Skip to main content
Glama
IBM

Chuk MCP Maritime Archives

by IBM

maritime_search_wrecks

Query historical shipwreck databases across VOC, EIC, UKHO, NOAA, and other archives. Filter by ship name, date range, region, cause, status, depth, flag, or vessel type.

Instructions

Search for maritime shipwreck records across all archives.

Queries wreck databases for known and suspected wreck sites. All search parameters are optional and combined with AND logic. Supports cursor-based pagination.

Archives with wreck data: - maarer: MAARER VOC Wrecks, 1595-1795 - eic: English East India Company wrecks, 1600-1874 - carreira: Portuguese Carreira da India wrecks, 1497-1835 - galleon: Spanish Manila Galleon wrecks, 1565-1815 - soic: Swedish East India Company wrecks, 1731-1813 - ukho: UK Hydrographic Office Global Wrecks, 1500-2024 - noaa: NOAA Wrecks & Obstructions (AWOIS), 1600-2024

Args: ship_name: Ship name or partial name (case-insensitive) date_range: Date range as "YYYY/YYYY" or "YYYY-MM-DD/YYYY-MM-DD" region: Geographic region filter (e.g., cape, pacific, gulf_of_mexico) cause: Loss cause filter - storm, reef, fire, battle, grounding, scuttled, collision, unknown status: Wreck discovery status - found, unfound, approximate min_depth_m: Minimum estimated depth in metres max_depth_m: Maximum estimated depth in metres min_cargo_value: Minimum cargo value in guilders flag: Vessel nationality/flag (substring match, e.g. "UK", "NL", "US") vessel_type: Vessel type classification (substring match, e.g. "liner", "warship") gp_quality: NOAA position accuracy code (1=High, 2=Medium, 3=Low, 4=Poor) archive: Restrict to specific archive - maarer, eic, carreira, galleon, soic, ukho, noaa (default: all) max_results: Maximum results per page (default: 100, max: 500) cursor: Pagination cursor from a previous result's next_cursor field output_mode: Response format - "json" (default) or "text"

Returns: JSON or text with matching wreck records and pagination metadata

Tips for LLMs: - Use region to focus on a geographic area (e.g., "cape", "pacific") - Set status="unfound" to find wrecks that have not been located - If has_more is true, pass next_cursor as cursor to get the next page - Follow up with maritime_get_wreck for full details including position - Use maritime_export_geojson to map wreck positions - Use flag to filter by nationality (e.g. "UK", "NL", "US") - Use vessel_type to filter by ship classification (e.g. "liner", "warship") - Use gp_quality=1 to find NOAA wrecks with high-accuracy positions

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ship_nameNo
date_rangeNo
regionNo
causeNo
statusNo
min_depth_mNo
max_depth_mNo
min_cargo_valueNo
flagNo
vessel_typeNo
gp_qualityNo
archiveNo
max_resultsNo
cursorNo
output_modeNojson
Behavior5/5

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

Even without annotations, the description fully discloses behavior: all params optional with AND logic, cursor-based pagination, list of archives, default and max results, return format (JSON or text), and pagination metadata. It also notes that subsequent pages are obtained via cursor.

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 well-structured with sections for archives, arguments, returns, and tips. It is front-loaded with the main purpose and uses bullet-like format. While slightly long, each sentence provides value, making it efficient for an LLM to parse.

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

Completeness5/5

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

Given 15 optional parameters, no output schema, and no annotations, the description is remarkably complete. It explains return values (pagination metadata, wreck records), lists all archives, and provides actionable tips for common use cases. No gap in essential information.

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

Parameters5/5

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

The description compensates for 0% schema description coverage by providing detailed parameter explanations (e.g., case-insensitive ship name, cause list, archive abbreviations, range formats). This adds significant meaning beyond the raw schema.

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 'Search for maritime shipwreck records across all archives' with a specific verb and resource. It distinguishes itself from sibling tools like maritime_search_vessels and maritime_search_tracks by focusing solely on wrecks.

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 provides context for when to use the tool, including tips for LLMs (e.g., set status='unfound' to find unlooted wrecks) and suggests follow-up tools like maritime_get_wreck and maritime_export_geojson. However, it lacks explicit exclusions or when-not-to-use scenarios.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/IBM/chuk-mcp-maritime-archives'

If you have feedback or need assistance with the MCP directory API, please join our Discord server