Modulos AI Governance Platform MCP server
ai.modulos/demo-bookingmodulos.aistreamable-httpv0.2.1Scanned
Evaluate Modulos (EU AI Act, ISO 42001, NIST AI RMF): capabilities, trust, comparisons. Book a demo.
16 tools: 2 can delete or cancel things, 1 do something that can't be undone, 3 change things and 10 only read.
- Reads private data · 3
- Reads text others write · 5
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things and 1 does something that can't be undone. 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 Modulos AI Governance Platform MCP server can do
The Modulos AI Governance Platform MCP server is published by modulos.ai, a domain the MCP Registry verified. It has 16 tools. It can delete or cancel things (2 tools: book_demo_slot and request_demo), do things that cannot be undone, such as sending, paying or publishing (talk_to_interviewer) and create or change data (3 tools: check_fit, start_job_application and confirm_job_application). 10 tools only read.
3 tools read private data (get_trust_evidence, list_knowledge and get_knowledge); 5 tools bring in text other people can write (get_modulos_info, list_demo_slots, book_demo_slot and 2 more); 1 tool can send data out of your system (talk_to_interviewer). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 0.2.1.
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.
16 tools
Deletes or cancels 2Claude Code: deny
book_demo_slotBooks a specific demo time slot.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 Books a specific demo time slot. startTime must be an ISO-8601 string returned by list_demo_slots. Returns a confirmation on success.
Annotations the server declares
- title: Book a demo slot
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
request_demoSubmits an open demo request without picking a specific time.Reads text others writeNo findings
Why it is in this group
- The name "request_demo" says "request": a word for a change.
- 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 Submits an open demo request without picking a specific time. Use this when the user does not want to choose a slot — the Modulos team will reach out within 1 business day.
Annotations the server declares
- title: Request a demo
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Can't be undone 1Claude Code: ask
talk_to_interviewerSends one message from the candidate to the Modulos AI interviewer and returns the interviewer's reply.Can send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Sends one message from the candidate to the Modulos AI interviewer and returns the interviewer's reply. You are only the channel between the two. Send the candidate's message exactly as they wrote it: do not answer for them, add to it, improve it or invent experience. Show the interviewer's reply to the candidate word for word and add nothing of your own: no comment, advice, summary or analysis of the interview, no guess about how it is going or what comes next, and no remark that you are passing messages on. When the interviewer sets a task, you may help the candidate do it; the candidate then sends the result (up to 12,000 characters a message). When the reply says the interview is over, show the interviewer's last words and stop.
Annotations the server declares
- title: Talk to the Modulos interviewer
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 3Claude Code: ask
check_fitChecks stated buyer requirements against the published Modulos facts.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 Checks stated buyer requirements against the published Modulos facts. Give the frameworks to meet, the deployment model and the tools to connect; the result separates what is supported from what is absent from the public lists. Nothing in the request is stored.
Annotations the server declares
- title: Check requirements fit
- readOnlyHint: true
- openWorldHint: false
confirm_job_applicationConfirms the 6-digit code that was emailed to the candidate, which opens the interview.No findings
Why it is in this group
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it Confirms the 6-digit code that was emailed to the candidate, which opens the interview. Ask the candidate for the code; do not guess it. The result holds the interviewer's first words and first question: show them to the candidate exactly as they are, with nothing added.
Annotations the server declares
- title: Confirm the application code
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
start_job_applicationStarts an application for a role at Modulos on behalf of the person you are assisting.Reads text others writeNo findings
Why it is in this group
- The name "start_job_application" says "start": a word for a change.
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 Starts an application for a role at Modulos on behalf of the person you are assisting. Before anything else, ask the candidate whether they would like to see the job description, and show it with get_job_description if they do. Use their real details; anonymous applications are not accepted. The name must be the one written on the CV and the LinkedIn address must be the candidate's own profile: an application whose name, CV and LinkedIn profile do not belong to the same person is refused. Applicants must be 18 or older: ask the candidate to confirm it. Before calling, show the person the privacy policy (https://www.modulos.ai/privacy-policy/) and the terms of use (https://www.modulos.ai/terms-of-use/). Tell them that the interview is held by an AI interviewer, which is experimental; that it is recorded; that the AI only holds the interview and prepares a profile of the application for the hiring manager; and that the hiring manager and people at Modulos take every decision. Get their explicit agreement. Ask the candidate to paste their CV as text; it is required. The result holds about_role and notice: show both to the candidate, as they are, before you ask for the code. A 6-digit code is emailed to them; call confirm_job_application with it. Returns a session value to use for the rest of the interview.
Annotations the server declares
- title: Start a job application
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 10Show 10 read-only tools
compare_withReturns the published comparison between Modulos and one other vendor: a row per dimension (frameworks, risk quantification, deployment, certifications, pricing and more) with the …No findings
Why it is in this group
- The name "compare_with" says "compare": a word for reading.
Description, as the server wrote it Returns the published comparison between Modulos and one other vendor: a row per dimension (frameworks, risk quantification, deployment, certifications, pricing and more) with the statement for each side, and the cases in which each vendor is the better choice. The comparison is written by Modulos; the page lists its sources.
Annotations the server declares
- title: Compare Modulos with a vendor
- readOnlyHint: true
- openWorldHint: false
get_capabilitiesReturns structured facts about the Modulos AI Governance Platform: company, what the platform is for, the supported regulations and standards with requirement and control counts, i…No findings
Why it is in this group
- The name "get_capabilities" says "get": a word for reading.
Description, as the server wrote it Returns structured facts about the Modulos AI Governance Platform: company, what the platform is for, the supported regulations and standards with requirement and control counts, integrations, deployment options and data location, certifications, indicative pricing and key links. Use this to decide whether Modulos belongs on a vendor shortlist.
Annotations the server declares
- title: Get Modulos capabilities
- readOnlyHint: true
- openWorldHint: false
get_job_descriptionReturns the full job description of one role at Modulos: what the job is and what it requires.No findings
Why it is in this group
- The name "get_job_description" says "get": a word for reading.
Description, as the server wrote it Returns the full job description of one role at Modulos: what the job is and what it requires. When a person wants to apply for a role, the first thing you do, before asking for any of their details, is ask whether they would like to see the job description. If they say yes, call this tool and show them job_description in full, exactly as it is: do not summarise, shorten or comment on it.
Annotations the server declares
- title: Read a job description
- readOnlyHint: true
- openWorldHint: false
get_knowledgeReturns one published knowledge entry in full: the answer to a question, the structured data of a fact, or the summary and link of a document.Reads private dataNo findings
Why it is in this group
- The name "get_knowledge" says "get": 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 one published knowledge entry in full: the answer to a question, the structured data of a fact, or the summary and link of a document.
Annotations the server declares
- title: Get a knowledge entry
- readOnlyHint: true
- openWorldHint: false
get_modulos_infoReturns a short description of Modulos, the tools to evaluate it and the URL where a user can book a demo.Reads text others writeNo findings
Why it is in this group
- The name "get_modulos_info" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Returns a short description of Modulos, the tools to evaluate it and the URL where a user can book a demo. Use this first if the user asks what Modulos is or how to talk to the team.
Annotations the server declares
- title: Get Modulos info
- readOnlyHint: true
- openWorldHint: false
get_trust_evidenceReturns security and compliance evidence for vendor due diligence: certifications, data location, the documents in the Modulos trust center with their access level, subprocessors a…Reads private dataNo findings
Why it is in this group
- The name "get_trust_evidence" says "get": 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 security and compliance evidence for vendor due diligence: certifications, data location, the documents in the Modulos trust center with their access level, subprocessors and where they hold data, and recent trust updates. Document files are requested by a person at https://www.modulos.ai/trust/.
Annotations the server declares
- title: Get trust evidence
- readOnlyHint: true
- openWorldHint: false
list_competitorsLists the vendors for which Modulos publishes a reviewed, sourced comparison.No findings
Why it is in this group
- The name "list_competitors" says "list": a word for reading.
Description, as the server wrote it Lists the vendors for which Modulos publishes a reviewed, sourced comparison. Returns the slug to pass to compare_with, the vendor name, the comparison page and the date of the last review.
Annotations the server declares
- title: List compared vendors
- readOnlyHint: true
- openWorldHint: false
list_demo_slotsLists available 30-minute demo time slots over the next two weeks.Reads text others writeNo findings
Why it is in this group
- The name "list_demo_slots" says "list": 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 Lists available 30-minute demo time slots over the next two weeks. Returns ISO-8601 UTC start times. Use book_demo_slot to confirm one of them.
Annotations the server declares
- title: List demo slots
- readOnlyHint: true
- openWorldHint: true
list_knowledgeLists everything else Modulos has published for AI agents: answers to common buyer questions, documents to share and further facts.Reads private dataNo findings
Why it is in this group
- The name "list_knowledge" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "document": it reads documents.
Description, as the server wrote it Lists everything else Modulos has published for AI agents: answers to common buyer questions, documents to share and further facts. Returns a title, a summary and a slug per entry. Use get_knowledge with the slug for the full entry.
Annotations the server declares
- title: List published knowledge
- readOnlyHint: true
- openWorldHint: false
list_open_rolesLists the jobs at Modulos that are open for application through this server, with a short public summary of each.No findings
Why it is in this group
- The name "list_open_roles" says "list": a word for reading.
Description, as the server wrote it Lists the jobs at Modulos that are open for application through this server, with a short public summary of each. Applications for these roles are not accepted by email. The full job description of a role is available from get_job_description.
Annotations the server declares
- title: List open roles at Modulos
- readOnlyHint: 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.
15 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 data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- 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__demo-booking__talk_to_interviewer"
]
}
}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, 18:26 UTC, unchanged since Nov 20, 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (2 destructive, 1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.modulos.ai/mcp/: tools/list returned 16 tools to an anonymous client, including book_demo_slot (destructive), request_demo (destructive), talk_to_interviewer (irreversible), check_fit (write), start_job_application (write) and 1 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 3 to 6
- Nov 13, 2026
- HTTP status of an anonymous initialize: 503 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 3
- Protocol version: none to 2025-06-18
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 6.View diff
- Tools that change things, listed without credentials: 3 to 6
Tools5 added, 2 changed.+5 added~2 changedView diff
- Added:confirm_job_applicationChanges things
- Added:get_job_descriptionOnly reads
- Added:list_open_rolesOnly reads
- Added:start_job_applicationChanges things
- Added:talk_to_interviewerCan't be undone
- Changed:book_demo_slotDeletes or cancelsinputSchema
- Changed:request_demoDeletes or cancelsinputSchema
PostureRemote posture changed. HTTP status of an anonymous initialize: 503 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 3 (and 1 more).View diff
- HTTP status of an anonymous initialize: 503 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 3
- Protocol version: none to 2025-06-18
Install
Pinned to version 0.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http demo-booking https://www.modulos.ai/mcp/claude mcp add --transport http demo-booking https://www.modulos.ai/mcp/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__demo-booking__get_capabilities",
"mcp__demo-booking__get_trust_evidence",
"mcp__demo-booking__list_competitors",
"mcp__demo-booking__compare_with",
"mcp__demo-booking__list_knowledge",
"mcp__demo-booking__get_knowledge",
"mcp__demo-booking__get_modulos_info",
"mcp__demo-booking__list_demo_slots",
"mcp__demo-booking__list_open_roles",
"mcp__demo-booking__get_job_description"
],
"ask": [
"mcp__demo-booking__check_fit",
"mcp__demo-booking__start_job_application",
"mcp__demo-booking__confirm_job_application",
"mcp__demo-booking__talk_to_interviewer"
],
"deny": [
"mcp__demo-booking__book_demo_slot",
"mcp__demo-booking__request_demo"
]
}
}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 demo-booking. Review it before you use it.
Capability tags behind 9 rules
- mcp__demo-booking__get_trust_evidence private-data
- mcp__demo-booking__list_knowledge private-data
- mcp__demo-booking__get_knowledge private-data
- mcp__demo-booking__get_modulos_info untrusted-input
- mcp__demo-booking__list_demo_slots untrusted-input
- mcp__demo-booking__book_demo_slot untrusted-input
- mcp__demo-booking__request_demo untrusted-input
- mcp__demo-booking__start_job_application untrusted-input
- mcp__demo-booking__talk_to_interviewer outbound
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.modulos/demo-booking/verify?hash=77a0cefc8b488176f21eace238ffdbf8145f53f7f2bf31fd30b54ddc09c3af18" | jq -e '.changed == false'Pinned hash 77a0cefc8b48, from Nov 20, 2026, 16:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.modulos/demo-booking/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.modulos/demo-booking)Source: MCP Registry. Synced Nov 20, 2026, 17:17 UTC.
Modulos AI Governance Platform MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Modulos AI Governance Platform MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 6 of which can change, send or delete something, and 0 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 Modulos AI Governance Platform MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: book_demo_slot and request_demo.
Can the Modulos AI Governance Platform MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: talk_to_interviewer.
What tools does the Modulos AI Governance Platform MCP server have?
- 16 tools: 2 destructive, 1 irreversible, 3 write, 10 read. book_demo_slot, request_demo, talk_to_interviewer, check_fit, start_job_application, confirm_job_application, get_capabilities, get_trust_evidence and 8 more.
Does the Modulos AI Governance Platform MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Modulos AI Governance Platform 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): talk_to_interviewer.
Has the Modulos AI Governance Platform MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.