postsleuth
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mail_dns_checkA | Check the DNS records receivers use to accept or reject your mail: MX, SPF (syntax, 10-lookup limit, whether the sending IP is authorised), DKIM selector keys (presence, key size), DMARC policy and reporting, PTR with forward confirmation (FCrDNS) against myhostname. |
| postfix_configA | Delivery-relevant non-default Postfix settings from postconf -n (relayhost, TLS policy, SASL, concurrency/rate limits, queue lifetimes, domains, milters). Secret-looking values are redacted. |
| postfix_doctorA | One-call diagnosis of a Postfix server: queue summary, qshape of the deferred queue, log outcomes for the window, DNS authentication checks, and a list of findings with next steps. |
| postfix_log_statsA | Aggregate the Postfix mail log over a time window: totals (received, sent, deferred attempts, bounced, expired, smtpd rejects), per-domain outcomes, domains still failing, grouped deferral reasons and bounce causes with category and hint, and DKIM selectors seen in signing logs. |
| postfix_log_traceA | Follow one message through the log by queue ID or email address: every line for each matching queue ID (smtpd, cleanup, qmgr, smtp/local, bounce notifications) and its final status. |
| postfix_log_trendA | Per-destination deferral rate over time buckets from the mail log: sent/deferred counts and rate per bucket, plus a direction (improving / worsening / flat / insufficient_data) comparing the early vs late half of the window. Use to see whether Gmail/Outlook/etc. is getting better or worse. |
| postfix_queue_listA | List queued messages (queue ID, queue, arrival time, size, sender, recipients with delay reasons), filtered by queue, recipient domain, sender, reason text, reason category or minimum age. |
| postfix_queue_shapeA | qshape-style matrix of a queue: rows are recipient (or sender) domains, columns are message age buckets in minutes (5,10,20,...,1280+). Shows which destination is backing up and since when. |
| postfix_queue_summaryA | Summarise the Postfix queue (postqueue -j): counts per queue, top recipient and sender domains, delay reasons grouped and classified with hints, oldest message. |
| postfix_reason_categoriesA | List the failure categories postsleuth assigns to delay/bounce reasons, with the hint for each. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Most tools target distinct facets: queue_summary (counts), queue_shape (age matrix), queue_list (individual messages), log_stats (aggregate outcomes), log_trace (single-message), log_trend (per-destination trend), and mail_dns_check. The main overlap is that postfix_doctor is a one-call aggregate that duplicates much of queue_summary/log_stats/DNS, and log_stats vs log_trend share a time-window log surface, but descriptions make the boundaries workable.
Nine tools follow a consistent snake_case postfix_<subject>_<aspect> pattern (queue_list, log_trace, log_stats, reason_categories, etc.). Only mail_dns_check breaks the prefix, though it retains the same snake_case verb_noun style, making it a minor deviation rather than an inconsistency.
Ten tools is a well-scoped count for a Postfix diagnostics server, with each tool covering a distinct grain of analysis (DNS, config, queue, logs, categories, plus a doctor aggregate). No tool feels redundant padding.
The surface covers the key diagnostic lifecycle well: DNS/auth checks, config inspection, queue views at three grains, log aggregation/trace/trend, and failure categorization. The notable gap is that everything is read-only — no remediation actions such as queue flush, requeue, or delete — which an operator would likely want next.