Pipefire MCP server
Commit Nov 12, 2026Lets an AI client audit email deliverability, check DNS records like SPF and DMARC, and score cold email content for spam risk.
Also known as mikelovatt/pipefire-cli, pipefire-cli
- Stars
- 0
- Tools
- 16
- Downloads, 30 days
- —
- Latest version
- 1.2.0
- Last commit
- Nov 12, 2026
- License
- MIT
What is Pipefire MCP?
Pipefire lets an AI client audit email deliverability, check DNS records like SPF and DMARC, and score cold email content for spam risk. It exposes 16 tools, such as check_domain_email_setup, check_dmarc, check_spf.
Summary generated from the project's README
About Pipefire MCP server
Pipefire provides a suite of sixteen email deliverability tools designed for AI agents and terminal users. It allows developers to audit domain configurations, verify DNS records, and evaluate the risk of spam for outbound messages. The server functions as a remote MCP server via streamable HTTP, making it compatible with clients like Claude Code, Cursor, LobeHub, and Gemini CLI. It also operates as a local command line application via npx.
Users can perform technical checks on SPF, DKIM, DMARC, MX, BIMI, and MTA-STS records without needing an account or an API key. The tools include specialized functions to analyze raw email headers, check if domains appear on spam blacklists, and score cold email content or subject lines. For those using the Pipefire agency platform, the server can also interface with existing campaigns and mailboxes to draft or manage outreach. All checks are read-only and no data is stored by the server.
What you can do with it
- 1Audit domain email configurationAsk your AI agent to verify if a specific domain is correctly configured for sending email.
- 2Evaluate cold email riskHave an AI client score the spam risk of a draft email and its subject line before sending.
- 3Analyze email delivery failuresProvide raw email headers to an AI to understand why a message might have landed in spam.
Written from the project's README. Every use case is checked against a quote from it.
How to install Pipefire MCP
Formats verified 10 Nov 2026Install Pipefire MCP in Claude Code
$ claude mcp add --transport http pipefire-cli https://pipefire.ai/mcpInstall Pipefire MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"pipefire-cli": {
"url": "https://pipefire.ai/mcp"
}
}
}Install Pipefire MCP in VS Code
.vscode/mcp.json
{
"servers": {
"pipefire-cli": {
"type": "http",
"url": "https://pipefire.ai/mcp"
}
}
}Install Pipefire MCP in Codex
~/.codex/config.toml
[mcp_servers.pipefire-cli] url = "https://pipefire.ai/mcp"
Install Pipefire MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"pipefire-cli": {
"httpUrl": "https://pipefire.ai/mcp"
}
}
}Pipefire MCP tools 16
Detected from the READMEcheck_domain_email_setupcheck_dmarccheck_spfcheck_dkimcheck_mxcheck_bimicheck_mta_stscheck_blacklistsanalyze_email_headerscheck_cold_emailtest_subject_linesuggest_sending_domains
| check_domain_email_setup | — | |
| check_dmarc | — | |
| check_spf | — | |
| check_dkim | — | |
| check_mx | — | |
| check_bimi | — | |
| check_mta_sts | — | |
| check_blacklists | — | |
| analyze_email_headers | — | |
| check_cold_email | — | |
| test_subject_line | — | |
| suggest_sending_domains | — |
Show all 16 toolsShow fewer tools
guess_email_addressesgenerate_spf_recordgenerate_dmarc_recordgenerate_dkim_record
| guess_email_addresses | — | |
| generate_spf_record | — | |
| generate_dmarc_record | — | |
| generate_dkim_record | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work
- Source repository linked and reachablemikelovatt/pipefire-cli is public and reachablegithub.com/mikelovatt/pipefire-cli ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/mikelovatt/pipefire-cli ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model16 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 564 msPass
README
View on GitHubPipefire email deliverability tools
Sixteen free email deliverability tools for your AI agent and your terminal. Check a domain's SPF, DKIM, DMARC, MX, BIMI and MTA-STS records, look it up on spam blacklists, read raw email headers, score a cold email and its subject line, and build SPF, DMARC and DKIM records.
Built by Pipefire, cold email software for agencies that sets up and runs outreach for you. The SPF, DMARC and MX checks use the same code Pipefire uses to check its own sending domains, and the cold email checker scores against the same writing rules.
No account. No API key. Nothing you check is stored.
Connect it to your AI agent
It runs as a remote MCP server (streamable HTTP):
https://pipefire.ai/mcp
- LobeHub, Cline, Cursor or any MCP client: add a remote server with the URL above. See llms-install.md.
- Claude Code:
claude mcp add --transport http pipefire https://pipefire.ai/mcp - Gemini CLI:
gemini extensions install https://github.com/mikelovatt/pipefire-cli - Claude and ChatGPT: step by step at pipefire.ai/mcp-server.
Then ask in plain words, for example "Is example.com set up to send email?" or "Score this cold email before I send it".
Pipefire customers: connect the same address in Claude, ChatGPT or Manus and sign in when asked. Your assistant can then read your campaigns, replies, mailboxes and results, draft a new campaign, rewrite a reply draft and pause or resume sending. It never sends an email or launches a campaign: those stay in the Pipefire console behind your click.
Tools
Every tool is read-only. Each one also has a free web version on pipefire.ai.
| Tool | What it does | On the web |
|---|---|---|
check_domain_email_setup |
MX, SPF, DKIM and DMARC in one go, each with pass, warn or fail and how to fix it | Domain checker |
check_dmarc |
DMARC policy and reports. Tells you if the domain can be impersonated by email | DMARC checker |
check_spf |
SPF record, and whether it stays under the 10 DNS lookup limit | SPF checker |
check_dkim |
DKIM public key. Google Workspace, Microsoft 365 and common selectors are tried | DKIM checker |
check_mx |
Mail servers and which provider handles the domain's email | |
check_bimi |
BIMI logo record, and whether DMARC is strict enough for it | BIMI checker |
check_mta_sts |
MTA-STS policy, which forces encrypted delivery of incoming mail | MTA-STS checker |
check_blacklists |
Whether the domain's sending IPs, or one IPv4 address, are on the major spam blacklists | Blacklist checker |
analyze_email_headers |
Reads raw email headers: SPF, DKIM and DMARC results, alignment, hops and delays | Header analyzer |
check_cold_email |
Scores a cold email out of 10 against the rules Pipefire checks its own emails with | Cold email checker |
test_subject_line |
Scores a subject line out of 10: length, wording that hurts opens, spam triggers | Subject line tester |
suggest_sending_domains |
Lookalike sending domains, so your main domain never sends cold email | Sending domain generator |
guess_email_addresses |
Likely email address formats for a person at a company | Email permutator |
generate_spf_record |
Builds an SPF record from the services the domain sends with | SPF generator |
generate_dmarc_record |
Builds a DMARC record from a policy and a reports address | DMARC generator |
generate_dkim_record |
Formats a DKIM public key as the TXT record to publish | DKIM generator |
The server also offers a guides resource and two prompts: a full domain audit with a prioritised fix list, and "why did this land in spam?" from a message's headers.
From the terminal
The same tools as a command line app. Needs Node 18 or newer, no dependencies.
npx pipefire check example.com
| Command | What it does |
|---|---|
pipefire check <domain> |
MX, SPF, DKIM and DMARC in one go |
pipefire dmarc <domain> |
DMARC policy and reports |
pipefire spf <domain> |
SPF record and the 10 DNS lookup limit |
pipefire dkim <domain> [selector] |
DKIM public key |
pipefire mx <domain> |
Mail servers and the email provider |
pipefire bimi <domain> |
BIMI logo record |
pipefire mta-sts <domain> |
MTA-STS policy |
pipefire blacklist <domain or ip> |
Spam blacklist lookup |
pipefire headers < headers.txt |
Read raw email headers |
pipefire subject "<subject line>" |
Score a cold email subject line |
pipefire email --subject "..." < body.txt |
Score a whole cold email |
pipefire domains <brand> |
Ideas for separate cold email sending domains |
pipefire guess <first> <last> <domain> |
Likely email address formats for a person |
pipefire gen-dmarc <domain> --policy reject --rua you@x.com |
Build a DMARC record |
pipefire gen-spf google microsoft |
Build an SPF record |
Add --json to any command for raw output. Install it globally with npm install -g pipefire.
$ npx pipefire dmarc example.com
DMARC check for example.com
DMARC (policy and reports): WARN
Record: v=DMARC1;p=reject;sp=reject;adkim=s;aspf=s
Found: Policy p=reject, with no reports address.
Fix: Add rua=mailto:you@yourdomain so you receive the daily reports that show who sends as you.
How it works
Every tool calls the same code as the free tools at pipefire.ai/tools, through Pipefire's public MCP endpoint. Checks are rate limited per IP. Nothing you check is stored.
About Pipefire
Pipefire is cold email software for agencies that sets up and runs outreach for you. It buys the sending domains, sets up the mailboxes and warms them for 14 days before any cold email goes out. It finds prospects, writes the emails, sends them at a safe daily pace and sorts the replies. You approve every email before it is sent, and your company domain never sends cold email.
License
MIT
Pipefire MCP questions
How do I add Pipefire MCP to Claude Code?
Run claude mcp add --transport http pipefire-cli https://pipefire.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Pipefire MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Pipefire MCP provide?
It exposes 16 tools, including check_domain_email_setup, check_dmarc, check_spf, check_dkim, check_mx.
Do I need an account or API key to use the tools?
No, you can use the tools without an account or an API key, and nothing you check is stored.
Can the AI agent send emails for me?
No, the AI assistant can draft campaigns and replies, but it never sends an email or launches a campaign itself; those actions require your approval in the Pipefire console.
How can I connect this to my AI agent?
You can connect it to clients like LobeHub, Cline, or Cursor by adding the remote server URL, or use specific commands for Claude Code and Gemini CLI.