Enpitech MCP server
io.github.enpitech/enpitechenpitechstreamable-httpv1.1.0Scanned
AgentReady website scans for AI agents, AI Hub search, newsletter and contact, from Enpitech.
8 tools: 1 can delete or cancel things, 1 do something that can't be undone, 5 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 3
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool 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 Enpitech MCP server can do
The Enpitech MCP server is published by the GitHub account enpitech. It has 8 tools. It can delete or cancel things (1 tool: email_agentready_report), do things that cannot be undone, such as sending, paying or publishing (submit_contact) and create or change data (5 tools: contact_form, agent_ready, agentready_scan, newsletter and 1 more). 1 tool only reads.
4 tools bring in text other people can write (submit_contact, email_agentready_report, agentready_scan and 1 more); 3 tools can send data out of your system (submit_contact, agent_ready and agentready_scan).
The fixed checks matched 4 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 19, 2026, version 1.1.0.
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.
8 tools
Deletes or cancels 1Claude Code: deny
email_agentready_reportEmails the full 22-point AgentReady report for a site that has already been scanned, and stores the submitted name, email, phone and company as a sales lead in Enpitech's CRM under…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 Emails the full 22-point AgentReady report for a site that has already been scanned, and stores the submitted name, email, phone and company as a sales lead in Enpitech's CRM under the agent-ready origin. The AgentReady view calls this tool when the user fills in the report form on the results page; it is not offered to the model. The scan is re-run server-side before the report is rendered, so the emailed report reflects the site at send time. Returns success with an emailed flag, which is false when the lead was stored but the email did not go out.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Can't be undone 1Claude Code: ask
submit_contactSends a contact enquiry to Enpitech, storing the submitted name, email, message and optional phone and company as a sales lead in Enpitech's CRM, tagged with the origin surface.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "submit_contact" says "submit": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.phone): what the tool writes goes there.
Description, as the server wrote it Sends a contact enquiry to Enpitech, storing the submitted name, email, message and optional phone and company as a sales lead in Enpitech's CRM, tagged with the origin surface. The contact form view calls this tool when the user submits the form; it can also be called directly once the user has given those details in the conversation. Every field carries a value the user actually supplied; contact_form opens the same form as a view for the user to fill in when a detail is missing.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 5Claude Code: ask
agent_readyOpens Enpitech's AgentReady scanner as a view in the conversation.Can send data out1 finding
Why it is in this group
- The description's first verb is "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "agent_ready" 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,"openWorldHint":false}; The description's first verb is "open": a word for a change.
Description, as the server wrote it Opens Enpitech's AgentReady scanner as a view in the conversation. Inside the view the scanner fetches the site's public pages and runs 22 checks across five weighted categories (Discovery & Access, Readable for Agents, Structured Data, Actions & MCP, Trust & Safety), then shows a 0-100 agent-readiness score, the per-category breakdown, and the fixes ranked by the points each would recover. Use it when the user asks how ready a website is for AI agents, their own or any site they name: how readable, accessible or usable it is to AI, to agents or to AI crawlers; whether ChatGPT or Claude can read or use it; how to show up in AI answers; or for an audit of llms.txt, robots.txt, schema.org markup or MCP support. url is optional: with no URL the scanner opens with an empty input for the user to fill in. This tool returns only the URL it was opened with; the scan runs inside the view, via agentready_scan.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
agentready_scanRuns the AgentReady scan on one site and returns the raw result, with no view.Reads text others writeCan send data out1 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "agentready_scan" 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,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Runs the AgentReady scan on one site and returns the raw result, with no view. It fetches the site's public pages and runs 22 checks across five weighted categories (Discovery & Access, Readable for Agents, Structured Data, Actions & MCP, Trust & Safety), returning a 0-100 agent-readiness score, the per-category breakdown of every check, and the top fixes ranked by the points each would recover. When bot protection blocks too many checks the result carries limited: true and the headline score is not meaningful, though the per-check breakdown still is. When the scan does not run it returns ok: false with an errorType of invalid, unreachable, timeout or ratelimited. agent_ready runs this same scan and presents it as a visual report, so this tool fits the cases a view does not: the result is wanted as data, or several sites are being compared at once. The AgentReady view also calls this tool to run its own scan. Read-only: it fetches only public pages of the site named in the call and changes nothing on it.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
contact_formOpens Enpitech's contact form as a view in the conversation, where the user types their own name, email and message, plus an optional phone number and company, and submits it.1 finding
Why it is in this group
- The description's first verb is "open": 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 "contact_form" 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,"openWorldHint":false}; The description's first verb is "open": a word for a change.
Description, as the server wrote it Opens Enpitech's contact form as a view in the conversation, where the user types their own name, email and message, plus an optional phone number and company, and submits it. Use it when the user wants to get in touch with Enpitech about frontend engineering work: frontend is the bottleneck their releases wait on; AI-generated frontend code their team cannot safely merge; senior React engineers embedded in a product team; AI features, an MCP app, or an agent-ready interface built into their product; private training for their team on AI-assisted frontend delivery or Claude Code; hosting, sponsoring or speaking at a frontend meetup. It opens a form and answers no questions. The tool itself sends nothing: it returns the contact surface the form opened on, and the enquiry is sent by submit_contact when the user submits.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
newsletterOpens a signup form for the Enpitech newsletter, about frontend, AI and how teams ship, as a view in the conversation.1 finding
Why it is in this group
- The description's first verb is "open": 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 "newsletter" 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,"openWorldHint":false}; The description's first verb is "open": a word for a change.
Description, as the server wrote it Opens a signup form for the Enpitech newsletter, about frontend, AI and how teams ship, as a view in the conversation. The user types their own email and subscribes there. Use it when the user asks to subscribe to, join or get the Enpitech newsletter. It opens a form and subscribes no one: the subscription happens only when the user submits the form.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
subscribe_newsletterSubscribes the email address the user typed into the newsletter signup view to the Enpitech newsletter, managed in Mailchimp.Reads text others writeNo findings
Why it is in this group
- The name "subscribe_newsletter" says "subscribe": 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 Subscribes the email address the user typed into the newsletter signup view to the Enpitech newsletter, managed in Mailchimp. The newsletter view calls this tool when the user submits the form; it is not offered to the model. Returns success with a status of subscribed, or pending when a confirmation email was sent first. Every newsletter email carries an unsubscribe link.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 1Show 1 read-only tool
ai_hub_searchSearches the Enpitech AI Hub, Enpitech's curated catalog of Claude Code skills, MCP servers and AI tools, and agentic workflows for frontend teams, each one used by Enpitech engine…No findings
Why it is in this group
- The name "ai_hub_search" says "search": a word for reading.
Description, as the server wrote it Searches the Enpitech AI Hub, Enpitech's curated catalog of Claude Code skills, MCP servers and AI tools, and agentic workflows for frontend teams, each one used by Enpitech engineers in production. Use it when the user wants a skill, MCP server, AI tool or workflow for a frontend task (code review, Figma to code, testing, context files, generative UI and so on), or asks what the AI Hub has. Returns matching items with a one-line take, an overview, the install command when there is one, and a link to the item's page on enpitech.dev. Read-only: it searches a published catalog and sends nothing anywhere.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- 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 private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- 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, 19:04 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
- 7
- 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 7 tools that change things (1 destructive, 1 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.enpitech.dev/mcp-app: tools/list returned 8 tools to an anonymous client, including email_agentready_report (destructive), submit_contact (irreversible), contact_form (write), agent_ready (write), agentready_scan (write) and 2 more
Findings
Matches of fixed checks, with the text they matched.
- Warncontact_form
The server marks "contact_form" 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,"openWorldHint":false}; The description's first verb is "open": a word for a change.
- Warnagent_ready
The server marks "agent_ready" 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,"openWorldHint":false}; The description's first verb is "open": a word for a change.
- Warnagentready_scan
The server marks "agentready_scan" 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,"openWorldHint":true}; The description's first verb is "run": a word for a change.
- Warnnewsletter
The server marks "newsletter" 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,"openWorldHint":false}; The description's first verb is "open": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:agent_readyChanges thingsdescription
- Changed:agentready_scanChanges thingsdescription
- Changed:email_agentready_reportDeletes or cancelsdescription
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http enpitech https://mcp.enpitech.dev/mcp-appclaude mcp add --transport http enpitech https://mcp.enpitech.dev/mcp-appRun 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__enpitech__ai_hub_search"
],
"ask": [
"mcp__enpitech__contact_form",
"mcp__enpitech__submit_contact",
"mcp__enpitech__agent_ready",
"mcp__enpitech__agentready_scan",
"mcp__enpitech__newsletter",
"mcp__enpitech__subscribe_newsletter"
],
"deny": [
"mcp__enpitech__email_agentready_report"
]
}
}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 enpitech. Review it before you use it.
Capability tags behind 5 rules
- mcp__enpitech__submit_contact untrusted-input, outbound
- mcp__enpitech__agent_ready outbound
- mcp__enpitech__email_agentready_report untrusted-input
- mcp__enpitech__agentready_scan untrusted-input, outbound
- mcp__enpitech__subscribe_newsletter 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.enpitech/enpitech/verify?hash=1836ba3766a141d3736ce9190be00cb0de719076bfe61d9cdae6bd1a1828ea17" | jq -e '.changed == false'Pinned hash 1836ba3766a1, from Nov 19, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.enpitech/enpitech/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.enpitech/enpitech)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:33 UTC.
Enpitech MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Enpitech MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 7 of which can change, send or delete something, and 4 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 Enpitech MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: email_agentready_report.
Can the Enpitech MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: submit_contact.
What tools does the Enpitech MCP server have?
- 8 tools: 1 destructive, 1 irreversible, 5 write, 1 read. email_agentready_report, submit_contact, contact_form, agent_ready, agentready_scan, newsletter, subscribe_newsletter and ai_hub_search.
Does the Enpitech MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Enpitech MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): submit_contact, agent_ready and agentready_scan.
Has the Enpitech MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.