Skip to content

Feranor Resilience MCP server

com.feranor/resilienceferanor.comstreamable-httpv1.1.4Scanned

Scan/purge hidden text & score web domains: TLS, DNS, headers, speed. Free scans, $0.01 actions.

6 tools: 1 can delete or cancel things and 5 change things.

Tools: 1 delete, 0 irreversible, 5 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 6
  • Can send data out · 0
  • 3 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Feranor Resilience MCP server can do

The Feranor Resilience MCP server is published by feranor.com, a domain the MCP Registry verified. It has 6 tools. It can delete or cancel things (1 tool: text_purge_v1) and create or change data (5 tools: domain_check_batch_v1, domain_check_v1, domain_check_score_v1, text_scan_v1 and 1 more). None of its tools only reads.

6 tools bring in text other people can write (text_purge_v1, domain_check_batch_v1, domain_check_v1 and 3 more).

The fixed checks matched 3 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 13, 2026, version 1.1.4.

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.

6 tools

Deletes or cancels 1Claude Code: deny
  • text_purge_v1Removes invisible Unicode characters and replaces homoglyphs in a text string.Reads text others write1 finding

    Why it is in this group

    • The name "text_purge_v1" says "purge": a word for removing or ending something.
    • The server marks it not destructive (destructiveHint: false), 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.

    Findings

    • Warn

      The server marks "text_purge_v1" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "text_purge_v1" says "purge": a word for removing or ending something.

      What this check looks for
    Description, as the server wrote it
    Removes invisible Unicode characters and replaces homoglyphs in a text string. Returns the cleaned text plus a before-and-after comparison. Use this tool after text_scan_v1 to fix flagged issues. Price: $0.01 per call (x402, USDC on Base). No signup, no API key.

    Annotations the server declares

    • title: Watermarked text, Purge
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: false
Changes things 5Claude Code: ask
  • domain_check_batch_v1Runs the full resilience check on up to 100 domains in a single call and returns the same scored report for each one: TLS certificate, security headers, DNS redundancy, response ti…Reads text others write1 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.

    Findings

    • Warn

      The server marks "domain_check_batch_v1" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Runs the full resilience check on up to 100 domains in a single call and returns the same scored report for each one: TLS certificate, security headers, DNS redundancy, response time, with every individual finding. Use it to audit a portfolio, to rank a list of vendors, or to re-check a fleet after a config rollout. A domain that cannot be reached is returned with its own error rather than failing the batch, and it is still charged, because the crawl was attempted. Do not use it for a single domain: domain_check_v1 is simpler and costs the same for one. Private, internal and localhost hostnames and IP addresses are rejected. Price: $0.01 per domain, dropping to $0.005 from 100 domains, up to 100 per call. One payment covers the whole batch (x402, USDC on Base). No signup, no API key.

    Annotations the server declares

    • title: Domain Resilience Check, Batch
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • domain_check_score_batch_v1Free.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 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.
    Description, as the server wrote it
    Free. Returns the overall resilience score out of 100 for up to 100 public web domains, plus the score of each category and how many findings each one raised. Use it to triage a portfolio: rank a list of domains, confirm which ones are healthy, or decide which ones are worth pulling the full report on. It tells you which categories are weak and how many issues they hold, but not what the issues are. A domain that cannot be reached is returned with its own error rather than failing the batch. Duplicates are removed. For the individual findings and the prioritised remediation list on a whole list, use domain_check_batch_v1. For a single domain, use domain_check_score_v1. Free, no payment required.

    Annotations the server declares

    • title: Domain Resilience Score, Batch
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • domain_check_score_v1Free.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 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.
    Description, as the server wrote it
    Free. Returns the overall resilience score out of 100 for a public web domain, plus the score of each category and how many findings each one raised. Use it to triage: to rank a list of domains, to confirm a domain is healthy, or to decide whether the detailed report is worth pulling. It tells you which categories are weak and how many issues they hold, but not what the issues are. For the individual findings and the prioritised remediation list, use domain_check_v1. Free, no payment required.

    Annotations the server declares

    • title: Domain Resilience Score
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • domain_check_v1Measures how resilient a public web domain is from the outside and returns a weighted score out of 100, a per-category breakdown, and prioritised findings explaining what to fix fi…Reads text others write1 finding

    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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...enticated, no ports are scanned, and no credentials are needed. Do not use it for private,..."

      What this check looks for
    Description, as the server wrote it
    Measures how resilient a public web domain is from the outside and returns a weighted score out of 100, a per-category breakdown, and prioritised findings explaining what to fix first. Use it to audit a domain you do not control, to verify a fix after deployment, or to compare several domains on the same scale. Covers TLS certificate validity and protocol version, HTTP to HTTPS redirection, HSTS, Content-Security-Policy, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, cache directives, response time, DNS redundancy, IPv6 availability, CDN detection and software version disclosure. Everything is read from the public internet: nothing is authenticated, no ports are scanned, and no credentials are needed. Do not use it for private, internal, or localhost hostnames, for IP addresses, or to test a service you need logged-in access to. For a free score without the detailed findings, use domain_check_score_v1 instead. Price: $0.01 per call (x402, USDC on Base). No signup, no API key.

    Annotations the server declares

    • title: Domain Resilience Check
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • text_scan_v1Free.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 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.
    Description, as the server wrote it
    Free. Scans a text string for invisible Unicode characters, homoglyphs, and normalization issues. Returns a risk score and a detailed report. Use this tool before text_purge_v1 to inspect suspicious content. Free, no payment required.

    Annotations the server declares

    • title: Watermarked text, Scan
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • 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.

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 write6
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:38 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
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 (1 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.feranor.com/mcp: tools/list returned 6 tools to an anonymous client, including text_purge_v1 (destructive), domain_check_batch_v1 (write), domain_check_v1 (write), domain_check_score_v1 (write), text_scan_v1 (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn1 info
  • The server marks "text_purge_v1" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "text_purge_v1" says "purge": a word for removing or ending something.

    What this check looks for
  • The server marks "domain_check_batch_v1" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...enticated, no ports are scanned, and no credentials are needed. Do not use it for private,..."

    What this check looks for

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 1.1.4. Values in angle brackets are yours to fill in.

claude mcp add --transport http resilience https://www.feranor.com/mcp
claude mcp add --transport http resilience https://www.feranor.com/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.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__resilience__domain_check_batch_v1",
      "mcp__resilience__domain_check_v1",
      "mcp__resilience__domain_check_score_v1",
      "mcp__resilience__text_scan_v1",
      "mcp__resilience__domain_check_score_batch_v1"
    ],
    "deny": [
      "mcp__resilience__text_purge_v1"
    ]
  }
}

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 resilience. Review it before you use it.

Capability tags behind 6 rules
  • mcp__resilience__text_purge_v1 untrusted-input
  • mcp__resilience__domain_check_batch_v1 untrusted-input
  • mcp__resilience__domain_check_v1 untrusted-input
  • mcp__resilience__domain_check_score_v1 untrusted-input
  • mcp__resilience__text_scan_v1 untrusted-input
  • mcp__resilience__domain_check_score_batch_v1 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.feranor/resilience/verify?hash=9cacfccc428dbc224c6f7982386eacef355f418d770807a220b89205ad734481" | jq -e '.changed == false'

Pinned hash 9cacfccc428d, from Nov 13, 2026, 05:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.feranor/resilience/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.feranor/resilience
[![Anlyon Radar](https://radar.anlyon.com/badge/com.feranor/resilience.svg)](https://radar.anlyon.com/servers/com.feranor/resilience)

Source: MCP Registry. Synced Oct 21, 2026, 17:54 UTC.

Feranor Resilience MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Feranor Resilience MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 6 of which can change, send or delete something, and 3 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 Feranor Resilience MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: text_purge_v1.

Can the Feranor Resilience 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 Feranor Resilience MCP server have?

6 tools: 1 destructive, 5 write. text_purge_v1, domain_check_batch_v1, domain_check_v1, domain_check_score_v1, text_scan_v1 and domain_check_score_batch_v1.

Does the Feranor Resilience MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Feranor Resilience MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Feranor Resilience MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.