Amalgix
About
Mixture-of-Agents document intelligence engine — 100% recall across 10 languages, x402 micropayment (USDC on Base/Solana), 6 tools from $0.08/call
Details
- Author
- Amalgix-io
- Downloads
- 341
- Categories
- Other, AI, Productivity, Automation
Jump to
- Cross‑model evidence pipeline: extraction then verification with different models.
- Source‑grounded claims with evidence, source reference, confidence, and verification status.
- Financial Filing Intelligence for SEC filings (10‑K, 10‑Q, 20‑F).
- Contract Risk Intelligence for clauses, obligations, liability, and missing terms.
- x402 pay‑per‑call settlement in USDC on Base and Solana.
- Up to 3.8× cheaper than two‑pass calls to frontier models.
- No API keys required for MCP; optional wallet login for dashboard attribution.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AmalgixCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add Amalgix to any Streamable HTTP MCP‑compatible client by configuring the server URL https://amalgix.io/mcp with transport streamable-http. For REST, call https://amalgix.io/api/v1/health to verify service availability; paid endpoints require x402 payment headers. Use the free estimate_cost tool to preview pricing before any paid call.
analyze_document
Analyze a document using Crucible™ Evidence Engine. Returns source-grounded findings with evidence, confidence, verification status, and routing metadata. Use specialized financial/contract tools when the domain is known.
analyze_public_filing
Crucible™ Financial Filing Intelligence for public filings and annual reports. Accepts content, filingUrl, or SEC ticker/CIK lookup for 10-K, 10-Q, and 20-F filings. Returns metrics, risk changes, contradictions, source evidence, confidence, and a not-investment-advice flag.
review_contract_risks
Crucible™ Contract Risk Intelligence for contracts, MSAs, NDAs, procurement agreements, and compliance documents. Extracts risk clauses, obligations, deadlines, liability exposure, missing terms, unusual clauses, evidence, and human-review flags. Not legal advice.
extract_web
Extract content from a web page URL, optionally analyzing it with the actor-critic pipeline. Works with static and server-rendered HTML pages.
summarize
Generate a concise summary with key points. Faster and cheaper than analyze_document — best for shorter documents.
estimate_cost
FREE: Estimate the x402 USDC cost of any tool or multi-step workflow before paying. Use this before calling paid tools to check pricing.
health_check
FREE: Check service health, engine availability, and uptime. Use before dispatching paid calls to confirm the service is operational.
delegate_bulk_translate
Translate all string values in a JSON object or array to any target language. Preserves JSON structure, keys, and non-string values. Auto-chunks large payloads. Ideal for i18n locale files.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"amalgix": {
"amalgix": {
"url": "https://amalgix.io/mcp",
"transport": "streamable-http"
}
}
}
}McpServers
{
"amalgix": {
"url": "https://amalgix.io/mcp",
"transport": "streamable-http"
}
}Why Amalgix?
AI agents that need evidence-backed facts from financial filings and contracts face a problem: calling frontier models like Opus 4.8 or GPT-5.5 is expensive, and a single call doesn't produce verified evidence — you need at least two passes (extract + verify) to get source-grounded output.
Amalgix solves this with a cross-model evidence pipeline:
1. Model A extracts — A specialized extraction model pulls structured findings from your document. Each claim is tied to a verbatim quote, confidence score, and source reference.
2. Model B verifies — A different model cross-checks every finding against the original source. Contradictions are flagged; unsupported claims are marked for review — not presented as facts.
3. You pay less — Because each stage uses the optimal model for the job (not the most expensive one), the total pipeline cost is significantly lower than running frontier models yourself.
Cost Comparison (1MB Document)
| Provider | Pipeline Cost | vs Amalgix |
|:---------|:-------------|:-----------|
| Amalgix | $0.82 | — |
| Opus 4.8 (2-pass) | $2.88 | 3.5x more |
| GPT-5.5 (2-pass) | $3.12 | 3.8x more |
> Competitor costs represent what it takes to replicate Amalgix's extract → verify output using those models directly (2-pass, ~15% + ~10% output ratio).
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
