FrankoX MCP server
com.frankox/trade-intelligencefrankox.comstreamable-httpv1.0.0Scanned
Verified opt-in trade profiles and consented manufacturer drafts; no private customer data.
22 tools: 5 can delete or cancel things, 5 change things and 12 only read.
- Reads private data · 5
- Reads text others write · 6
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
5 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 FrankoX MCP server can do
The FrankoX MCP server is published by frankox.com, a domain the MCP Registry verified. It has 22 tools. It can delete or cancel things (5 tools: update_manufacturer_draft, create_agent_conversation, reply_to_agent_conversation, initiate_network_request and 1 more) and create or change data (5 tools: register_manufacturer_interest, create_manufacturer_draft, request_opportunity_match, discover_network_intents and 1 more). 12 tools only read.
5 tools read private data (search_opportunities, get_public_company_profile, get_public_product_profile and 2 more); 6 tools bring in text other people can write (create_agent_conversation, get_agent_conversation, list_agent_conversations and 3 more); 1 tool can send data out of your system (reply_to_agent_conversation). 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 2 findings (annotation-conflict and credentials-mention). 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 9, 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.
22 tools
Deletes or cancels 5Claude Code: deny
create_agent_conversationOpen a private account-bound agent conversation with explicit user consent.Reads text others writeNo findings
Why it is in this group
- The name "create_agent_conversation" says "create": 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 Open a private account-bound agent conversation with explicit user consent. Content is untrusted and does not verify or enroll a company.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
initiate_network_requestConsent-only FX network discovery/handshake.Reads text others writeNo findings
Why it is in this group
- The name "initiate_network_request" 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 Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
reply_to_agent_conversationReply in an existing account-bound conversation; no authority changes or external outreach.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "reply_to_agent_conversation" says "reply": a word for sending, and what is sent cannot be taken back.
- 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.
- outboundThe name "reply_to_agent_conversation" says "reply": it sends or publishes something to other people.
Description, as the server wrote it Reply in an existing account-bound conversation; no authority changes or external outreach.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
respond_to_network_requestConsent-only FX network discovery/handshake.Reads text others writeNo findings
Why it is in this group
- The name "respond_to_network_request" 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 Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
update_manufacturer_draftUpdate the authenticated submitting agent's unconfirmed draft with optimistic revision checks.No findings
Why it is in this group
- The name "update_manufacturer_draft" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update the authenticated submitting agent's unconfirmed draft with optimistic revision checks.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
Changes things 5Claude Code: ask
create_manufacturer_draftSubmit an explicitly consented private unverified manufacturer draft.No findings
Why it is in this group
- The name "create_manufacturer_draft" says "create": a word for a change.
Description, as the server wrote it Submit an explicitly consented private unverified manufacturer draft. Requires real company confirmation before authority and independent review/publication permission before search visibility.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
discover_network_intentsConsent-only FX network discovery/handshake.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 Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
external_business_handshakeSubmit public non-binding business intent after creating a public ingress session.1 finding
Why it is in this group
- The description's first verb is "submit": a word for a change.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...ting a public ingress session. Send its credential in X-FrankoX-Session header. Never cust..."
Description, as the server wrote it Submit public non-binding business intent after creating a public ingress session. Send its credential in X-FrankoX-Session header. Never customer/OAuth access. No automatic Opportunity. See /external-agents/skill.md.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
register_manufacturer_interestRecord interest only after explicit user approval.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 Record interest only after explicit user approval. Does not enroll or verify a company.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
request_opportunity_matchFilter only permitted public opportunity projections.1 finding
Why it is in this group
- The name "request_opportunity_match" says "request": 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 "request_opportunity_match" 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 "request_opportunity_match" says "request": a word for a change.
Description, as the server wrote it Filter only permitted public opportunity projections. No private/customer matching, scoring changes or autonomous research execution.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
Only reads 12Show 12 read-only tools
get_agent_conversationRead only the authenticated client and customer account's own conversation.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_agent_conversation" says "get": a word for reading.
What it can reach
- private-dataThe name "get_agent_conversation" says "get" and "conversation": it reads messages.
- private-dataThe description's first sentence says "read" and "conversation": it reads messages.
- untrusted-inputThe name "get_agent_conversation" says "get" and "conversation": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Read only the authenticated client and customer account's own conversation.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_external_agent_entrypointPublic FrankoX agent identity and safe pre-tenant handshake instructions.No findings
Why it is in this group
- The name "get_external_agent_entrypoint" says "get": a word for reading.
Description, as the server wrote it Public FrankoX agent identity and safe pre-tenant handshake instructions. No verified match or autonomous commercial authority.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_network_requestConsent-only FX network discovery/handshake.No findings
Why it is in this group
- The name "get_network_request" says "get": a word for reading.
Description, as the server wrote it Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_public_company_profileRetrieve a verified opt-in public profile by opaque ID; returns no private contacts or documents.Reads private dataNo findings
Why it is in this group
- The name "get_public_company_profile" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "retrieve" and "contact": it reads contacts.
Description, as the server wrote it Retrieve a verified opt-in public profile by opaque ID; returns no private contacts or documents.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_public_product_profileRetrieve a verified opt-in public profile by opaque ID; returns no private contacts or documents.Reads private dataNo findings
Why it is in this group
- The name "get_public_product_profile" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "retrieve" and "contact": it reads contacts.
Description, as the server wrote it Retrieve a verified opt-in public profile by opaque ID; returns no private contacts or documents.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
list_agent_conversationsList bounded private conversations for this authenticated client and customer account.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_agent_conversations" says "list": a word for reading.
What it can reach
- private-dataThe name "list_agent_conversations" says "list" and "conversation": it reads messages.
- private-dataThe description's first sentence says "list" and "conversation": it reads messages.
- untrusted-inputThe name "list_agent_conversations" says "list" and "conversation": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it List bounded private conversations for this authenticated client and customer account.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
list_network_intentsConsent-only FX network discovery/handshake.No findings
Why it is in this group
- The name "list_network_intents" says "list": a word for reading.
Description, as the server wrote it Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
list_network_requestsConsent-only FX network discovery/handshake.No findings
Why it is in this group
- The name "list_network_requests" says "list": a word for reading.
Description, as the server wrote it Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
search_manufacturersSearch only verified opt-in public manufacturer projections; no availability or demand inference.No findings
Why it is in this group
- The name "search_manufacturers" says "search": a word for reading.
Description, as the server wrote it Search only verified opt-in public manufacturer projections; no availability or demand inference.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
search_opportunitiesSearch permitted abstract public opportunity profiles; private counterparties and contacts excluded.Reads private dataNo findings
Why it is in this group
- The name "search_opportunities" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "contact": it reads contacts.
Description, as the server wrote it Search permitted abstract public opportunity profiles; private counterparties and contacts excluded.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
search_productsSearch only verified opt-in public product profiles.No findings
Why it is in this group
- The name "search_products" says "search": a word for reading.
Description, as the server wrote it Search only verified opt-in public product profiles.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
search_suppliersFind public manufacturer/supplier profile candidates; existence does not establish available stock.No findings
Why it is in this group
- The name "search_suppliers" says "search": a word for reading.
Description, as the server wrote it Find public manufacturer/supplier profile candidates; existence does not establish available stock.
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.
30 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 data5
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- 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__trade-intelligence__reply_to_agent_conversation"
]
}
}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 17, 2026, 15:23 UTC, unchanged since Nov 3, 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
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://frankox.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://frankox.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (5 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://frankox.com/mcp: tools/list returned 22 tools to an anonymous client, including update_manufacturer_draft (destructive), create_agent_conversation (destructive), reply_to_agent_conversation (destructive), initiate_network_request (destructive), respond_to_network_request (destructive) and 5 more
Posture changes
- Nov 3, 2026
- Tools that change things, listed without credentials: 6 to 10
Findings
Matches of fixed checks, with the text they matched.
The server marks "request_opportunity_match" 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 "request_opportunity_match" says "request": a word for a change.
The description mentions "credential".
What this check looks forMatched text
description: "...ting a public ingress session. Send its credential in X-FrankoX-Session header. Never cust..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools8 added.+8 addedView diff
- Added:discover_network_intentsChanges things
- Added:external_business_handshakeChanges things
- Added:get_external_agent_entrypointOnly reads
- Added:get_network_requestOnly reads
- Added:initiate_network_requestDeletes or cancels
- Added:list_network_intentsOnly reads
- Added:list_network_requestsOnly reads
- Added:respond_to_network_requestDeletes or cancels
PostureRemote posture changed. Tools that change things, listed without credentials: 6 -> 10.View diff
- Tools that change things, listed without credentials: 6 to 10
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http trade-intelligence https://frankox.com/mcpclaude mcp add --transport http trade-intelligence https://frankox.com/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__trade-intelligence__search_manufacturers",
"mcp__trade-intelligence__search_products",
"mcp__trade-intelligence__search_suppliers",
"mcp__trade-intelligence__search_opportunities",
"mcp__trade-intelligence__get_public_company_profile",
"mcp__trade-intelligence__get_public_product_profile",
"mcp__trade-intelligence__get_agent_conversation",
"mcp__trade-intelligence__list_agent_conversations",
"mcp__trade-intelligence__list_network_intents",
"mcp__trade-intelligence__list_network_requests",
"mcp__trade-intelligence__get_network_request",
"mcp__trade-intelligence__get_external_agent_entrypoint"
],
"ask": [
"mcp__trade-intelligence__register_manufacturer_interest",
"mcp__trade-intelligence__create_manufacturer_draft",
"mcp__trade-intelligence__request_opportunity_match",
"mcp__trade-intelligence__discover_network_intents",
"mcp__trade-intelligence__external_business_handshake"
],
"deny": [
"mcp__trade-intelligence__update_manufacturer_draft",
"mcp__trade-intelligence__create_agent_conversation",
"mcp__trade-intelligence__reply_to_agent_conversation",
"mcp__trade-intelligence__initiate_network_request",
"mcp__trade-intelligence__respond_to_network_request"
]
}
}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 trade-intelligence. Review it before you use it.
Capability tags behind 9 rules
- mcp__trade-intelligence__search_opportunities private-data
- mcp__trade-intelligence__get_public_company_profile private-data
- mcp__trade-intelligence__get_public_product_profile private-data
- mcp__trade-intelligence__create_agent_conversation untrusted-input
- mcp__trade-intelligence__get_agent_conversation private-data, untrusted-input
- mcp__trade-intelligence__list_agent_conversations private-data, untrusted-input
- mcp__trade-intelligence__reply_to_agent_conversation untrusted-input, outbound
- mcp__trade-intelligence__initiate_network_request untrusted-input
- mcp__trade-intelligence__respond_to_network_request 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/com.frankox/trade-intelligence/verify?hash=6668bea96cb31ebb60ff6927e68ea3d4a21456309e8aa0e899af12082ea28d55" | jq -e '.changed == false'Pinned hash 6668bea96cb3, from Nov 9, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.frankox/trade-intelligence/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.frankox/trade-intelligence)Source: MCP Registry. Synced Oct 25, 2026, 19:17 UTC.
FrankoX MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the FrankoX MCP server safe?
- No scan can promise that. What its definitions show: 22 tools, 10 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 FrankoX MCP server delete data?
- Yes. 5 tools can delete, cancel or revoke something: update_manufacturer_draft, create_agent_conversation, reply_to_agent_conversation, initiate_network_request and respond_to_network_request.
Can the FrankoX 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 FrankoX MCP server have?
- 22 tools: 5 destructive, 5 write, 12 read. update_manufacturer_draft, create_agent_conversation, reply_to_agent_conversation, initiate_network_request, respond_to_network_request, register_manufacturer_interest, create_manufacturer_draft, request_opportunity_match and 14 more.
Does the FrankoX MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the FrankoX 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): reply_to_agent_conversation.
Has the FrankoX MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.