MCP.Market

Amalgix MCP server

online · 100% uptime
by Amalgix-io·io.github.Amalgix-io/Amalgix·v1.1.0
No reviews yet

Cross-model evidence pipeline for financial filings & contracts. x402 pay-per-call.

B79/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B79/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Amalgix yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Amalgix tools (8)

write = sends, deletes, buys or posts
  • analyze_documentFree

    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_filingFree

    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.

  • delegate_bulk_translateFree

    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.

  • estimate_costFree

    FREE: Estimate the x402 USDC cost of any tool or multi-step workflow before paying. Use this before calling paid tools to check pricing.

  • extract_webFree

    Extract content from a web page URL, optionally analyzing it with the actor-critic pipeline. Works with static and server-rendered HTML pages.

  • health_checkFree

    FREE: Check service health, engine availability, and uptime. Use before dispatching paid calls to confirm the service is operational.

  • review_contract_risksFree

    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.

  • summarizeFree

    Generate a concise summary with key points. Faster and cheaper than analyze_document — best for shorter documents.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 847ms20/20
  • Tool poisoning8 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 119 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 79/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Amalgix compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
79/100
higher than 58% of 4,460 AI and agents servers
Tools
8
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
323 ms
faster than 44% of 2,331 AI and agents servers

What its tools let an agent do: 8 read

Install Amalgix in Claude Code, Cursor or VS Code

claude mcp add --transport http Amalgix https://amalgix.io/mcp
Add to Cursor

What the publisher says

From the Amalgix repository's README, as published. We do not edit it. Read it on GitHub

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)

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)

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:

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

REST

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.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Amalgix: common questions

Is Amalgix MCP server safe?
Mostly: it is graded B (79/100). Read the Amalgix safety report
How do I install Amalgix?
It runs remotely at amalgix.io. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Amalgix need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Amalgix maintained?
The last commit was 156 days ago (2026-06-01). The latest release is v1.1.0.
Is Amalgix up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Amalgix?
Servers from other publishers that do the same job: Ausca MCP server, HOL Guard MCP server and Watch Skill MCP server.
How does Amalgix compare with other AI and agents MCP servers?
safety score 79/100 (higher than 58% of 4,460 AI and agents servers); tools 8 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Amalgix

Same job from other publishers: the closest match first, then the best rated.

  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B
  • DCC-MCP Core
    Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
    A
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A