Amalgix MCP server
io.github.Amalgix-io/AmalgixAmalgix-iostreamable-httpv1.1.0Scanned
Cross-model evidence pipeline for financial filings & contracts. x402 pay-per-call.
8 tools: 6 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 7
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Amalgix MCP server can do
The Amalgix MCP server is published by the GitHub account Amalgix-io. It has 8 tools. It can create or change data (6 tools: review_contract_risks, extract_web, summarize, estimate_cost and 2 more), but cannot delete data. 2 tools only read.
1 tool reads private data (analyze_document); 7 tools bring in text other people can write (analyze_document, analyze_public_filing, review_contract_risks and 4 more); 1 tool can send data out of your system (extract_web). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 1.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Changes things 6Claude Code: ask
delegate_bulk_translateTranslate all string values in a JSON object or array to any target language.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
estimate_costFREE: Estimate the x402 USDC cost of any tool or multi-step workflow before paying.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it FREE: Estimate the x402 USDC cost of any tool or multi-step workflow before paying. Use this before calling paid tools to check pricing.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
extract_webExtract content from a web page URL, optionally analyzing it with the actor-critic pipeline.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Extract content from a web page URL, optionally analyzing it with the actor-critic pipeline. Works with static and server-rendered HTML pages.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
health_checkFREE: Check service health, engine availability, and uptime.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it FREE: Check service health, engine availability, and uptime. Use before dispatching paid calls to confirm the service is operational.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
review_contract_risksCrucible™ Contract Risk Intelligence for contracts, MSAs, NDAs, procurement agreements, and compliance documents.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
summarizeGenerate a concise summary with key points.Reads text others write1 finding
Why it is in this group
- The name "summarize" says "summarize": a word for reading.
- The description's first verb is "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "summarize" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "summarize" says "summarize": a word for reading.
Description, as the server wrote it Generate a concise summary with key points. Faster and cheaper than analyze_document — best for shorter documents.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
analyze_documentAnalyze a document using Crucible™ Evidence Engine.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "analyze_document" says "analyze": a word for reading.
What it can reach
- private-dataThe name "analyze_document" says "analyze" and "document": it reads documents.
- private-dataThe description's first sentence says "analyze" and "document": it reads documents.
- private-dataThe input names a file (input.fileUrl), and the tool reads: it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
analyze_public_filingCrucible™ Financial Filing Intelligence for public filings and annual reports.Reads text others writeNo findings
Why it is in this group
- The name "analyze_public_filing" says "analyze": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
7 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__amalgix__extract_web"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:56 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://amalgix.io/mcp: tools/list returned 8 tools to an anonymous client, including review_contract_risks (write), extract_web (write), summarize (write), estimate_cost (write), health_check (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
- Warnsummarize
The server marks "summarize" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "summarize" says "summarize": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http amalgix https://amalgix.io/mcpclaude mcp add --transport http amalgix https://amalgix.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__amalgix__analyze_document",
"mcp__amalgix__analyze_public_filing"
],
"ask": [
"mcp__amalgix__review_contract_risks",
"mcp__amalgix__extract_web",
"mcp__amalgix__summarize",
"mcp__amalgix__estimate_cost",
"mcp__amalgix__health_check",
"mcp__amalgix__delegate_bulk_translate"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as amalgix. Review it before you use it.
Capability tags behind 7 rules
- mcp__amalgix__analyze_document private-data, untrusted-input
- mcp__amalgix__analyze_public_filing untrusted-input
- mcp__amalgix__review_contract_risks untrusted-input
- mcp__amalgix__extract_web untrusted-input, outbound
- mcp__amalgix__summarize untrusted-input
- mcp__amalgix__health_check untrusted-input
- mcp__amalgix__delegate_bulk_translate untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Amalgix-io/Amalgix/verify?hash=ff30bea3cd08dfd54ca24c1220d80a2d2a45889c2a1ccf647f976e354ec2a812" | jq -e '.changed == false'Pinned hash ff30bea3cd08, from Nov 15, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Amalgix-io/Amalgix/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Amalgix-io/Amalgix)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:14 UTC.
Amalgix MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Amalgix MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 6 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Amalgix MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Amalgix MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Amalgix MCP server have?
- 8 tools: 6 write, 2 read. review_contract_risks, extract_web, summarize, estimate_cost, health_check, delegate_bulk_translate, analyze_document and analyze_public_filing.
Does the Amalgix MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Amalgix MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): extract_web.
Has the Amalgix MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.