Curagent Title Risk MCP server
io.github.ksh0rt/curagent-mcpksh0rtstreamable-httpv1.0.3Scanned
AI title risk analysis for US real estate closing docs. Get an API key at curagent.io
3 tools: 1 change things and 2 only read.
- Reads private data · 2
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- 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 Curagent Title Risk MCP server can do
The Curagent Title Risk MCP server is published by the GitHub account ksh0rt. It has 3 tools. It can create or change data (1 tool: analyze_title_documents), but cannot delete data. 2 tools only read.
2 tools read private data (analyze_title_documents and check_coverage).
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 20, 2026, version 1.0.3.
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.
3 tools
Changes things 1Claude Code: ask
analyze_title_documentsAnalyzes US real estate title and closing documents and returns a structured risk report: a risk score (0-100, higher is safer) and level, findings with verbatim evidence from the …Reads private data1 finding
Why it is in this group
- The name "analyze_title_documents" says "analyze": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- private-dataThe name "analyze_title_documents" says "analyze" and "document": it reads documents.
- private-dataThe description's first sentence says "analyze" and "document": it reads documents.
Findings
- Warn
The server marks "analyze_title_documents" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "analyze_title_documents" says "analyze": a word for reading.
Description, as the server wrote it Analyzes US real estate title and closing documents and returns a structured risk report: a risk score (0-100, higher is safer) and level, findings with verbatim evidence from the documents and guidance on how to cure each one, the Schedule B-I requirements extracted from any title commitment in the package, and the jurisdiction applied (jurisdictionApplied). Accepts one or more PDF documents as base64 strings (deed, title commitment, mortgage, closing disclosure, survey, payoff letter, HOA estoppel, etc.), including a single PDF containing a whole closing package, which is split into its constituent instruments. Submitting several documents together also enables cross-document checks for contradictions in parcel ID, address, and party names. Properties in all 50 states and DC are analyzed; statute citations appear only for jurisdictions at production maturity, so call check_coverage to see each state's maturity. Uses one of your 3 free analyses (sandbox tier) or 1 credit (paid tiers); call get_credit_balance first to confirm available credits.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
Only reads 2Show 2 read-only tools
check_coverageReturns what Curagent supports: every analyzed US jurisdiction with its maturity, which document types, and how analysis is priced.Reads private dataNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "document": it reads documents.
Description, as the server wrote it Returns what Curagent supports: every analyzed US jurisdiction with its maturity, which document types, and how analysis is priced. Curagent runs its full analysis for properties in all 50 states and DC using each state's own terminology; jurisdictions at production maturity also include hand-verified statute citations in cure guidance. No API key is needed for this call.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_credit_balanceReturns the caller's remaining Curagent credit balance and tier.No findings
Why it is in this group
- The name "get_credit_balance" says "get": a word for reading.
Description, as the server wrote it Returns the caller's remaining Curagent credit balance and tier. Call this before analyzing to confirm available usage. Sandbox tier includes 3 free analyses total, not a recurring allowance; paid tiers use 1 credit per analysis.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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, 19:07 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
- 1
- 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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.curagent.io/: tools/list returned 3 tools to an anonymous client, including analyze_title_documents (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "analyze_title_documents" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "analyze_title_documents" says "analyze": 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 1.0.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http curagent https://mcp.curagent.io/claude mcp add --transport http curagent https://mcp.curagent.io/Run 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__curagent__get_credit_balance",
"mcp__curagent__check_coverage"
],
"ask": [
"mcp__curagent__analyze_title_documents"
],
"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 curagent. Review it before you use it.
Capability tags behind 2 rules
- mcp__curagent__analyze_title_documents private-data
- mcp__curagent__check_coverage private-data
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.ksh0rt/curagent-mcp/verify?hash=569e0ad7af81575aa21300cd67ffea330ca868664ba471e4d3b8244dae347a25" | jq -e '.changed == false'Pinned hash 569e0ad7af81, from Nov 20, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.ksh0rt/curagent-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.ksh0rt/curagent-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:37 UTC.
Curagent Title Risk MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Curagent Title Risk MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 1 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 Curagent Title Risk MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Curagent Title Risk 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 Curagent Title Risk MCP server have?
- 3 tools: 1 write, 2 read. analyze_title_documents, get_credit_balance and check_coverage.
Does the Curagent Title Risk MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Curagent Title Risk MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Curagent Title Risk MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.