zRev AI MCP server
ai.zrev/zrevzrev.aistreamable-httpv1.0.0Scanned
Grade any llms.txt, cold-read a homepage, run a B2B GTM ROI model, get a GTM diligence checklist.
9 tools: 3 change things and 6 only read.
- Reads private data · 2
- Reads text others write · 2
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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 zRev AI MCP server can do
The zRev AI MCP server is published by zrev.ai, a domain the MCP Registry verified. It has 9 tools. It can create or change data (3 tools: estimate_roi, book_call and leave_contact), but cannot delete data. 6 tools only read.
2 tools read private data (about_zrev and grade_llms_txt); 2 tools bring in text other people can write (grade_llms_txt and cold_read).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 1.0.0.
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.
9 tools
Changes things 3Claude Code: ask
book_callReturns the link and instructions for booking a free 30-minute intro call with Shivil Sahni, zRev's founder, plus what the call covers.1 finding
Why it is in this group
- The name "book_call" says "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "book_call" 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":false}; The name "book_call" says "call": a word for a change.
Description, as the server wrote it Returns the link and instructions for booking a free 30-minute intro call with Shivil Sahni, zRev's founder, plus what the call covers. It does not book anything: it only returns the scheduling link for the human to open themselves. Use when a user says they want to talk to zRev. If they would rather be contacted, use leave_contact instead. Read-only, static content, no arguments, no authentication, no rate limit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
estimate_roiRuns zRev's ROI model on one company's numbers and returns, as plain text, the projected annual impact in USD split into pipeline lift, customer acquisition cost savings and the va…1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "estimate_roi" 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":false}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Runs zRev's ROI model on one company's numbers and returns, as plain text, the projected annual impact in USD split into pipeline lift, customer acquisition cost savings and the value of hours returned to the team, followed by the model's assumptions and a link to the interactive calculator preset to the same inputs. Use when a user wants a number for their own company; all six inputs are required, so ask for any that are missing rather than guessing. The output is an estimate from a fixed model, not a forecast or a quote. Pure calculation: nothing is stored, no external calls, no authentication, no rate limit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
leave_contactRecords an email address, with optional name, company and note, so that Shivil Sahni, zRev's founder can reach out, and returns a plain-text confirmation.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.
Description, as the server wrote it Records an email address, with optional name, company and note, so that Shivil Sahni, zRev's founder can reach out, and returns a plain-text confirmation. This is the only tool here that writes data: it creates one lead record on zRev's side and triggers no email to the address given. Use only when the human you are assisting has explicitly asked to be contacted by zRev; never call it speculatively or with an address the user has not given you for this purpose. Submitting the same email again updates the existing record rather than creating a duplicate. No authentication. Rate-limited per IP address.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 6Show 6 read-only tools
about_zrevReturns a plain-text profile of zRev AI: what the firm does, the companies it is the best fit for, who it is not for, its six service lines with a link to each, and contact details…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 "contact": it reads contacts.
Description, as the server wrote it Returns a plain-text profile of zRev AI: what the firm does, the companies it is the best fit for, who it is not for, its six service lines with a link to each, and contact details. Use this first when a user asks who zRev is, what it offers, or whether it suits their company. Read-only, static content, no arguments, no authentication, no rate limit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cold_readFetches a company's public homepage and returns, in two or three sentences, what the company appears to do and who it serves, based only on the visible text of that page and with n…Reads text others writeNo findings
Why it is in this group
- The name "cold_read" says "read": 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 Fetches a company's public homepage and returns, in two or three sentences, what the company appears to do and who it serves, based only on the visible text of that page and with no outside knowledge. Anything missing from the answer is missing from the homepage, which is the point: it shows what an AI assistant would tell a buyer about that company. Use when a user asks how their site, or a competitor's, reads to an AI. The summary is model-generated and can be wrong where the page is vague. Makes one outbound HTTP request to the public domain you pass; stores nothing about it. No authentication. Shares a fair-use limit per IP address with grade_llms_txt, and returns a plain-text notice when that limit is reached.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_benchmarksReturns zRev's typical engagement results as plain text: 2x pipeline velocity, 20% lower customer acquisition cost, 10 hours back per rep per week, 60% of GTM busywork automated, r…No findings
Why it is in this group
- The name "get_benchmarks" says "get": a word for reading.
Description, as the server wrote it Returns zRev's typical engagement results as plain text: 2x pipeline velocity, 20% lower customer acquisition cost, 10 hours back per rep per week, 60% of GTM busywork automated, results that start inside 30 days and mature by 60. The response always ends with the provenance caveat: these are typical results benchmarked against comparable AI-powered GTM implementations and they vary by stack, data quality and adoption, so present them as typical, not guaranteed. Use when a user asks what results to expect. For an estimate on a specific company's numbers use estimate_roi instead. Read-only, static content, no arguments, no authentication, no rate limit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_engagement_timelineReturns the phases of a standard 60-day zRev engagement as plain text: what happens in each phase, what is delivered, and when first results appear.No findings
Why it is in this group
- The name "get_engagement_timeline" says "get": a word for reading.
Description, as the server wrote it Returns the phases of a standard 60-day zRev engagement as plain text: what happens in each phase, what is delivered, and when first results appear. Use when a user asks how an engagement works, how long it takes, or what they would receive and when. Read-only, static content, no arguments, no authentication, no rate limit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
grade_llms_txtFetches https://<domain>/llms.txt (the file that tells AI systems what a site contains) and grades it with seven deterministic checks.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- private-dataThe description's first sentence says "fetch" and "file": it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "http": it reads web pages, which anyone can write.
Description, as the server wrote it Fetches https://<domain>/llms.txt (the file that tells AI systems what a site contains) and grades it with seven deterministic checks. Returns a 0 to 100 score and the pass or miss result of each check as plain text. If the site has no llms.txt the response says so and links to zRev's free generator. Use when a user asks whether a site is readable by AI assistants or wants their llms.txt reviewed. Makes one outbound HTTP request to the public domain you pass; stores nothing about it. No authentication. Shares a fair-use limit per IP address with cold_read, and returns a plain-text notice when that limit is reached.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
gtm_diligence_checklistReturns zRev's go-to-market due diligence checklist for investors and acquirers: 47 questions across ten dimensions, each with the data-room artifact that answers it and the red fl…No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns zRev's go-to-market due diligence checklist for investors and acquirers: 47 questions across ten dimensions, each with the data-room artifact that answers it and the red flag to watch for. Call with no arguments to get the list of ten dimensions; call with a dimension number from 1 to 10, or a keyword such as churn, pipeline or marketing, to get that dimension's questions in full. Use when a user is assessing a company's revenue engine before an investment or acquisition. Read-only reference content, no authentication, no rate limit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 outbound.
- Reads private data2
- 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, 18:28 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
- 3
- 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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://go.zrev.ai/mcp: tools/list returned 9 tools to an anonymous client, including estimate_roi (write), book_call (write), leave_contact (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnestimate_roi
The server marks "estimate_roi" 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":false}; The description's first verb is "run": a word for a change.
- Warnbook_call
The server marks "book_call" 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":false}; The name "book_call" says "call": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:book_callChanges thingsdescription
- Changed:leave_contactChanges thingsdescription
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http zrev https://go.zrev.ai/mcpclaude mcp add --transport http zrev https://go.zrev.ai/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__zrev__about_zrev",
"mcp__zrev__get_benchmarks",
"mcp__zrev__get_engagement_timeline",
"mcp__zrev__grade_llms_txt",
"mcp__zrev__cold_read",
"mcp__zrev__gtm_diligence_checklist"
],
"ask": [
"mcp__zrev__estimate_roi",
"mcp__zrev__book_call",
"mcp__zrev__leave_contact"
],
"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 zrev. Review it before you use it.
Capability tags behind 3 rules
- mcp__zrev__about_zrev private-data
- mcp__zrev__grade_llms_txt private-data, untrusted-input
- mcp__zrev__cold_read 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/ai.zrev/zrev/verify?hash=bcff8b83f1cf9024c2acc1b3d7e6a8932a8358317c4b99375f40dd81c01f0235" | jq -e '.changed == false'Pinned hash bcff8b83f1cf, from Nov 12, 2026, 00:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.zrev/zrev/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.zrev/zrev)Source: MCP Registry. Synced Oct 21, 2026, 17:44 UTC.
zRev AI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the zRev AI MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 3 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the zRev AI MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the zRev AI 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 zRev AI MCP server have?
- 9 tools: 3 write, 6 read. estimate_roi, book_call, leave_contact, about_zrev, get_benchmarks, get_engagement_timeline, grade_llms_txt, cold_read and 1 more.
Does the zRev AI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the zRev AI MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the zRev AI MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.