Pipefire MCP server
ai.pipefire/pipefirepipefire.aistreamable-httpv1.2.0Scanned
Cold email for agencies: SPF, DKIM, DMARC, blacklist checks, plus campaigns and replies.
31 tools: 2 do something that can't be undone, 19 change things and 10 only read.
- Reads private data · 9
- Reads text others write · 21
- Can send data out · 2
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here do 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 Pipefire MCP server can do
The Pipefire MCP server is published by pipefire.ai, a domain the MCP Registry verified. It has 31 tools. It can do things that cannot be undone, such as sending, paying or publishing (results and redraft_reply) and create or change data (19 tools: check_domain_email_setup, check_dmarc, check_spf, check_dkim and 15 more), but cannot delete data. 10 tools only read.
9 tools read private data (check_mx, analyze_email_headers, guess_email_addresses and 6 more); 21 tools bring in text other people can write (check_domain_email_setup, check_dmarc, check_spf and 18 more); 2 tools can send data out of your system (results and redraft_reply). 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 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 10, 2026, version 1.2.0.
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.
31 tools
Can't be undone 2Claude Code: ask
redraft_replyAsk Pipefire to rewrite the draft answer to a prospect, with an instruction such as "shorter", "more casual" or "offer to send the list first".Can send data outNo findings
Why it is in this group
- The name "redraft_reply" says "reply": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "redraft_reply" says "reply": it sends or publishes something to other people.
Description, as the server wrote it Ask Pipefire to rewrite the draft answer to a prospect, with an instruction such as "shorter", "more casual" or "offer to send the list first". Returns the new draft. It does not send: get the approval link with get_reply_approval_link.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
resultsEmails sent, replies, interested leads and meetings booked between two dates (inclusive).Can send data out1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "results" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it Emails sent, replies, interested leads and meetings booked between two dates (inclusive). Dates are YYYY-MM-DD. Defaults to the last 30 days.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Changes things 19Claude Code: ask
account_summaryOverview of this Pipefire account: campaigns running, emails sent and replies this month, interested leads, and replies waiting for an answer.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 Overview of this Pipefire account: campaigns running, emails sent and replies this month, interested leads, and replies waiting for an answer. Start here.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_bimiCheck a domain's BIMI record (logo in the inbox) and whether its DMARC policy is strict enough for BIMI to show.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 Check a domain's BIMI record (logo in the inbox) and whether its DMARC policy is strict enough for BIMI to show.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_blacklistsCheck whether a domain's sending IPs, or a single IPv4 address, are listed on the major email blacklists (Spamhaus, Barracuda, SpamCop and others), with removal links.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 Check whether a domain's sending IPs, or a single IPv4 address, are listed on the major email blacklists (Spamhaus, Barracuda, SpamCop and others), with removal links.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_cold_emailScore a cold email (subject and body) out of 10 against the rules Pipefire checks its own emails with: length, reading level, the ask, subject line, and spam-filter wording.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 Score a cold email (subject and body) out of 10 against the rules Pipefire checks its own emails with: length, reading level, the ask, subject line, and spam-filter wording. Returns each issue with why it matters and how to fix it.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_dkimLook up a domain's DKIM public key, trying the selectors Google Workspace, Microsoft 365 and common senders use, plus one you name.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 Look up a domain's DKIM public key, trying the selectors Google Workspace, Microsoft 365 and common senders use, plus one you name.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_dmarcCheck a domain's DMARC record: whether one exists at _dmarc, its policy (none, quarantine, reject), whether reports are collected, and outdated tags.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 Check a domain's DMARC record: whether one exists at _dmarc, its policy (none, quarantine, reject), whether reports are collected, and outdated tags. Tells you whether the domain can be impersonated by email.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_domain_email_setupCheck whether a domain is set up to send and receive email properly: MX, SPF, DKIM and DMARC in one go, each with pass/warn/fail, what was found, and how to fix it.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 Check whether a domain is set up to send and receive email properly: MX, SPF, DKIM and DMARC in one go, each with pass/warn/fail, what was found, and how to fix it. Use when someone asks why their email goes to spam, whether their domain is set up right, or before sending cold email.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_mta_stsCheck a domain's MTA-STS policy, which forces encrypted delivery of incoming mail.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 Check a domain's MTA-STS policy, which forces encrypted delivery of incoming mail.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_spfCheck a domain's SPF record: whether it exists, is valid, stays under the 10 DNS lookup limit, and ends with a sensible all mechanism.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 Check a domain's SPF record: whether it exists, is valid, stays under the 10 DNS lookup limit, and ends with a sensible all mechanism.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
create_campaignWrite a new campaign from a short brief: who to email, where, and what you offer them.Reads text others writeNo findings
Why it is in this group
- The name "create_campaign" says "create": 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 Write a new campaign from a short brief: who to email, where, and what you offer them. Pipefire writes the email sequence (two subject-line versions), starts finding and verifying the businesses, and saves it as a DRAFT. Nothing sends until you launch it. Read it with get_campaign. Takes up to a minute.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
generate_dkim_recordFormat a DKIM public key as the TXT record to publish at selector._domainkey.yourdomain.1 finding
Why it is in this group
- The name "generate_dkim_record" says "generate": 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 "generate_dkim_record" 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 "generate_dkim_record" says "generate": a word for a change.
Description, as the server wrote it Format a DKIM public key as the TXT record to publish at selector._domainkey.yourdomain.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
generate_dmarc_recordBuild a valid DMARC TXT record (to publish at _dmarc.yourdomain) from a policy and report addresses.1 finding
Why it is in this group
- The name "generate_dmarc_record" says "generate": 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 "generate_dmarc_record" 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 "generate_dmarc_record" says "generate": a word for a change.
Description, as the server wrote it Build a valid DMARC TXT record (to publish at _dmarc.yourdomain) from a policy and report addresses.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
generate_spf_recordBuild a valid SPF TXT record for a domain from the email services it sends with, with warnings about the 10-lookup limit.1 finding
Why it is in this group
- The name "generate_spf_record" says "generate": 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 "generate_spf_record" 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 "generate_spf_record" says "generate": a word for a change.
Description, as the server wrote it Build a valid SPF TXT record for a domain from the email services it sends with, with warnings about the 10-lookup limit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
lead_sourcingHow far Pipefire has got finding the businesses for one campaign: how many found, how many with an email, how many emails checked, how many owners named, which sources they came fr…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 How far Pipefire has got finding the businesses for one campaign: how many found, how many with an email, how many emails checked, how many owners named, which sources they came from, and the latest businesses found. Use after create_campaign, or when asked how a campaign's list is coming along.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
pause_campaignStop a running campaign.No findings
Why it is in this group
- The description's first verb is "stop": a word for a change.
Description, as the server wrote it Stop a running campaign. Nothing further sends until it is resumed. Replies still arrive. Reversible with resume_campaign.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
request_lead_listWhen a prospect replies yes to a lead list, queue it: local businesses of the types they sell to, around their town, verified, as a spreadsheet and PDF on a private link.Reads text others writeNo findings
Why it is in this group
- The name "request_lead_list" says "request": 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 When a prospect replies yes to a lead list, queue it: local businesses of the types they sell to, around their town, verified, as a spreadsheet and PDF on a private link. Ready in about 30 minutes; the link appears in the conversation and get_conversation. Up to 5 a day.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
resume_campaignRestart a campaign you paused.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "restart": 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 Restart a campaign you paused. A campaign Pipefire paused to protect your sending reputation cannot be resumed from here; the answer says why.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
suggest_sending_domainsSuggest lookalike sending domains for cold email (so the main domain is never put at risk), with live .com/.net availability.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 Suggest lookalike sending domains for cold email (so the main domain is never put at risk), with live .com/.net availability. Give a business name or its website.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
test_subject_lineScore a cold email subject line out of 10: length, wording that hurts opens, and spam trigger words, with fixes.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 Score a cold email subject line out of 10: length, wording that hurts opens, and spam trigger words, with fixes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 10Show 10 read-only tools
analyze_email_headersRead the raw headers of a received email: SPF, DKIM and DMARC results, alignment, the delivery path and delays.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "analyze_email_headers" says "analyze": a word for reading.
What it can reach
- private-dataThe name "analyze_email_headers" says "analyze" and "email": it reads mail.
- private-dataThe description's first sentence says "read" and "email": it reads mail.
- untrusted-inputThe name "analyze_email_headers" says "analyze" and "email": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it Read the raw headers of a received email: SPF, DKIM and DMARC results, alignment, the delivery path and delays. Use when someone pastes headers and asks why a message went to spam or failed authentication.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_mxList a domain's mail servers (MX records) and which provider handles its email.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "mail": it reads mail.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "list" and "mail": it reads inbound email, which other people can write.
Description, as the server wrote it List a domain's mail servers (MX records) and which provider handles its email.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
fleet_statusThe sending domains and mailboxes on this Pipefire account: which are ready, which are warming (and on what day), how many emails a day they can send, and anything paused or broken…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "fleet_status" says "status": a word for reading.
What it can reach
- private-dataThe description's first sentence says "mailbox": it reads mail.
- untrusted-inputThe description's first sentence says "mailbox": it reads inbound email, which other people can write.
Description, as the server wrote it The sending domains and mailboxes on this Pipefire account: which are ready, which are warming (and on what day), how many emails a day they can send, and anything paused or broken. Pipefire buys, sets up and warms these for you.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_campaignOne campaign in full: its market, how far it has got (found, verified, contacted, replied, interested), the emails it sends (both subject-line versions of email 1), and a sample of…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_campaign" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
Description, as the server wrote it One campaign in full: its market, how far it has got (found, verified, contacted, replied, interested), the emails it sends (both subject-line versions of email 1), and a sample of the businesses it will email. Use after create_campaign to read what was written.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_conversationThe full email thread with one prospect: what was sent, what they replied, and the draft answer if one is waiting.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_conversation" says "get": a word for reading.
What it can reach
- private-dataThe name "get_conversation" says "get" and "conversation": it reads messages.
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe name "get_conversation" says "get" and "conversation": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
Description, as the server wrote it The full email thread with one prospect: what was sent, what they replied, and the draft answer if one is waiting. Sending the answer is done in the Pipefire console (link included), never from here.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_launch_linkCheck that a draft campaign has its emails and return the link to it in the Pipefire console, where the user reads the emails and presses Launch themselves.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_launch_link" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
Description, as the server wrote it Check that a draft campaign has its emails and return the link to it in the Pipefire console, where the user reads the emails and presses Launch themselves. This tool changes nothing and sends nothing.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_reply_approval_linkCheck that a draft answer is waiting on a conversation and return the link to it in the Pipefire console, where the user reads it and presses Approve to send it themselves.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_reply_approval_link" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "conversation": it reads messages.
- untrusted-inputThe name "get_reply_approval_link" says "get" and "reply": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "conversation": it reads messages, which other people can write.
Description, as the server wrote it Check that a draft answer is waiting on a conversation and return the link to it in the Pipefire console, where the user reads it and presses Approve to send it themselves. This tool changes nothing and sends nothing.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
guess_email_addressesList the likely email address formats for a person at a company domain (first@, first.last@, flast@ ...).Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- private-dataThe name "guess_email_addresses" says "email": it reads mail.
- private-dataThe description's first sentence says "list" and "email": it reads mail.
- untrusted-inputThe name "guess_email_addresses" says "email": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it List the likely email address formats for a person at a company domain (first@, first.last@, flast@ ...). Guesses only: verify before sending.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_campaignsEvery campaign on this Pipefire account with its status, market, people contacted, replies, interested leads, meetings and next send.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_campaigns" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "meeting": it reads calendars.
- untrusted-inputThe description's first sentence says "reply": it reads comments, which other people can write.
Description, as the server wrote it Every campaign on this Pipefire account with its status, market, people contacted, replies, interested leads, meetings and next send. Use the id with pause_campaign or resume_campaign.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_repliesProspect replies that need an answer, oldest first: who, which campaign, what the reply was classified as, a snippet, and whether a draft answer is ready.Reads text others writeNo findings
Why it is in this group
- The name "list_replies" says "list": a word for reading.
What it can reach
- untrusted-inputThe name "list_replies" says "list" and "reply": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "reply": it reads comments, which other people can write.
Description, as the server wrote it Prospect replies that need an answer, oldest first: who, which campaign, what the reply was classified as, a snippet, and whether a draft answer is ready. Use the id with get_conversation.
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.
378 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data9
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write21
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__pipefire__redraft_reply",
"mcp__pipefire__results"
]
}
}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, 18:27 UTC, unchanged since Nov 13, 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
- 21
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://pipefire.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://pipefire.ai
- 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 21 tools that change things (2 irreversible, 19 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://pipefire.ai/mcp: tools/list returned 31 tools to an anonymous client, including results (irreversible), redraft_reply (irreversible), check_domain_email_setup (write), check_dmarc (write), check_spf (write) and 16 more
Posture changes
- Nov 13, 2026
- Tools that change things, listed without credentials: 13 to 21
- RFC 9728 protected resource metadata: none to https://pipefire.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://pipefire.ai
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to no
Findings
Matches of fixed checks, with the text they matched.
The server marks "generate_spf_record" 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 "generate_spf_record" says "generate": a word for a change.
The server marks "generate_dmarc_record" 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 "generate_dmarc_record" says "generate": a word for a change.
The server marks "generate_dkim_record" 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 "generate_dkim_record" says "generate": a word for a change.
- Warnresults
The server marks "results" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input addresses people (input.to): what it sends cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 13 -> 21; RFC 9728 protected resource metadata: none -> https://pipefire.ai/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://pipef…View diff
- Tools that change things, listed without credentials: 13 to 21
- RFC 9728 protected resource metadata: none to https://pipefire.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://pipefire.ai
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to no
Tools15 added, 9 changed.+15 added~9 changedView diff
- Added:account_summaryChanges things
- Added:create_campaignChanges things
- Added:fleet_statusOnly reads
- Added:get_campaignOnly reads
- Added:get_conversationOnly reads
- Added:get_launch_linkOnly reads
- Added:get_reply_approval_linkOnly reads
- Added:lead_sourcingChanges things
- Added:list_campaignsOnly reads
- Added:list_repliesOnly reads
- Added:pause_campaignChanges things
- Added:redraft_replyCan't be undone
- Added:request_lead_listChanges things
- Added:resultsCan't be undone
- Added:resume_campaignChanges things
- Changed:analyze_email_headersOnly readsinputSchema
- Changed:check_blacklistsChanges thingsinputSchema
- Changed:check_cold_emailChanges thingsinputSchema
- Changed:check_domain_email_setupChanges thingsinputSchema
- Changed:generate_dkim_recordChanges thingsinputSchema
- Changed:generate_dmarc_recordChanges thingsinputSchema
- Changed:generate_spf_recordChanges thingsinputSchema
- Changed:guess_email_addressesOnly readsinputSchema
- Changed:test_subject_lineChanges thingsinputSchema
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http pipefire https://pipefire.ai/mcpclaude mcp add --transport http pipefire https://pipefire.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__pipefire__check_mx",
"mcp__pipefire__analyze_email_headers",
"mcp__pipefire__guess_email_addresses",
"mcp__pipefire__list_campaigns",
"mcp__pipefire__list_replies",
"mcp__pipefire__get_conversation",
"mcp__pipefire__fleet_status",
"mcp__pipefire__get_campaign",
"mcp__pipefire__get_launch_link",
"mcp__pipefire__get_reply_approval_link"
],
"ask": [
"mcp__pipefire__check_domain_email_setup",
"mcp__pipefire__check_dmarc",
"mcp__pipefire__check_spf",
"mcp__pipefire__check_dkim",
"mcp__pipefire__check_bimi",
"mcp__pipefire__check_mta_sts",
"mcp__pipefire__check_blacklists",
"mcp__pipefire__check_cold_email",
"mcp__pipefire__test_subject_line",
"mcp__pipefire__suggest_sending_domains",
"mcp__pipefire__generate_spf_record",
"mcp__pipefire__generate_dmarc_record",
"mcp__pipefire__generate_dkim_record",
"mcp__pipefire__account_summary",
"mcp__pipefire__results",
"mcp__pipefire__pause_campaign",
"mcp__pipefire__resume_campaign",
"mcp__pipefire__create_campaign",
"mcp__pipefire__redraft_reply",
"mcp__pipefire__request_lead_list",
"mcp__pipefire__lead_sourcing"
],
"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 pipefire. Review it before you use it.
Capability tags behind 23 rules
- mcp__pipefire__check_domain_email_setup untrusted-input
- mcp__pipefire__check_dmarc untrusted-input
- mcp__pipefire__check_spf untrusted-input
- mcp__pipefire__check_dkim untrusted-input
- mcp__pipefire__check_mx private-data, untrusted-input
- mcp__pipefire__check_bimi untrusted-input
- mcp__pipefire__check_mta_sts untrusted-input
- mcp__pipefire__check_blacklists untrusted-input
- mcp__pipefire__analyze_email_headers private-data, untrusted-input
- mcp__pipefire__suggest_sending_domains untrusted-input
- mcp__pipefire__guess_email_addresses private-data, untrusted-input
- mcp__pipefire__list_campaigns private-data, untrusted-input
- mcp__pipefire__list_replies untrusted-input
- mcp__pipefire__get_conversation private-data, untrusted-input
- mcp__pipefire__results outbound
- mcp__pipefire__resume_campaign untrusted-input
- mcp__pipefire__fleet_status private-data, untrusted-input
- mcp__pipefire__get_campaign private-data, untrusted-input
- mcp__pipefire__create_campaign untrusted-input
- mcp__pipefire__get_launch_link private-data, untrusted-input
- mcp__pipefire__redraft_reply outbound
- mcp__pipefire__get_reply_approval_link private-data, untrusted-input
- mcp__pipefire__request_lead_list 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.pipefire/pipefire/verify?hash=4c3fa6e68aea39f853e4082cbbe9eef5eba03e0c63e2320456c139a70b64ba14" | jq -e '.changed == false'Pinned hash 4c3fa6e68aea, from Nov 10, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.pipefire/pipefire/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.pipefire/pipefire)Source: MCP Registry · repository. Synced Nov 10, 2026, 20:17 UTC.
Pipefire MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Pipefire MCP server safe?
- No scan can promise that. What its definitions show: 31 tools, 21 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 Pipefire MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Pipefire MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: results and redraft_reply.
What tools does the Pipefire MCP server have?
- 31 tools: 2 irreversible, 19 write, 10 read. results, redraft_reply, check_domain_email_setup, check_dmarc, check_spf, check_dkim, check_bimi, check_mta_sts and 23 more.
Does the Pipefire MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Pipefire MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): results and redraft_reply.
Has the Pipefire MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.