Skip to main content
Glama

Postmark

by io.github.pipeworx-io

Recent Alerts

recent_alerts
Read-onlyIdempotent

Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carries source, citation_uri (pipeworx:// when available), and the raw event payload. Filter by type (e.g. "sec_8k") and/or since (ISO timestamp). Set mark_read:true to flag returned events read so the next call only shows newer ones. Polls work fine; the same feed is also at GET registry.pipeworx.io/alerts.json for scripts and dashboards.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNoOptional — filter to one subscription type.
limitNoMax events to return (1-200, default 50).
sinceNoOptional ISO timestamp — return events fired_at >= this time.
mark_readNoFlag the returned events read in the same call (default false).
unread_onlyNoReturn only events where read_at is null (default false).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A3.8/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses a significant behavioral trait: setting mark_read:true flags events as read, affecting future calls. This directly contradicts the readOnlyHint=true annotation, as it involves a state change. The contradiction is serious, so the score is 1 despite the disclosure otherwise being useful.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise yet packs useful information: return payload, filter options, mark_read behavior, and an alternative access method. Every sentence contributes value, and it's front-loaded with the primary purpose, making it well-structured and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the return payload ('source, citation_uri, raw event payload'), filtering, and mark_read semantics, making it fairly complete without an output schema. It could mention the default limit or interaction with unread_only, but the essentials are there. The direct URL alternative also adds operational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents all 5 parameters with descriptions (100% coverage), so the baseline is 3. The description adds extra meaning by providing an example type ('sec_8k') and explaining that mark_read affects future calls, which goes beyond the schema's basic parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Pull fired events from your subscription feed.' It specifies the resource (subscription feed alerts), the action (pull), and provides details about the returned data. It effectively distinguishes itself from sibling tools like list_subscriptions by focusing on fired events rather than subscriptions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use the tool: for polling alerts, with filtering options, and mentions an alternative for scripts/dashboards (the direct GET URL). It doesn't explicitly contrast with sibling tools, but the context of subscription feed and alternative endpoint provides clear guidance on when this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Postmark toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3/5.0
Disambiguation2/5

The tool set mixes multiple domains (Postmark email, Pipeworx data queries, Polymarket betting, memory utilities) with several overlapping tools. ask_pipeworx and ask_pipeworx_beta are essentially identical, send/send_batch and bounces/bounce are similar, and multiple polymarket analysis tools (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker) could be confused. Despite detailed descriptions, the sheer number of query and analysis tools increases the chance of misselection.

Naming Consistency3/5

All tool names use lowercase_with_underscores, so the casing is consistent. However, there is no uniform verb_noun pattern: some start with verbs (ask, send, bounce, resolve, validate), while others are noun phrases (server, bounces, recent_alerts, entity_profile). This mixed semantic structure makes it less predictable, but the names are still readable.

Tool Count2/5

41 tools is far above the typical well-scoped range of 3-15. The server combines multiple unrelated domains—email, data lookup, prediction markets, memory, and subscriptions—resulting in a heavyweight and unfocused surface. Most of the tools would be better split into separate, purpose-specific servers.

Completeness2/5

For a server named Postmark, the email side is incomplete: there is no update server configuration, message stream management, or inbound email handling. The Pipeworx data tools provide good read coverage but lack write/management operations for entities. The inclusion of unrelated tools makes the surface feel arbitrary rather than complete for any single domain.

Resources