Amalgix MCP Server (io.github.Amalgix-io/Amalgix)

Amalgix provides a cross-model evidence pipeline for financial filings and contracts. It is offered as an MCP server and also exposes a REST interface, with a pay-per-call model using x402 (described as up to 3.8x cheaper than calling frontier models directly).

🛠️ Key Features

Cross-model evidence pipeline for financial filings & contracts
MCP + REST interface
x402 pay-per-call pricing model

🚀 Use Cases

Evidence extraction and support for financial filings
Contract intelligence and document evidence workflows

⚡ Developer Benefits

Integration via MCP
Access patterns supported via REST
x402 micropayment approach for per-call usage (USDC referenced in topics)

⚠️ Limitations

Pricing described only as “up to 3.8x cheaper”; no guaranteed performance or accuracy claims provided

Relevant Topics

ai-agent, ai-api, llm, mcp, mcp-server, micropayments, usdc, x402, contract-intelligence, financial-filings, document-intelligence

Amalgix Logo

Amalgix

Cross-Model Evidence Pipeline for Financial Filings & Contracts
MCP + REST · x402 Pay-Per-Call · Up to 3.8x cheaper than calling frontier models directly

Website | OpenAPI Spec | Smithery | x402scan | X (Twitter)

MCP x402 Chains Tools Evidence backed

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:

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.
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.
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).

What is Amalgix?

A crypto-native, MCP + REST intelligence API for AI agents. The proprietary Crucible™ Evidence Engine orchestrates the cross-model pipeline:

Source-grounded claims — each material finding includes claim, evidence, sourceRef, confidence, and verificationStatus
Cross-model verification — extraction and verification use different models, catching errors that single-model approaches miss
Financial Filing Intelligence — SEC 10-K, 10-Q, and 20-F analysis by content, filing URL, ticker, or CIK
Contract Risk Intelligence — clauses, obligations, deadlines, liability, missing terms, and evidence
x402 payments — paid calls settle in USDC on Base or Solana. No API keys required, no subscriptions
Wallet dashboard — EVM wallet login for request history and API key management

Crucible is designed for evidence triage and agent workflows. It does not claim perfect accuracy, legal advice, or investment advice; responses expose confidence and verification metadata so downstream systems can inspect the basis for each finding.

Quick Start

MCP

Add Amalgix to any Streamable HTTP MCP-compatible client:

json

{
  "mcpServers": {
    "amalgix": {
      "url": "https://amalgix.io/mcp",
      "transport": "streamable-http"
    }
  }
}

REST

bash

curl -X GET https://amalgix.io/api/v1/health

Paid endpoints require x402 payment headers. Use estimate_cost first to preview pricing before any paid call.

Tools

Tool	Description	Pricing
`analyze_public_filing`	Financial Filing Intelligence for public SEC filings. Accepts content, filingUrl, ticker, or CIK for 10-K, 10-Q, and 20-F workflows.	$0.03-$79.00
`review_contract_risks`	Contract Risk Intelligence for clauses, obligations, liability exposure, missing clauses, unusual terms, evidence, and human-review flags. Not legal advice.	$0.03-$79.00
`analyze_document`	General evidence analysis with source-grounded findings, confidence, and verification status.	$0.03-$79.00
`extract_web`	Static/server-rendered public web content extraction with optional analysis.	From $0.01
`summarize`	Fast single-pass summarization with key points.	From $0.01
`delegate_bulk_translate`	Translate JSON string values while preserving object structure.	From $0.01
`estimate_cost`	Free pre-flight cost preview for paid tools or workflows.	Free
`health_check`	Free service health and engine availability check.	Free

REST Endpoints

Endpoint	Method	Purpose
`/api/v1/filings/analyze`	POST	Financial Filing Intelligence
`/api/v1/contracts/review`	POST	Contract Risk Intelligence
`/api/v1/analyze`	POST	General Crucible™ evidence analysis
`/api/v1/cost`	POST	Cost estimation, free
`/api/v1/health`	GET	Health check, free
`/api/v1/auth/evm/nonce`	POST	Create wallet-login challenge, free
`/api/v1/auth/evm/verify`	POST	Verify wallet signature, free
`/api/v1/api-keys`	GET/POST	List or create API keys after wallet login, free
`/api/v1/jobs`	GET	Recent analysis jobs after wallet login, free
`/api/v1/requests`	GET	Recent request logs after wallet login, free
`/api/v1/payments`	GET	Recent x402 payment events after wallet login, free

Legacy REST tools (/api/v1/extract, /api/v1/summarize, /api/v1/translate) are available as operator opt-in via AMALGIX_ENABLE_LEGACY_REST_TOOLS=true. They remain accessible through MCP by default.

Crucible™ Output Contract

Crucible normalizes evidence into a stable shape for agents:

json

{
  "analysis": {
    "summary": "...",
    "evidenceFindings": [
      {
        "claim": "...",
        "evidence": "...",
        "sourceRef": "document:line:12",
        "confidence": "high",
        "verificationStatus": "supported"
      }
    ],
    "overallConfidence": "high"
  },
  "meta": {
    "engine": "Crucible™ Evidence Engine",
    "analysisType": "general_evidence",
    "routingTier": "large_context",
    "estimatedCost": 0.03
  }
}

Analysis modes:

general_evidence
financial_filing
contract_review

Pricing

Dynamic pricing based on document size. Amalgix's cross-model pipeline delivers equivalent evidence quality at a fraction of single-model cost:

File Size	Amalgix	Opus 4.8 (2-pass)	GPT-5.5 (2-pass)	Savings
256KB	$0.30	$0.76	$0.82	59-62%
1MB	$0.82	$2.88	$3.12	72-74%
5MB	$7.36	$12.12	$13.14	39-44%
20MB	$29.42	$46.52	$50.50	37-42%

Use the free estimate_cost tool for a request-specific quote.

Payment

Amalgix uses the x402 protocol for pay-per-call settlement:

Currency: USDC
Chains: Base (EVM) or Solana (SVM)
Scheme: exact
Authentication: x402 for paid execution; optional wallet/API key identity for dashboard and REST attribution

Security & Privacy

Contract raw text is not persisted by default; Amalgix stores hashes, metadata, job status, and optional results only when configured.
Public financial filing metadata may be cached because filings are public.
Connections use TLS.
Paid analysis content is sent to third-party LLM providers for processing.
Do not submit passwords, private keys, SSNs, classified data, or other regulated PII.
Contract and filing outputs are evidence triage only, not legal or investment advice.

io.github.Amalgix-io/Amalgix

Amalgix MCP Server (io.github.Amalgix-io/Amalgix)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Relevant Topics

Topics

analyze_document

analyze_public_filing

review_contract_risks

extract_web

summarize

estimate_cost

health_check

delegate_bulk_translate

Amalgix

Why Amalgix?

Cost Comparison (1MB Document)

What is Amalgix?

Quick Start

MCP

REST

Tools

REST Endpoints

Crucible™ Output Contract

Pricing

Payment

Security & Privacy

Links

License

Install

Remote endpoint

Related servers

content	string	optional	Document content to analyze (max 20MB). Required unless fileUrl is provided. Accepts: (1) plain text, (2) Base64-encoded file with data URI prefix (e.g., "data:application/pdf;base64,..."), or (3) raw Base64 binary for text-extractable source documents. PRIVACY NOTICE: Content is transmitted to third-party LLM providers for processing. Do NOT submit documents containing passwords, private keys, SSNs, or other regulated PII.
query	string	required	Analysis question or focus area
fileUrl	string	optional	Optional: HTTPS URL to download the document from. If provided, content field is ignored. Use text-extractable source documents. Max 20MB.
format	string	optional	Optional: Force a specific input format. Default: auto-detect via magic bytes.
analysisType	string	optional	Optional Crucible™ analysis mode. Default: auto.
sourceType	string	optional	Optional source type metadata for Crucible™ routing and output metadata.
ticker	string	optional	Optional ticker/company symbol metadata for financial filing analysis.
partyPerspective	string	optional	Optional contract review perspective. Default: neutral.
jurisdiction	string	optional	Optional contract jurisdiction metadata. Output remains evidence triage, not legal advice.

url	string	required	Web page URL to extract content from
query	string	optional	Optional analysis question to apply after extraction

ticker	string	optional	Ticker symbol, e.g. AAPL. Used to resolve SEC filings when content/filingUrl is omitted.
cik	string	optional	SEC CIK. Optional alternative to ticker.
form	string	optional	SEC filing form. Default: 10-K.
year	integer	optional	Filing or report year. Omit for latest matching filing.
filingUrl	string	optional	Public filing/report URL. Used before ticker lookup when provided.
content	string	optional	Uploaded or preprocessed filing text. Used before URL/ticker lookup when provided.
depth	string	optional	Analysis depth hint. Default: standard.
question	string	optional	Optional focus question for the filing analysis.

content	string	required	Document text to summarize
max_length	integer	optional	Optional maximum summary length in words (default: 500)

tool	string	required	Tool name to estimate cost for (e.g. "analyze_document", "extract_web", "summarize")
content_length	integer	optional	Approximate character count of your input document (used for LLM cost estimation)
depth	string	optional	Workflow depth hint for filing/contract tools. Default: standard
input_source	string	optional	Input source hint used to explain cache/download behavior
query	string	optional	Optional analysis query. Include it for exhaustive/high-output requests so the preview matches the x402 quote.
content_sample	string	optional	Optional short content excerpt for multilingual/high-output pricing hints without sending the full document.
workflow	array	optional	Optional list of tool names for a multi-step workflow. Returns total cost for the full pipeline.

json	string	required	JSON string (object or array) whose string values will be translated
target_language	string	required	Target language name or ISO 639-1 code (e.g. "Chinese", "zh", "Japanese", "ja", "fr")
source_language	string	optional	Source language (default: auto-detect). E.g. "English", "en"
preserve_keys	boolean	optional	If true (default), object keys are left untranslated. Set false to also translate keys.