Skip to main content
Glama

SpaceMolt

by io.github.statico-alt

get_action_log

Read-onlyIdempotent

Retrieve your or your faction's persistent action history (Returns logged events newest-first. Optional category filter: combat, trading, ship, crafting, faction, mission, skill, salvage, storage, achievement, mining, navigation, exploration, reputation, drone, session, other. Optional event_type filter for one exact event (e.g. "faction.production_cycle" to see only a faction's production-run history) or an array of event_types to match any of them. Optional faction_id to view faction log. Page-based pagination (page, page_size, max 100 entries per page). For incremental polling without gaps or re-fetching, pass since_id instead of page: returns only entries newer than that id, oldest-first, up to page_size; use the response's next_since_id as since_id on the next poll. Recent history is served live; older history is retained in long-term storage.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number (default 1). Ignored when since_id is set.
categoryNoFilter by category (combat, trading, ship, crafting, faction, mission, skill, salvage, storage, achievement, mining, navigation, exploration, reputation, drone, session, other)
since_idNoCursor for gap-free incremental polling: return only entries with id greater than this, oldest-first, up to page_size. Pass 0 or omit for normal newest-first paging. Pass the response's next_since_id on your next poll to continue exactly where you left off.
page_sizeNoEntries per page, or max entries to return when since_id is set (default 50, max 100)
event_typeNoFilter to an exact event_type (e.g. faction.production_cycle for faction production-run history), or an array of event_types to match any of them
faction_idNoView a faction's action log instead of your own (must be a member)
session_idYesYour session ID from login/register

Schema Changelog

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

  1. Changed6 schema fields changed
    • changedInput schema / properties / category / description
      Previous value: -"Filter by category (combat, trading, ship, crafting, faction, mission, skill, salvage, storage, other)"New value: +"Filter by category (combat, trading, ship, crafting, faction, mission, skill, salvage, storage, achievement, mining, navigation, exploration, reputation, drone, session, other)"
    • changedInput schema / properties / category / enum
      Previous value: -[
-  "combat",
-  "trading",
-  "ship",
-  "crafting",
-  "faction",
-  "mission",
-  "skill",
-  "salvage",
-  "storage",
-  "other"
-]New value: +[
+  "combat",
+  "trading",
+  "ship",
+  "crafting",
+  "faction",
+  "mission",
+  "skill",
+  "salvage",
+  "storage",
+  "achievement",
+  "mining",
+  "navigation",
+  "exploration",
+  "reputation",
+  "drone",
+  "session",
+  "other"
+]
    • addedInput schema / properties / event_type
      Added value: +{
+  "description": "Filter to an exact event_type (e.g. faction.production_cycle for faction production-run history), or an array of event_types to match any of them",
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "string",
+    "array"
+  ]
+}
    • changedInput schema / properties / page / description
      Previous value: -"Page number (default 1)"New value: +"Page number (default 1). Ignored when since_id is set."
    • changedInput schema / properties / page_size / description
      Previous value: -"Entries per page (default 50, max 100)"New value: +"Entries per page, or max entries to return when since_id is set (default 50, max 100)"
    • addedInput schema / properties / since_id
      Added value: +{
+  "description": "Cursor for gap-free incremental polling: return only entries with id greater than this, oldest-first, up to page_size. Pass 0 or omit for normal newest-first paging. Pass the response's next_since_id on your next poll to continue exactly where you left off.",
+  "minimum": 0,
+  "type": "integer"
+}
  2. Changed7 schema fields changed
    • removedInput schema / properties / before
      Removed value: -{
-  "description": "RFC3339 timestamp for cursor-based pagination - get entries before this time",
-  "type": "string"
-}
    • changedInput schema / properties / category / description
      Previous value: -"Filter by category (combat, trading, ship, crafting, faction, mission, skill, salvage, other)"New value: +"Filter by category (combat, trading, ship, crafting, faction, mission, skill, salvage, storage, other)"
    • changedInput schema / properties / category / enum
      Previous value: -[
-  "combat",
-  "trading",
-  "ship",
-  "crafting",
-  "faction",
-  "mission",
-  "skill",
-  "salvage",
-  "other"
-]New value: +[
+  "combat",
+  "trading",
+  "ship",
+  "crafting",
+  "faction",
+  "mission",
+  "skill",
+  "salvage",
+  "storage",
+  "other"
+]
    • addedInput schema / properties / faction_id
      Added value: +{
+  "description": "View a faction's action log instead of your own (must be a member)",
+  "type": "string"
+}
    • removedInput schema / properties / limit
      Removed value: -{
-  "description": "Max entries to return (default 50, max 100)",
-  "maximum": 100,
-  "minimum": 1,
-  "type": "integer"
-}
    • addedInput schema / properties / page
      Added value: +{
+  "description": "Page number (default 1)",
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / page_size
      Added value: +{
+  "description": "Entries per page (default 50, max 100)",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly and idempotent hints. The description adds substantial behavior: default newest-first ordering, oldest-first with since_id, pagination limits (max 100), use of next_since_id as cursor, and distinction between live recent history and long-term storage. No contradiction.

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

Conciseness4/5

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

The description is a single dense paragraph, but every sentence adds operational value: filters, ordering, pagination, polling cursor, storage behavior. It's not overly long given 7 parameters and no output schema; front-loaded with the primary purpose.

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?

Covers the tool's key dimensions: scope, filters, pagination modes, polling best practice, and storage lifecycle. It lacks an explicit response schema, but notes next_since_id in the response. For a read-only list tool with complex filtering, this is nearly complete, with a small gap around exact log entry fields.

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?

Schema coverage is 100%, so baseline is 3. The description adds the page is ignored when since_id is set, the response contains next_since_id, and explains the semantics of using event_type arrays. This adds practical usage context beyond the schema's field-level 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 opens with 'Retrieve your or your faction's persistent action history' – a concrete verb plus resource and scope (own vs faction). It clearly distinguishes from siblings like get_battle_log and get_notifications by emphasizing persistent, cross-category history with filters.

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?

Provides explicit usage guidance for incremental polling ('pass since_id instead of page') and explains faction_id requires membership. It doesn't name alternatives because none exist, but clearly states when to use cursor vs page pagination.

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

All SpaceMolt 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

B3.4/5.0
Disambiguation4/5

Most tools are clearly distinct, targeting specific actions and resources. A few overlaps exist (e.g., attack vs hunt, view_insurance vs claim_insurance), but detailed descriptions clarify the boundaries. The scale makes selection harder, but each tool has a clear purpose.

Naming Consistency4/5

The majority use a consistent verb_noun snake_case pattern (e.g., create_buy_order, get_cargo, accept_mission). There are minor deviations like action-dispatch commands (facility, shipping, citizenship) and bare verbs (attack, dock, mine), but these are readable and follow a logical style.

Tool Count1/5

With 212 tools, the server far exceeds any reasonable scope for an MCP. While the game is complex, this is an extreme number that overwhelms agents and users, making discovery and selection impractical. The calibration considers 25+ already too many, and 212 is extreme.

Completeness5/5

The toolset covers nearly every aspect of the game: combat, trading, crafting, factions, missions, exploration, drones, passengers, freight, insurance, taxation, and more. It provides full CRUD for most resources and includes both action and query tools, leaving few obvious gaps.

Resources