Predictive Maintenance MCP Server

search_documentation

Find relevant passages in machine manuals and bearing catalogs by running semantic search over PDFs, text files, and JSON resources to answer maintenance questions.

Instructions

Semantic search across all machine manuals and bearing catalogs.

Uses vector retrieval (RAG) to find the most relevant passages from
PDFs, text files, and JSON catalogs in resources/.

Backends (chosen automatically):
  - FAISS + sentence-transformers  (pip install predictive-maintenance-mcp[vector-search])
  - TF-IDF keyword search          (default, zero extra deps)

The index is built lazily on first call and cached on disk.  It is
automatically rebuilt when source files change.

Args:
    query: Natural-language question or keywords
           (e.g. "bearing 6205 geometry", "maintenance interval pump")
    top_k: Number of passages to return (default: 5)
    force_reindex: Rebuild the index even if cache is fresh (default: False)
    ctx: MCP context. Unused — see this module's docstring on logging.

Returns:
    Dictionary with ranked results, each containing text passage, source
    file, relevance score, and chunk index.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes
`top_k`	No
`force_reindex`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.13.0Oct 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations provided, the description carries the full behavioral disclosure burden. It exceeds basic expectations by revealing lazy index building, disk caching, automatic rebuild on source changes, backend fallback (FAISS vs TF-IDF), and the return format including relevance score and chunk index. It also notes the ctx parameter is unused. It does not mention potential performance impacts or error cases, but is notably transparent.

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 well-structured with clear sections: purpose, backend details, indexing behavior, arguments, and return value. Every sentence adds value—backend options, caching, parameter explanations, and return fields—without fluff. The core purpose is front-loaded in the first line.

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?

For a tool with 3 parameters, no annotations, and a provided output schema, this description is self-sufficient. It explains the search scope, retrieval algorithm, backend choices, caching behavior, parameter semantics, and return structure. It also mentions the optional dependency for the FAISS backend, making it complete for an agent to invoke correctly.

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 input schema has zero description coverage, but the description fully compensates with an Args section. It explains query with natural-language examples, top_k as 'Number of passages to return' with default, force_reindex as 'Rebuild the index even if cache is fresh', and ctx as unused. This provides complete semantic meaning beyond the bare 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 opens with 'Semantic search across all machine manuals and bearing catalogs', a specific verb+resource+scope statement. It further clarifies it uses vector retrieval (RAG) to find relevant passages from PDFs, text files, and JSON catalogs, distinguishing it from sibling tools like read_manual_excerpt or search_bearing_catalog.

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

Usage Guidelines3/5

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

The description provides clear context for usage: natural-language questions or keywords like 'bearing 6205 geometry', and explains the automated backend selection. However, it does not explicitly state when to use this tool over sibling tools such as search_bearing_catalog, nor does it mention exclusions or alternative contexts.

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

Deploy Server