agent might need to carefully choose between similar tools.
Tool names follow a consistent verb_noun pattern throughout (e.g., analyze_call, check_compliance, generate_exam). There are no deviations in naming conventions, making it easy to predict and understand tool functions from their names.
With 33 tools, the count is too high for a single server, indicating a lack of focus. The tools span diverse domains like sales analysis, compliance, timezone handling, and memory management, which should likely be split into multiple specialized servers for better coherence.
Within each sub-domain, the tools provide good coverage (e.g., memory tools include read, write, and search; verification tools offer basic, deep, and batch options). However, some gaps exist, such as no delete operation for memories or limited update capabilities in other areas, but agents can generally work around these.
15 paid AI agent primitives via x402 (USDC on Base). Pay-per-call MCP server.
Production-grade MCP gateway delivering 8 real-time AI tools with instant x402 micropayments settled in USDC on Base Mainnet or SPL-USDC on Solana. Features Basescan contract auditing, wallet analytics, headless browser scraping, and pre-scraped oracle data feeds.
Production-grade MCP gateway delivering 8 real-time AI tools with instant x402 micropayments settled in USDC on Base Mainnet or SPL-USDC on Solana. Features Basescan contract auditing, wallet analytics, headless browser scraping, and pre-scraped oracle data feeds.
Pay-per-call x402 MCP for AI agents: 35 tools, USDC on Base, from $0.001/call, no API keys.