Real estate deal memo MCP server
io.github.agentwares/deal-memoagentwaresstreamable-httpv0.1.1Scanned
Real estate deal memo from a US address: AVM, rent, comps, cap rate, cash-on-cash, DSCR, red flags.
2 tools: 2 can delete or cancel things.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel 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 Real estate deal memo MCP server can do
The Real estate deal memo MCP server is published by the GitHub account agentwares. It has 2 tools. It can delete or cancel things (2 tools: realestate_deal_memo and realestate_lookup). None of its tools only reads.
2 tools bring in text other people can write (realestate_deal_memo and realestate_lookup).
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 16, 2026, version 0.1.1.
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.
2 tools
Deletes or cancels 2Claude Code: deny
realestate_deal_memoUnderwrite a US residential property from its street address for a rental, flip or hold strategy.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 destructive (destructiveHint: true).
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 Underwrite a US residential property from its street address for a rental, flip or hold strategy. Pulls the property record (owner, last sale, taxes, HOA), the automated value estimate with sale comps and the long-term rent estimate with rental comps from RentCast, then computes NOI, cap rate, cash-on-cash, DSCR, GRM and break-even occupancy from stated assumptions with deterministic math (plus 70%-rule, profit and ROI for a flip; a multi-year exit projection for a hold), lists red flags with a pass/review/fail screen, and adds a one-paragraph analyst memo. Returns {data, sources, as_of, confidence, notice}. Not financial advice: verify before acting. Paid: $0.75 per call; without credit you get a PAYMENT_REQUIRED result. Set sample=true for a free example response.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
realestate_lookupFetch one RentCast record for a US street address.Reads text others write1 finding
Why it is in this group
- The name "realestate_lookup" says "lookup": a word for reading.
- The server marks it destructive (destructiveHint: true).
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 "realestate_lookup" destructive (destructiveHint: true), and its name says "lookup", a word for reading.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":true,"idempotentHint":false,"openWorldHint":true}; The name "realestate_lookup" says "lookup": a word for reading.
Description, as the server wrote it Fetch one RentCast record for a US street address. kind=property: characteristics, owner, last sale, tax bill, assessment, HOA and sale history. kind=value: automated value estimate with a low/high range and the sale comps behind it. kind=rent: long-term rent estimate with a range and rental comps. One upstream call per lookup; use realestate_deal_memo when you need all three plus the underwriting. Returns {data, sources, as_of, confidence, notice}. Paid: $0.10 per call; without credit you get a PAYMENT_REQUIRED result. Set sample=true for a free example response.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- 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, 19:01 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
- 2
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 destructive). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agentwares-deal-memo.vercel.app/api/mcp: tools/list returned 2 tools to an anonymous client, including realestate_deal_memo (destructive), realestate_lookup (destructive)
Findings
Matches of fixed checks, with the text they matched.
The server marks "realestate_lookup" destructive (destructiveHint: true), and its name says "lookup", a word for reading.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":true,"idempotentHint":false,"openWorldHint":true}; The name "realestate_lookup" says "lookup": 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 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http deal-memo https://agentwares-deal-memo.vercel.app/api/mcpclaude mcp add --transport http deal-memo https://agentwares-deal-memo.vercel.app/api/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": [],
"ask": [],
"deny": [
"mcp__deal-memo__realestate_deal_memo",
"mcp__deal-memo__realestate_lookup"
]
}
}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 deal-memo. Review it before you use it.
Capability tags behind 2 rules
- mcp__deal-memo__realestate_deal_memo untrusted-input
- mcp__deal-memo__realestate_lookup 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.agentwares/deal-memo/verify?hash=1003445b14ebe68e5b09ba7707d8dc2fcceec31b92bef7a20ab20ac479f2ada5" | jq -e '.changed == false'Pinned hash 1003445b14eb, from Nov 16, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.agentwares/deal-memo/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.agentwares/deal-memo)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:22 UTC.
Real estate deal memo MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Real estate deal memo MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, 2 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 Real estate deal memo MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: realestate_deal_memo and realestate_lookup.
Can the Real estate deal memo 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 Real estate deal memo MCP server have?
- 2 tools: 2 destructive. realestate_deal_memo and realestate_lookup.
Does the Real estate deal memo MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Real estate deal memo MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Real estate deal memo MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.